{ "data": { "similar": [ { "grade": "A", "json": "https://www.anchorterminal.com/tools/agentcore-memory.json", "name": "Amazon Bedrock AgentCore Memory", "score": 79.7, "shared": [ "memory.store", "memory.search", "memory.user", "memory.delete" ], "slug": "agentcore-memory" }, { "grade": "BB", "json": "https://www.anchorterminal.com/tools/zep.json", "name": "Zep", "score": 74, "shared": [ "memory.store", "memory.search", "memory.user", "memory.delete" ], "slug": "zep" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/honcho.json", "name": "Honcho", "score": 64.2, "shared": [ "memory.store", "memory.search", "memory.user", "memory.delete" ], "slug": "honcho" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/supermemory.json", "name": "Supermemory API + MCP", "score": 63.8, "shared": [ "memory.store", "memory.search", "memory.user", "memory.delete" ], "slug": "supermemory" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/past-dev.json", "name": "past.dev", "score": 63.7, "shared": [ "memory.store", "memory.search", "memory.user", "memory.delete" ], "slug": "past-dev" }, { "grade": "C", "json": "https://www.anchorterminal.com/tools/hy-memory.json", "name": "Hy Memory", "score": 57.8, "shared": [ "memory.store", "memory.search", "memory.user", "memory.delete" ], "slug": "hy-memory" } ], "tool": { "slug": "tencentdb-agent-memory", "name": "TencentDB Agent Memory", "vendor": "Tencent Cloud", "vendorUrl": "https://github.com/TencentCloud/TencentDB-Agent-Memory", "kind": "http-api", "category": "agent-memory", "summary": "TencentDB Agent Memory is Tencent Cloud's MIT-licensed, self-hosted memory stack for coding agents. A proxy injects layered conversation memory, skills, wiki pages and code graphs into each request, with a team panel and HTTP API over SQLite.", "url": "https://www.anchorterminal.com/tools/tencentdb-agent-memory", "markdownUrl": "https://www.anchorterminal.com/tools/tencentdb-agent-memory.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/tencentdb-agent-memory.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/tencentdb-agent-memory.json", "repo": "https://github.com/TencentCloud/TencentDB-Agent-Memory", "license": "MIT", "transports": [ "http" ], "packages": [ { "registry": "oci", "name": "agentmemory/memory-core" }, { "registry": "oci", "name": "agentmemory/memory-hub" }, { "registry": "oci", "name": "agentmemory/memory-proxy" }, { "registry": "npm", "name": "@tencentdb-agent-memory/memory-tencentdb" }, { "registry": "npm", "name": "@tencentdb-agent-memory/memory-sdk-ts-v2" } ], "auth": "api-key", "authNotes": "Self-hosted, with no Tencent account. Agents reach memory through the proxy with a per-user key (`sk-mem-...`) sent as the Anthropic or OpenAI auth token, which the proxy checks against Memory Core. Users can hold several revocable keys, and the panel can log in through an OAuth2 identity provider. Memory Core's own bearer gate (`MEMORY_CORE_GATEWAY_API_KEY`) is empty by default, data-plane routes need only the `x-tdai-service-id` header, and the proxy's admin routes have no authentication (https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/MemoryCore/v3-api-memorycore-doc.md).", "pricing": "free", "pricingNotes": "Free under MIT, with nothing to buy and no signup. The owner pays for the LLM calls that extract L1 to L3 memory, build wiki pages and code graphs and answer through the proxy, at whichever OpenAI-compatible or Anthropic-compatible provider is configured (https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/INSTALL.md).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, install guide, API references or changelog read on 30 October 2026. Self-hosted open-source software with no paid endpoint.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 2218, "pypiWeekly": null, "asOf": "2026-10-30" }, "docsUrl": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/INSTALL.md", "openapi": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/MemoryKnowledge/openapi.yaml", "capabilities": [ "memory.store", "memory.search", "memory.user", "memory.delete", "knowledge.search" ], "tags": [ "self-hosted", "open-source", "local", "docker", "typescript", "python", "free", "no-card", "mit", "openai-compatible", "skills", "beta" ], "lastRelease": "2026-10-26", "graded": true, "anchor": { "graded": true, "score": 56, "grade": "C", "agentReady": false, "rank": 767, "ranked": true, "rankOf": 1239, "categoryRank": 14, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 68, "maintenance": 70, "payments": 60, "reliability": 51, "schema": 61, "security": 30, "transparency": 68 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 51, "points": 10.2, "reason": "Local-software reading, as software the owner runs. Official multi-architecture images (amd64 and arm64) on Docker Hub's agentmemory account, named in the changelog, with Node 22.16 or later stated for the plugin and Python 3.9 or later for the SDK. Setup still needs a git clone for the start scripts, which pull `:latest` (18 of 20). Vitest suites are declared in the package files and CONTRIBUTING.md mentions CI, but no workflow file was found at the usual paths on either branch and GitHub's Actions pages weren't readable, so a passing default branch is not confirmed (8 of 25). GitHub issues weren't readable, so open crash reports weren't counted. The changelogs list fixes for empty recall, lost memories, duplicated history and a Knowledge service that failed to start on OpenTelemetry drift, and outside pull requests (#31, #59, #79, #85) were merged into the plugin (8 of 25). Keep a Changelog with SemVer declared and upgrade notes, such as backend switches not migrating data and a v2 to v3 migration tool, but three version streams disagree (image tags 1.0.x for releases 2.0.x, the npm plugin at 1.0.3 while main's changelog stops at 0.3.6) and ROADMAP.md still says 2.0.1-beta.1 is current (9 of 15). Release 2.0.3, but the README heads the Hub 'Team Memory Beta' and the SDKs are beta-only (8 of 15).", "checked": "2026-10-30" }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 61, "points": 9.91, "reason": "API reading for a self-hosted HTTP service. The Knowledge service has an OpenAPI 3.0.3 file of 28 paths with no security scheme. Memory Core's 109 endpoints and the proxy's routes are described only in Markdown references, and the proxy's main LLM paths are outside them (10 of 25). No website and no llms.txt. The docs are Markdown in the repository and readable raw (5 of 10). Each Core endpoint states what it does, its limits and caveats, such as which deletes skip user checks, and Knowledge's tool list marks its tools read-only. The API references and the changelog are in Chinese; the README and install guide are in English (11 of 20). Zod-checked inputs with bounds (1 to 100 messages, 8,192 characters per message, `limit` up to 100) and enums for atom types, but the reference records that `version` comes back as a string from `atomic/update` and a number from `query` (10 of 15). Worked request and response examples per endpoint and error tables per module, with the three different error-message formats set out (12 of 15). `/v3` paths with v1 and v2 routes listed as deprecated, and a dated public changelog for every release since 0.1.0 (13 of 15).", "checked": "2026-10-30" }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 68, "points": 11.05, "reason": "Read with the API lines. `limit` defaults of 5 or 20 up to 100, `recall.maxResults` 5, and character budgets and a token ratio for what the proxy injects, but no field selection, and the proxy adds memory to every request's system prompt whether or not the agent asks (16 of 25). `limit` and `offset` on list and query routes, `{items, total}` on meta lists, filters by session, time range, atom type and team, agent, user and task IDs (18 of 20). HTTP codes with documented meanings (400, 401, 403, 404, 409, 422, 429, 503), but three message formats by module, `/v3/meta/auth/verify` answering 200 with `valid: false` for a bad key, and `tools/call` failing as HTTP 500 inside a `code: 0` envelope (12 of 20). Wiki and code-graph creation and knowledge upserts are idempotent by name or repository, while `/v3/session/add` is documented as not idempotent and `conversation/add` takes no idempotency key (10 of 20). Zero-configuration defaults and an interactive start script, official TypeScript and Python SDKs in beta, and agents join by changing a base URL. Header preselection for Hermes and OpenClaw needs a task ID made in the panel first (12 of 15).", "checked": "2026-10-30" }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 30, "points": 5.25, "reason": "Read as self-hosted software with a network API. Per-user `sk-mem-` keys, several per user and revocable, and OAuth2 for panel login. Against that, Memory Core's bearer gate is off by default and the .env template says setting it breaks the proxy's auth and session setup, the data plane takes team, agent and user IDs from the caller and needs only `x-tdai-service-id`, the proxy's rate-limit and session admin routes have no authentication, `/v3/instance/destroy` rests on the same unset bearer, the deploy README's defaults include an `admin` key, and the start scripts publish every port on all interfaces (8 of 30). Private-by-default assets with team, restricted and agent visibility, ACLs by user, role and agent, and read-only Knowledge tools. Data-plane deletes and `chat-memory/clear` make no user-level check and nothing asks for confirmation (8 of 20). The proxy injects stored memory, skills, imported documents and code into the system prompt, and we found no guidance on prompt injection or memory poisoning. Personal skills are private until shared after review (3 of 15). Participation logs, memory-generation logs and the raw L0 record let the operator trace what was written, and per-call analytics to ClickHouse is available but off by default (9 of 15). No SECURITY.md on either branch, no security.txt on www.tencent.com, and no disclosure route, bounty or audit named for the project. The npm plugin's postinstall runs a bash script that rewrites OpenClaw's installed files, with output sent to /dev/null (2 of 20).", "checked": "2026-10-30" }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 60, "points": 7.5, "reason": "Read with the self-hosted rule. MIT software with nothing to buy from Tencent, so 20 for pricing, 20 for a free start and 20 for use without an account. No x402, MPP or L402 (0). Memory extraction, wiki and code-graph building and the proxied model are paid to whichever LLM provider the owner configures.", "checked": "2026-10-30" }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 70, "points": 6.13, "reason": "Release 2.0.3 on 26 October 2026 by the changelog, with images tagged 1.0.3 on Docker Hub the same day, 4 days before this check (30). Seven releases in the 90 days to 30 October, 2.0.0 (3 August), 2.0.1-beta.1, 2.0.1, 2.0.2-beta.1, 2.0.2 (9 October), 2.0.3-beta.1 and 2.0.3 (20). GitHub issues and pull requests weren't readable, so reply times weren't judged. The plugin changelog credits fixes to numbered issues and outside pull requests, and the README says issues get a reply within 24 hours, which we couldn't check (10 of 25). Official TypeScript and Python SDKs exist but only as betas, the TypeScript one last published on 14 August 2026, and the Python package name differs between the changelog and its pyproject. No MCP server, so the registry line doesn't apply (6 of 15). npm packages carry registry signatures but no provenance attestations, the deploy pulls `:latest` images, no CI file was found, and 2.0.3 fixed a Knowledge service broken by OpenTelemetry dependency drift (4 of 10).", "checked": "2026-10-30" }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 68, "points": 5.95, "note": "editorial 61, provenance 75", "reason": "MIT on both branches and in npm metadata, with the codegraph and Hermes Agent code it reuses credited in the README (30 of 30). The README says new chat memory and skills are private by default and sets out what each visibility means. No privacy statement says what each layer keeps or for how long. The proxy records every turn's upstream messages and model replies, the plugin's L0 and L1 retention defaults to never, `chat-memory/clear` empties L0, L1 and profile content while keeping the asset, and switching storage backends leaves data behind (12 of 30). v1 and v2 routes are marked deprecated with removal 'planned' and no date, and known limitations promise fixes 'in the next version' without dates (6 of 20). The plugin's metrics reporting is off by default and writes to local logs only, and ClickHouse analytics are off by default and documented. Core depends on OpenTelemetry exporters, and we didn't audit whether anything exports by default. The Hermes Docker image's default model endpoint is Tencent Cloud LKE, which the README states (13 of 20).", "checked": "2026-10-30" } ], "assessment": { "date": "2026-10-30", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "Read with the API lines. `limit` defaults of 5 or 20 up to 100, `recall.maxResults` 5, and character budgets and a token ratio for what the proxy injects, but no field selection, and the proxy adds memory to every request's system prompt whether or not the agent asks (16 of 25). `limit` and `offset` on list and query routes, `{items, total}` on meta lists, filters by session, time range, atom type and team, agent, user and task IDs (18 of 20). HTTP codes with documented meanings (400, 401, 403, 404, 409, 422, 429, 503), but three message formats by module, `/v3/meta/auth/verify` answering 200 with `valid: false` for a bad key, and `tools/call` failing as HTTP 500 inside a `code: 0` envelope (12 of 20). Wiki and code-graph creation and knowledge upserts are idempotent by name or repository, while `/v3/session/add` is documented as not idempotent and `conversation/add` takes no idempotency key (10 of 20). Zero-configuration defaults and an interactive start script, official TypeScript and Python SDKs in beta, and agents join by changing a base URL. Header preselection for Hermes and OpenClaw needs a task ID made in the panel first (12 of 15).", "maintenance": "Release 2.0.3 on 26 October 2026 by the changelog, with images tagged 1.0.3 on Docker Hub the same day, 4 days before this check (30). Seven releases in the 90 days to 30 October, 2.0.0 (3 August), 2.0.1-beta.1, 2.0.1, 2.0.2-beta.1, 2.0.2 (9 October), 2.0.3-beta.1 and 2.0.3 (20). GitHub issues and pull requests weren't readable, so reply times weren't judged. The plugin changelog credits fixes to numbered issues and outside pull requests, and the README says issues get a reply within 24 hours, which we couldn't check (10 of 25). Official TypeScript and Python SDKs exist but only as betas, the TypeScript one last published on 14 August 2026, and the Python package name differs between the changelog and its pyproject. No MCP server, so the registry line doesn't apply (6 of 15). npm packages carry registry signatures but no provenance attestations, the deploy pulls `:latest` images, no CI file was found, and 2.0.3 fixed a Knowledge service broken by OpenTelemetry dependency drift (4 of 10).", "payments": "Read with the self-hosted rule. MIT software with nothing to buy from Tencent, so 20 for pricing, 20 for a free start and 20 for use without an account. No x402, MPP or L402 (0). Memory extraction, wiki and code-graph building and the proxied model are paid to whichever LLM provider the owner configures.", "reliability": "Local-software reading, as software the owner runs. Official multi-architecture images (amd64 and arm64) on Docker Hub's agentmemory account, named in the changelog, with Node 22.16 or later stated for the plugin and Python 3.9 or later for the SDK. Setup still needs a git clone for the start scripts, which pull `:latest` (18 of 20). Vitest suites are declared in the package files and CONTRIBUTING.md mentions CI, but no workflow file was found at the usual paths on either branch and GitHub's Actions pages weren't readable, so a passing default branch is not confirmed (8 of 25). GitHub issues weren't readable, so open crash reports weren't counted. The changelogs list fixes for empty recall, lost memories, duplicated history and a Knowledge service that failed to start on OpenTelemetry drift, and outside pull requests (#31, #59, #79, #85) were merged into the plugin (8 of 25). Keep a Changelog with SemVer declared and upgrade notes, such as backend switches not migrating data and a v2 to v3 migration tool, but three version streams disagree (image tags 1.0.x for releases 2.0.x, the npm plugin at 1.0.3 while main's changelog stops at 0.3.6) and ROADMAP.md still says 2.0.1-beta.1 is current (9 of 15). Release 2.0.3, but the README heads the Hub 'Team Memory Beta' and the SDKs are beta-only (8 of 15).", "schema": "API reading for a self-hosted HTTP service. The Knowledge service has an OpenAPI 3.0.3 file of 28 paths with no security scheme. Memory Core's 109 endpoints and the proxy's routes are described only in Markdown references, and the proxy's main LLM paths are outside them (10 of 25). No website and no llms.txt. The docs are Markdown in the repository and readable raw (5 of 10). Each Core endpoint states what it does, its limits and caveats, such as which deletes skip user checks, and Knowledge's tool list marks its tools read-only. The API references and the changelog are in Chinese; the README and install guide are in English (11 of 20). Zod-checked inputs with bounds (1 to 100 messages, 8,192 characters per message, `limit` up to 100) and enums for atom types, but the reference records that `version` comes back as a string from `atomic/update` and a number from `query` (10 of 15). Worked request and response examples per endpoint and error tables per module, with the three different error-message formats set out (12 of 15). `/v3` paths with v1 and v2 routes listed as deprecated, and a dated public changelog for every release since 0.1.0 (13 of 15).", "security": "Read as self-hosted software with a network API. Per-user `sk-mem-` keys, several per user and revocable, and OAuth2 for panel login. Against that, Memory Core's bearer gate is off by default and the .env template says setting it breaks the proxy's auth and session setup, the data plane takes team, agent and user IDs from the caller and needs only `x-tdai-service-id`, the proxy's rate-limit and session admin routes have no authentication, `/v3/instance/destroy` rests on the same unset bearer, the deploy README's defaults include an `admin` key, and the start scripts publish every port on all interfaces (8 of 30). Private-by-default assets with team, restricted and agent visibility, ACLs by user, role and agent, and read-only Knowledge tools. Data-plane deletes and `chat-memory/clear` make no user-level check and nothing asks for confirmation (8 of 20). The proxy injects stored memory, skills, imported documents and code into the system prompt, and we found no guidance on prompt injection or memory poisoning. Personal skills are private until shared after review (3 of 15). Participation logs, memory-generation logs and the raw L0 record let the operator trace what was written, and per-call analytics to ClickHouse is available but off by default (9 of 15). No SECURITY.md on either branch, no security.txt on www.tencent.com, and no disclosure route, bounty or audit named for the project. The npm plugin's postinstall runs a bash script that rewrites OpenClaw's installed files, with output sent to /dev/null (2 of 20).", "transparency": "MIT on both branches and in npm metadata, with the codegraph and Hermes Agent code it reuses credited in the README (30 of 30). The README says new chat memory and skills are private by default and sets out what each visibility means. No privacy statement says what each layer keeps or for how long. The proxy records every turn's upstream messages and model replies, the plugin's L0 and L1 retention defaults to never, `chat-memory/clear` empties L0, L1 and profile content while keeping the asset, and switching storage backends leaves data behind (12 of 30). v1 and v2 routes are marked deprecated with removal 'planned' and no date, and known limitations promise fixes 'in the next version' without dates (6 of 20). The plugin's metrics reporting is off by default and writes to local logs only, and ClickHouse analytics are off by default and documented. Core depends on OpenTelemetry exporters, and we didn't audit whether anything exports by default. The Hermes Docker image's default model endpoint is Tencent Cloud LKE, which the README states (13 of 20)." }, "sources": [ { "what": "README, default branch (master)", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/README.md", "seen": "2026-10-30" }, { "what": "README, main branch (OpenClaw plugin)", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/main/README.md", "seen": "2026-10-30" }, { "what": "changelog, 2.x Hub line", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/CHANGELOG.md", "seen": "2026-10-30" }, { "what": "changelog, OpenClaw plugin line", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/main/CHANGELOG.md", "seen": "2026-10-30" }, { "what": "licence", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/LICENSE", "seen": "2026-10-30" }, { "what": "installation guide", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/INSTALL.md", "seen": "2026-10-30" }, { "what": "roadmap", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/ROADMAP.md", "seen": "2026-10-30" }, { "what": "contributing guide", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/CONTRIBUTING.md", "seen": "2026-10-30" }, { "what": "Memory Core v3 API reference", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/MemoryCore/v3-api-memorycore-doc.md", "seen": "2026-10-30" }, { "what": "Memory Proxy v3 API reference", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/MemoryProxy/v3-api-memoryproxy-doc.md", "seen": "2026-10-30" }, { "what": "Memory Knowledge v3 API reference", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/MemoryKnowledge/v3-api-memoryknowledge-doc.md", "seen": "2026-10-30" }, { "what": "Knowledge OpenAPI file", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/MemoryKnowledge/openapi.yaml", "seen": "2026-10-30" }, { "what": "Memory Panel API reference", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/MemoryPanel/panel-api-doc.md", "seen": "2026-10-30" }, { "what": "deploy README, default keys", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/deploy/global-images/README.md", "seen": "2026-10-30" }, { "what": "deploy .env template, gateway key note", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/deploy/global-images/.env.example", "seen": "2026-10-30" }, { "what": "start-all.sh", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/deploy/global-images/start-all.sh", "seen": "2026-10-30" }, { "what": "start-memory-core.sh, port publishing", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/deploy/global-images/start-memory-core.sh", "seen": "2026-10-30" }, { "what": "agents README, proxy setup skill", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/agents/README.md", "seen": "2026-10-30" }, { "what": "Python SDK pyproject", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/sdk/memory-core/python/pyproject.toml", "seen": "2026-10-30" }, { "what": "Memory Core package.json", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/MemoryCore/package.json", "seen": "2026-10-30" }, { "what": "OpenClaw plugin package.json", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/main/package.json", "seen": "2026-10-30" }, { "what": "OpenClaw plugin manifest and config schema", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/main/openclaw.plugin.json", "seen": "2026-10-30" }, { "what": "plugin postinstall hook (main)", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/main/scripts/postinstall.mjs", "seen": "2026-10-30" }, { "what": "OpenClaw patch script", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/main/scripts/openclaw-after-tool-call-messages.patch.sh", "seen": "2026-10-30" }, { "what": "npm metadata, OpenClaw plugin", "url": "https://registry.npmjs.org/@tencentdb-agent-memory%2Fmemory-tencentdb", "seen": "2026-10-30" }, { "what": "npm metadata, TypeScript SDK", "url": "https://registry.npmjs.org/@tencentdb-agent-memory%2Fmemory-sdk-ts-v2", "seen": "2026-10-30" }, { "what": "npm metadata, memory-tencentdb-v2", "url": "https://registry.npmjs.org/@tencentdb-agent-memory%2Fmemory-tencentdb-v2", "seen": "2026-10-30" }, { "what": "npm weekly downloads, plugin", "url": "https://api.npmjs.org/downloads/point/last-week/@tencentdb-agent-memory/memory-tencentdb", "seen": "2026-10-30" }, { "what": "Docker Hub repositories, agentmemory", "url": "https://hub.docker.com/v2/repositories/agentmemory/", "seen": "2026-10-30" }, { "what": "Docker Hub tags, memory-core", "url": "https://hub.docker.com/v2/repositories/agentmemory/memory-core/tags/", "seen": "2026-10-30" }, { "what": "security.txt (404)", "url": "https://www.tencent.com/.well-known/security.txt", "seen": "2026-10-30" }, { "what": "RDAP for tencent.com", "url": "https://rdap.verisign.com/com/v1/domain/tencent.com", "seen": "2026-10-30" } ], "openQuestions": [ "Judgement call. Graded on the default branch's 2.x stack (Memory Core, Hub and Proxy), the surface the repository now leads with, read as kind http-api run locally. The OpenClaw plugin on npm (main branch, 2,218 downloads in the week to 29 October) is described in details, not graded on its own.", "firstReleased is 2026-03-31, the npm upload of `@tencentdb-agent-memory/memory-tencentdb` 0.1.0. The plugin changelog dates 0.1.0 to 25 March 2026, and the repository's creation date and GitHub releases weren't read.", "unchecked: GitHub issues, pull requests, Actions results, stars, contributors, releases and the repository's creation date. github.com/robots.txt couldn't be fetched (WebFetch timed out and curl to github.com is intercepted by the session's proxy), so github.com wasn't read, and api.github.com is closed to this session. Files were read from raw.githubusercontent.com.", "unchecked: whether a .github/workflows directory exists. Common workflow file names returned 404 on master, and the directory couldn't be listed.", "unchecked: the Python SDK on PyPI. pypi.org answered the project page with a bot check, and its JSON API is disallowed by robots.txt. The changelog's package name and pyproject.toml's differ.", "unchecked: any Tencent Cloud hosted version. cloud.tencent.com and www.tencentcloud.com answered with a bot check. The code mentions COS storage, STS pools, TCVDB and Tencent Cloud LKE, which suggest a hosted deployment, but no public page was read.", "unchecked: whether `/v3/internal/meta/instance-upstream/list`, which the Core reference says returns upstream API keys in plain text behind only the Layer 1 bearer, holds the proxy's upstream key in the default local deployment.", "The deploy README lists default gateway and admin keys of `local` and `admin`, while .env.example leaves the gateway key empty and start-all.sh generates a random admin key on first boot. Which default applies depends on the script path; we didn't run it.", "Project claims, not verified. The README's WideSearch, SWE-bench, AA-LCR and PersonaMem figures (up to 61.38% fewer tokens, 48% to 76% on PersonaMem) and 'we respond within 24 hours'. Blog posts repeating the figures were found; no independent reproduction. Launch-post framing about vector databases is left out.", "No deduction. The unauthenticated admin routes and default-off gate are documented by the project itself and scored under Security, not deducted, as for AgentGate's default key on 15 October." ] }, "negative": 0, "verdict": "A self-hosted team memory stack with layered recall, per-asset visibility and ACLs, documented HTTP APIs and frequent releases, 2.0.0 to 2.0.3 since August. The default deployment publishes its ports on all host interfaces with the core's bearer gate off, data-plane deletes trust a service-ID header, and the proxy's rate-limit and session admin routes have no authentication.", "bestFor": "Small teams that run several coding agents on a host they control and want shared, permissioned memory, skills and code context injected through a proxy.", "strengths": [ "MIT licence in the repository and on every npm package, with three multi-architecture Docker images on Docker Hub's agentmemory account", "Layered recall from L3 persona and L2 scenarios down to L1 atoms and raw L0 conversation, with hybrid BM25 and vector search", "Assets are private by default, with team, restricted (user, role and agent ACLs) and agent visibility, and per-user revocable keys", "Coding agents join through the proxy by changing a base URL, for Claude Code, Codex, CodeBuddy, OpenCode, DeepSeek Harness and others", "Seven releases from 2.0.0 on 3 August to 2.0.3 on 26 October 2026, each in a dated Keep a Changelog file" ], "weaknesses": [ "The core's bearer gate is off by default, and the deploy notes say enabling it breaks the proxy's auth and session setup", "Data-plane deletes and chat-memory clears make no user-level check, trusting the bearer gate and `x-tdai-service-id`, per the API reference", "The proxy's rate-limit routes (GET, PUT, DELETE) and session admin routes have no authentication, per its own API reference", "No SECURITY.md on either branch, no security.txt and no disclosure route named for the project", "The npm OpenClaw plugin's postinstall rewrites the installed OpenClaw's files with sed, output silenced, unless skipped" ], "agentNotes": [ "Set `MEMORY_CORE_GATEWAY_API_KEY`, `KNOWLEDGE_SERVICE_KEY` and a non-default admin key before exposing ports 8420, 8424, 8096 or 8125 beyond the host", "In headless runs send `x-team-id`, `x-agent-id` and `x-task-id` headers to the proxy. Without all three it falls back to an interactive picker and skips memory", "Expect every proxied turn to be stored. The proxy records upstream messages and model replies to Memory Core, and injected memory lands in your system prompt", "Check `data.valid` on `/v3/meta/auth/verify` and `data.isError` on `/v3/tools/call`. Both can fail inside a success envelope", "Retry `/v3/session/add` only on 500, 503 or a network error. The API reference says it isn't idempotent and writes a new object each call" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 56 } ], "editorialScores": { "ergonomics": 68, "maintenance": 70, "payments": 60, "reliability": 51, "schema": 61, "security": 30, "transparency": 61 }, "provenanceScore": 75, "checked": { "categories": { "ergonomics": "2026-10-30", "maintenance": "2026-10-30", "payments": "2026-10-30", "reliability": "2026-10-30", "schema": "2026-10-30", "security": "2026-10-30", "transparency": "2026-10-30" }, "last": "2026-10-30", "oldest": "2026-10-30", "stale": false, "staleAfterDays": 90 }, "scoreHistory": [ { "date": "2026-10-30", "grade": "C", "kind": "listed", "method": "0.7", "score": 56 } ] }, "connect": { "install": "git clone https://github.com/TencentCloud/TencentDB-Agent-Memory.git\ncd TencentDB-Agent-Memory/deploy/global-images\ncp .env.example .env\n./start-all.sh", "http": "export ANTHROPIC_BASE_URL=http://127.0.0.1:8096/claude-code/default\nexport ANTHROPIC_AUTH_TOKEN='\u003csk-mem- user key\u003e'\nclaude --model \u003cPROXY_UPSTREAM_MODEL\u003e" }, "letme": { "capability": "https://letme.dev/memory.store", "tool": "https://letme.dev/tencentdb-agent-memory" }, "sameCompany": [ "hy-memory", "hy3" ], "notable": [ "`@tencentdb-agent-memory/memory-tencentdb` 0.1.0, the OpenClaw plugin, reached npm on 31 March 2026, and 1.0.3 on 22 September 2026 (https://registry.npmjs.org/@tencentdb-agent-memory%2Fmemory-tencentdb)", "The default branch (master) carries the 2.x Memory Hub stack. The main branch keeps the 0.3.x OpenClaw plugin source and its own changelog (https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/main/CHANGELOG.md)", "CHANGELOG.md dates 2.0.0-beta.1, the first public release of the 2.x line, to 21 July 2026 and 2.0.3 to 26 October 2026 (https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/CHANGELOG.md)", "Docker Hub counts 81,300 pulls of agentmemory/memory-core, 90,137 of memory-hub and 58,238 of memory-proxy, read on 30 October 2026. Image tags run 1.0.0 to 1.0.3 for releases 2.0.0 to 2.0.3 (https://hub.docker.com/v2/repositories/agentmemory/)", "The README says the OpenClaw plugin cuts tokens by up to 61.38% on WideSearch and raises PersonaMem accuracy from 48% to 76%. Project-reported, not reproduced by an independent source we found (https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/main/README.md)", "The Memory Proxy API reference says its rate-limit and session admin routes have no authentication, and that two handlers' comments claim admin auth the code doesn't call (https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/MemoryProxy/v3-api-memoryproxy-doc.md)" ], "area": "agent-runtime", "details": [ { "label": "Surface graded", "value": "The default branch (master) at 2.0.3, read from raw files on 30 October 2026. Memory Core (port 8420, 109 `/v3` endpoints), the Memory Hub panel and Knowledge service (8125 and 8424) and the Memory Proxy (8096), run from Docker Hub images by the scripts in deploy/global-images. Nothing was installed or run" }, { "label": "Age", "value": "The OpenClaw plugin reached npm as 0.1.0 on 31 March 2026 (its changelog dates 0.1.0 to 25 March). The 2.x Hub line's first public release, 2.0.0-beta.1, is dated 21 July 2026 and 2.0.0 3 August 2026. The repository's creation date wasn't read" }, { "label": "How agents connect", "value": "Through the proxy, by pointing an agent's Anthropic or OpenAI base URL at it. Each turn it injects the bound agent's L2 and L3 memory, matched skills and wiki or code-graph context into the system prompt and forwards to the configured upstream model. Guides cover Claude Code, CodeBuddy, WorkBuddy, Codex, DeepSeek Harness, OpenCode, Hermes, OpenClaw and Pi" }, { "label": "Session binding", "value": "On a new session the proxy asks the user to pick a team, agent and task through the client's AskUserQuestion tool. Hermes and OpenClaw can't answer the form, so they need `x-team-id`, `x-agent-id`, `x-task-id` and a static `x-conversation-id` in their config, or the proxy passes the session through without memory" }, { "label": "Memory layers", "value": "L0 raw conversation, L1 atoms (episodic, persona and instruction), L2 scenario blocks and L3 core persona. Background workers extract each layer from the one below as thresholds are hit. Recall uses BM25, vectors and reciprocal rank fusion, capped by item count, character budget and timeout" }, { "label": "Other assets", "value": "Skills extracted from conversations and tool calls, with versions and resource files. Wiki pages built from imported documents, and code graphs of symbols, callers and impact paths built from repositories. Knowledge exposes 7 read-only wiki tools and 9 code-graph tools through `/v3/tools/list` and `/v3/tools/call`" }, { "label": "Storage", "value": "SQLite with sqlite-vec by default, on the Memory Core container volume. MongoDB is an experimental backend, off by default, and switching backends doesn't migrate data. The plugin line also supports Tencent Cloud Vector Database (TCVDB)" }, { "label": "Access control", "value": "Assets are `private` by default, or `team`, `restricted` (user, role and agent ACLs) or `agent`. A global System Admin and team Admin and Member roles. Per-user `sk-mem-` keys, several per user, revocable except the last. Data-plane routes take team, agent and user IDs from the body or headers and fall back to a `default` bucket" }, { "label": "Unauthenticated routes", "value": "Per the API references, Memory Core's bearer gate is off when its key is empty (the default), data-plane deletes and `/v3/chat-memory/clear` make no user-level check and so rest on `x-tdai-service-id` alone, and the proxy's `/v3/admin/rate-limits` and `/v3/session/*` routes have no authentication. Knowledge leaves `tools/*` and read endpoints open even with its service key set" }, { "label": "Deploy defaults", "value": "The start scripts publish ports 8420, 8096, 8125 and 8424 with Docker's `-p` and no host address, which binds all interfaces, and set the gateway host to 0.0.0.0. The deploy README says its default admin key and gateway key are only for local trials and must be replaced before exposure" }, { "label": "OpenClaw plugin", "value": "`@tencentdb-agent-memory/memory-tencentdb` (npm 1.0.3, 22 September 2026), a four-layer local memory plugin with `tdai_memory_search` and `tdai_conversation_search` tools, short-term context offload to Mermaid canvases, and a Hermes gateway on port 8420. Its npm postinstall runs a bash script that locates OpenClaw and patches its dist files with sed, keeping .bak copies" }, { "label": "SDKs", "value": "TypeScript `@tencentdb-agent-memory/memory-sdk-ts-v2` (npm latest 1.0.0-beta.1, 1.0.1-beta.1 on the beta tag, 14 August 2026) and a Python SDK whose pyproject names `tencentdb-agent-memory-sdk-python-v2` 1.0.1-beta.1, while the changelog says `pip install tencentdb-agent-memory-sdk-python`. PyPI wasn't readable" }, { "label": "What leaves the machine", "value": "Conversation text goes to the configured memory LLM for L1 to L3 extraction, skill and wiki building, and every proxied request goes to the configured upstream model. The Hermes Docker image on the main branch defaults to Tencent Cloud's LKE endpoint with DeepSeek-V3.2. Analytics export to ClickHouse and the plugin's metrics reporting are off by default" }, { "label": "Documentation language", "value": "README, INSTALL and ROADMAP in English and Chinese. CHANGELOG.md and the Memory Core, Knowledge, Proxy and Panel API references in Chinese. The Knowledge service also has an OpenAPI 3.0.3 file of 28 paths" }, { "label": "Licence", "value": "MIT, 'Copyright (C) 2026 Tencent', on both branches and in the npm metadata. The README credits code taken from colbymchenry/codegraph and from Nous Research's Hermes Agent" }, { "label": "Cost", "value": "Free software. LLM calls for extraction, wiki and code-graph building and the proxied model, and any MongoDB or ClickHouse server, are the owner's" } ], "provenance": { "legalEntity": "Tencent", "domain": "tencent.com", "domainRegistered": "1998-09-14", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/CHANGELOG.md", "securityTxt": "none", "checked": "2026-10-30", "notes": [ "LICENSE reads 'Copyright (C) 2026 Tencent. All rights reserved.' above the MIT text, and the README footer reads '© TencentDB Agent Memory Team'. No fuller legal name was found.", "The repository is in GitHub's TencentCloud organisation. The 2.0.0 changelog and main-branch links still use github.com/Tencent/TencentDB-Agent-Memory, and raw files answer at both paths. The project has no website of its own. RDAP at Verisign gives tencent.com a registration date of 14 September 1998.", "No terms or privacy policy applies beyond the MIT licence. Self-hosted, so no status page.", "security.txt returns 404 on www.tencent.com. www.tencentcloud.com answers with a bot check, so its security.txt wasn't read. Neither branch has SECURITY.md.", "github.com pages and api.github.com weren't read. github.com/robots.txt couldn't be fetched from our session, so the host was left alone, and api.github.com is closed by the session's proxy. Files were read from raw.githubusercontent.com, which has no robots.txt (404)." ], "score": 75, "checks": [ { "check": "Legal entity named", "value": "Tencent", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "tencent.com, registered 1998-09-14 (28 years)", "points": 15, "max": 15, "state": "ok" }, { "check": "Endpoint on the vendor's domain", "value": "no hosted endpoint", "points": 0, "max": 0, "state": "na" }, { "check": "Terms of service", "value": "nothing hosted, so the MIT licence stands in", "points": 10, "max": 10, "state": "ok" }, { "check": "Privacy policy", "value": "nothing hosted, not scored", "points": 0, "max": 0, "state": "na" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "People named", "value": "6 named with their role, none with a public profile", "points": 7, "max": 10, "state": "part" }, { "check": "Support route", "value": "help pages, a community", "points": 5, "max": 5, "state": "ok" } ] }, "setup": { "asOf": "2026-10-30", "agentAlone": false, "agentAloneHow": "", "credential": { "kind": "api-key", "env": "MEMORY_LLM_BASE_URL, MEMORY_LLM_API_KEY and MEMORY_LLM_MODEL for extraction, PROXY_UPSTREAM_URL, PROXY_UPSTREAM_API_KEY and PROXY_UPSTREAM_MODEL for the proxied model, then the user's sk-mem- key as ANTHROPIC_AUTH_TOKEN or the OpenAI key", "sendAs": "The agent sends its sk-mem- user key to the proxy as its Anthropic or OpenAI auth token. The proxy calls the upstream model with the operator's PROXY_UPSTREAM_API_KEY" }, "humanSteps": [ { "do": "On a machine with Docker, clone the repository, run deploy/global-images/start-all.sh and enter the two LLM groups (memory and proxy) when it asks", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/INSTALL.md" }, { "do": "Set MEMORY_CORE_GATEWAY_API_KEY, KNOWLEDGE_SERVICE_KEY and a random admin key in .env, or keep the ports on a trusted host, before anyone else can reach them", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/deploy/global-images/README.md" }, { "do": "In the panel at port 8125, create a user, a team, an agent and optionally a task, and give the agent the user's sk-mem- key", "url": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/INSTALL.md" } ], "minutes": 30, "card": "no", "freeTier": "Free and open source under MIT. The memory LLM and the proxied upstream model are paid to whichever provider the person configures, or run on a local OpenAI-compatible server.", "verification": [], "scopes": "Use a business user's sk-mem- key, not the admin key that start-all.sh prints, keep assets private unless sharing is intended, and use spend-limited keys for the memory and upstream LLM groups.", "askHuman": "Please run TencentDB Agent Memory (Tencent Cloud's free MIT memory stack) with Docker, set its gateway and knowledge keys, create a team, agent and task for me in the panel, and give me the proxy URL and a non-admin sk-mem- user key. Note that every proxied turn is stored and sent to the LLMs you configure.", "docs": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/INSTALL.md", "sources": [ "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/INSTALL.md", "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/deploy/global-images/.env.example", "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/deploy/global-images/README.md" ] }, "compliance": { "asOf": "2026-10-30", "hosting": [ "self-hosted" ], "euResidency": "unknown", "trainsOnData": "no", "retention": "unknown", "zeroRetention": "unknown", "certifications": [], "dpa": "", "trustCenter": "", "subprocessors": "", "selfHost": "yes", "sources": [ "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/README.md", "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/INSTALL.md" ] }, "humans": { "slug": "tencentdb-agent-memory", "checked": "2026-10-30", "company": "Tencent Cloud", "people": [ { "name": "Ma Huateng (Pony Ma)", "role": "Co-founder, Chairman of the Board and Chief Executive Officer, Tencent", "founder": true, "photo": "/assets/img/people/tencent-cloud-ma-huateng-pony-ma.webp", "photoSource": "https://www.tencent.com/who-we-are/our-team/", "bio": "Ma Huateng (Pony Ma) co-founded Tencent in 1998 and is its chairman and chief executive, leading the group's strategy, direction and management. Before Tencent he led research and development for an internet paging system at China Motion Telecom Development.", "bioSources": [ "https://www.tencent.com/team/ma-huateng-pony-ma/" ], "page": "/people/ma-huateng-pony-ma/" }, { "name": "Xu Chenye (Daniel Xu)", "role": "Co-founder and Chief Information Officer, Tencent", "founder": true, "photo": "/assets/img/people/tencent-cloud-xu-chenye-daniel-xu.webp", "photoSource": "https://www.tencent.com/who-we-are/our-team/", "page": "/people/xu-chenye-daniel-xu/" }, { "name": "Zhang Zhidong (Tony Zhang)", "role": "Co-founder and Advisor Emeritus, Tencent", "founder": true, "photo": "/assets/img/people/tencent-cloud-zhang-zhidong-tony-zhang.webp", "photoSource": "https://www.tencent.com/who-we-are/our-team/", "page": "/people/zhang-zhidong-tony-zhang/" }, { "name": "Chen Yidan (Charles Chen)", "role": "Co-founder and Advisor Emeritus, Tencent", "founder": true, "photo": "/assets/img/people/tencent-cloud-chen-yidan-charles-chen.webp", "photoSource": "https://www.tencent.com/who-we-are/our-team/", "bio": "Chen Yidan, also known as Charles Chen, co-founded Tencent and was its chief administrative officer. He remains an Advisor Emeritus and is founder and honorary chairman of the Tencent Charity Foundation, and he also founded the Yidan Prize Foundation.", "bioSources": [ "https://www.tencent.com/who-we-are/our-team/", "https://en.wikipedia.org/wiki/Chen_Yidan" ], "page": "/people/chen-yidan-charles-chen/" }, { "name": "Zeng Liqing (Jason Zeng)", "role": "Co-founder and Advisor Emeritus, Tencent", "founder": true, "photo": "/assets/img/people/tencent-cloud-zeng-liqing-jason-zeng.webp", "photoSource": "https://www.tencent.com/who-we-are/our-team/", "page": "/people/zeng-liqing-jason-zeng/" }, { "name": "Tong Taosang (Dowson Tong)", "role": "Senior Executive Vice President, Tencent, and President of Cloud and Smart Industries Group", "photo": "/assets/img/people/tencent-cloud-tong-taosang-dowson-tong.webp", "photoSource": "https://www.tencent.com/who-we-are/our-team/", "bio": "Dowson Tong is a senior executive vice president of Tencent and has led its Cloud and Smart Industries Group, which runs the cloud business and enterprise services, since October 2018. He earlier ran Tencent's Social Network Group, which covered QQ, and before joining Tencent worked on messaging systems at Sendmail and server development at Oracle.", "bioSources": [ "https://www.tencent.com/team/tong-taosang-dowson-tong/" ], "page": "/people/tong-taosang-dowson-tong/" } ], "peopleNote": "TencentDB Agent Memory is credited to the 'TencentDB Agent Memory Team' in its README, LICENSE and package metadata, with no named lead, read on 30 October 2026. The npm packages under the @tencentdb-agent-memory scope list five maintainer accounts (peng-zou, cloudluo, zarekzhang, yoimiyaxu and chrishuan) with no names or roles, so they aren't listed as people. Company-level people are carried over from the Octop listing (data/humans/octop.json, checked 29 October 2026), which read Tencent's management page for the five co-founders and Dowson Tong, president of the Cloud and Smart Industries Group, which runs Tencent Cloud. GitHub's contributors page wasn't read, because github.com/robots.txt couldn't be fetched from our session.", "companySocial": { "linkedin": "https://www.linkedin.com/company/tencent-cloud", "x": "https://x.com/tencentcloud", "github": "https://github.com/TencentCloud" }, "support": { "urls": [ "https://github.com/TencentCloud/TencentDB-Agent-Memory/issues", "https://github.com/TencentCloud/TencentDB-Agent-Memory/discussions" ], "community": [ { "label": "TencentDB Agent Memory Discord", "url": "https://discord.gg/dJQM6mKMF", "kind": "discord" } ] }, "sources": [ "https://raw.githubusercontent.com/TencentCloud/TencentDB-Agent-Memory/master/README.md", "https://raw.githubusercontent.com/TencentCloud/TencentDB-Agent-Memory/master/LICENSE", "https://registry.npmjs.org/@tencentdb-agent-memory%2Fmemory-tencentdb", "https://www.tencent.com/who-we-are/our-team/", "https://en.wikipedia.org/wiki/Chen_Yidan" ], "ownership": { "status": "subsidiary", "parent": "Tencent Holdings Limited", "checked": "2026-10-30", "sources": [ "https://raw.githubusercontent.com/TencentCloud/TencentDB-Agent-Memory/master/LICENSE", "https://www.tencent.com/who-we-are/our-team/", "https://www.tencent.com/investors/" ] } }, "requirements": { "card": "no", "freeTier": true, "minutes": 30, "credential": "api-key", "hosting": [ "self-hosted" ], "euResidency": "unknown", "trainsOnData": "no", "zeroRetention": "unknown", "selfHost": "yes" }, "pageJsonUrl": "https://www.anchorterminal.com/tools/tencentdb-agent-memory.json" }, "verify": { "accepts": "a page on tencent.com or one of its subdomains, a page under github.com/tencentcloud, or the README of github.com/TencentCloud/TencentDB-Agent-Memory", "badgeUrl": "https://www.anchorterminal.com/badges/tencentdb-agent-memory.svg", "body": { "slug": "tencentdb-agent-memory", "url": "the page with the badge or the link" }, "docs": "https://www.anchorterminal.com/builders/#verify", "effect": "none, it never changes a grade, rank or review", "endpoint": "https://www.anchorterminal.com/api/v1/verify", "listingUrl": "https://www.anchorterminal.com/tools/tencentdb-agent-memory", "mcpTool": "verify_listing", "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it", "snippets": { "html": "\u003ca href=\"https://www.anchorterminal.com/tools/tencentdb-agent-memory\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/tencentdb-agent-memory.svg\" alt=\"TencentDB Agent Memory on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e", "markdown": "[![TencentDB Agent Memory on Anchor Terminal](https://www.anchorterminal.com/badges/tencentdb-agent-memory.svg)](https://www.anchorterminal.com/tools/tencentdb-agent-memory)", "link": "\u003ca href=\"https://www.anchorterminal.com/tools/tencentdb-agent-memory\"\u003eTencentDB Agent Memory on Anchor Terminal\u003c/a\u003e" } } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/tools/tencentdb-agent-memory", "json": "https://www.anchorterminal.com/tools/tencentdb-agent-memory.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/tools/tencentdb-agent-memory.md", "mcp": "https://www.anchorterminal.com/mcp", "pricing": "https://www.anchorterminal.com/tools/tencentdb-agent-memory#pricing", "reviews": "https://www.anchorterminal.com/tools/tencentdb-agent-memory#reviews", "slim": "https://www.anchorterminal.com/tools/tencentdb-agent-memory.min.md" }, "markdown": "## Overview\n\n**Grade C · 56/100 · rank #767 of 1239 · #14 in Agent memory · not agent-ready · confidence medium**\n\n\nMore from Tencent Cloud, listed separately because each is its own product: [Hy Memory](https://www.anchorterminal.com/tools/hy-memory.md) (Agent memory), [Hy3](https://www.anchorterminal.com/tools/hy3.md) (Open-weight models).\n\n## Assessment\n\nA self-hosted team memory stack with layered recall, per-asset visibility and ACLs, documented HTTP APIs and frequent releases, 2.0.0 to 2.0.3 since August. The default deployment publishes its ports on all host interfaces with the core's bearer gate off, data-plane deletes trust a service-ID header, and the proxy's rate-limit and session admin routes have no authentication.\n\n## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | Tencent Cloud (https://github.com/TencentCloud/TencentDB-Agent-Memory) |\n| Kind | HTTP API |\n| Category | Agent memory (https://www.anchorterminal.com/categories/agent-memory) |\n| Transport | HTTP |\n| Auth | API key · Self-hosted, with no Tencent account. Agents reach memory through the proxy with a per-user key (`sk-mem-...`) sent as the Anthropic or OpenAI auth token, which the proxy checks against Memory Core. Users can hold several revocable keys, and the panel can log in through an OAuth2 identity provider. Memory Core's own bearer gate (`MEMORY_CORE_GATEWAY_API_KEY`) is empty by default, data-plane routes need only the `x-tdai-service-id` header, and the proxy's admin routes have no authentication (https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/MemoryCore/v3-api-memorycore-doc.md). |\n| Pricing | Free (Free · OSS) · Free under MIT, with nothing to buy and no signup. The owner pays for the LLM calls that extract L1 to L3 memory, build wiki pages and code graphs and answer through the proxy, at whichever OpenAI-compatible or Anthropic-compatible provider is configured (https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/INSTALL.md). |\n| x402 | No · No x402, MPP or L402 in the README, install guide, API references or changelog read on 30 October 2026. Self-hosted open-source software with no paid endpoint. |\n| Licence | MIT |\n| Packages | oci: `agentmemory/memory-core`; oci: `agentmemory/memory-hub`; oci: `agentmemory/memory-proxy`; npm: `@tencentdb-agent-memory/memory-tencentdb`; npm: `@tencentdb-agent-memory/memory-sdk-ts-v2` |\n| Source | https://github.com/TencentCloud/TencentDB-Agent-Memory |\n| Docs | https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/INSTALL.md |\n| llms.txt | not found |\n| Last release | 2026-10-26 |\n| npm downloads / week | 2,218 |\n| Surface graded | The default branch (master) at 2.0.3, read from raw files on 30 October 2026. Memory Core (port 8420, 109 `/v3` endpoints), the Memory Hub panel and Knowledge service (8125 and 8424) and the Memory Proxy (8096), run from Docker Hub images by the scripts in deploy/global-images. Nothing was installed or run |\n| Age | The OpenClaw plugin reached npm as 0.1.0 on 31 March 2026 (its changelog dates 0.1.0 to 25 March). The 2.x Hub line's first public release, 2.0.0-beta.1, is dated 21 July 2026 and 2.0.0 3 August 2026. The repository's creation date wasn't read |\n| How agents connect | Through the proxy, by pointing an agent's Anthropic or OpenAI base URL at it. Each turn it injects the bound agent's L2 and L3 memory, matched skills and wiki or code-graph context into the system prompt and forwards to the configured upstream model. Guides cover Claude Code, CodeBuddy, WorkBuddy, Codex, DeepSeek Harness, OpenCode, Hermes, OpenClaw and Pi |\n| Session binding | On a new session the proxy asks the user to pick a team, agent and task through the client's AskUserQuestion tool. Hermes and OpenClaw can't answer the form, so they need `x-team-id`, `x-agent-id`, `x-task-id` and a static `x-conversation-id` in their config, or the proxy passes the session through without memory |\n| Memory layers | L0 raw conversation, L1 atoms (episodic, persona and instruction), L2 scenario blocks and L3 core persona. Background workers extract each layer from the one below as thresholds are hit. Recall uses BM25, vectors and reciprocal rank fusion, capped by item count, character budget and timeout |\n| Other assets | Skills extracted from conversations and tool calls, with versions and resource files. Wiki pages built from imported documents, and code graphs of symbols, callers and impact paths built from repositories. Knowledge exposes 7 read-only wiki tools and 9 code-graph tools through `/v3/tools/list` and `/v3/tools/call` |\n| Storage | SQLite with sqlite-vec by default, on the Memory Core container volume. MongoDB is an experimental backend, off by default, and switching backends doesn't migrate data. The plugin line also supports Tencent Cloud Vector Database (TCVDB) |\n| Access control | Assets are `private` by default, or `team`, `restricted` (user, role and agent ACLs) or `agent`. A global System Admin and team Admin and Member roles. Per-user `sk-mem-` keys, several per user, revocable except the last. Data-plane routes take team, agent and user IDs from the body or headers and fall back to a `default` bucket |\n| Unauthenticated routes | Per the API references, Memory Core's bearer gate is off when its key is empty (the default), data-plane deletes and `/v3/chat-memory/clear` make no user-level check and so rest on `x-tdai-service-id` alone, and the proxy's `/v3/admin/rate-limits` and `/v3/session/*` routes have no authentication. Knowledge leaves `tools/*` and read endpoints open even with its service key set |\n| Deploy defaults | The start scripts publish ports 8420, 8096, 8125 and 8424 with Docker's `-p` and no host address, which binds all interfaces, and set the gateway host to 0.0.0.0. The deploy README says its default admin key and gateway key are only for local trials and must be replaced before exposure |\n| OpenClaw plugin | `@tencentdb-agent-memory/memory-tencentdb` (npm 1.0.3, 22 September 2026), a four-layer local memory plugin with `tdai_memory_search` and `tdai_conversation_search` tools, short-term context offload to Mermaid canvases, and a Hermes gateway on port 8420. Its npm postinstall runs a bash script that locates OpenClaw and patches its dist files with sed, keeping .bak copies |\n| SDKs | TypeScript `@tencentdb-agent-memory/memory-sdk-ts-v2` (npm latest 1.0.0-beta.1, 1.0.1-beta.1 on the beta tag, 14 August 2026) and a Python SDK whose pyproject names `tencentdb-agent-memory-sdk-python-v2` 1.0.1-beta.1, while the changelog says `pip install tencentdb-agent-memory-sdk-python`. PyPI wasn't readable |\n| What leaves the machine | Conversation text goes to the configured memory LLM for L1 to L3 extraction, skill and wiki building, and every proxied request goes to the configured upstream model. The Hermes Docker image on the main branch defaults to Tencent Cloud's LKE endpoint with DeepSeek-V3.2. Analytics export to ClickHouse and the plugin's metrics reporting are off by default |\n| Documentation language | README, INSTALL and ROADMAP in English and Chinese. CHANGELOG.md and the Memory Core, Knowledge, Proxy and Panel API references in Chinese. The Knowledge service also has an OpenAPI 3.0.3 file of 28 paths |\n| Licence | MIT, 'Copyright (C) 2026 Tencent', on both branches and in the npm metadata. The README credits code taken from colbymchenry/codegraph and from Nous Research's Hermes Agent |\n| Cost | Free software. LLM calls for extraction, wiki and code-graph building and the proxied model, and any MongoDB or ClickHouse server, are the owner's |\n| Capabilities | memory.store, memory.search, memory.user, memory.delete, knowledge.search |\n| Tags | self-hosted, open-source, local, docker, typescript, python, free, no-card, mit, openai-compatible, skills, beta |\n| JSON | https://www.anchorterminal.com/api/v1/tools/tencentdb-agent-memory.json |\n\n## Score breakdown (methodology v0.7, October 2026 research run)\n\nAssessed 2026-10-30 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. \"This run\" is each category's share of the 100 points.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 20 | 51 | 10.2 |\n| Performance | 10% | pending | pending | n/a |\n| Schema \u0026 documentation | 13% | 16.2 | 61 | 9.9 |\n| Agent ergonomics | 13% | 16.2 | 68 | 11.1 |\n| Security \u0026 auth | 14% | 17.5 | 30 | 5.2 |\n| Payments \u0026 pricing | 10% | 12.5 | 60 | 7.5 |\n| Task success | 10% | pending | pending | n/a |\n| Maintenance \u0026 community | 7% | 8.8 | 70 | 6.1 |\n| Transparency \u0026 trust (editorial 61, provenance 75) | 7% | 8.8 | 68 | 6.0 |\n| Negative events | up to −15 | up to −15 | none recorded | 0 |\n| **Total** | | | | **56 → C** |\n\n### Why each score\n\n- Reliability 51 (checked 2026-10-30): Local-software reading, as software the owner runs. Official multi-architecture images (amd64 and arm64) on Docker Hub's agentmemory account, named in the changelog, with Node 22.16 or later stated for the plugin and Python 3.9 or later for the SDK. Setup still needs a git clone for the start scripts, which pull `:latest` (18 of 20). Vitest suites are declared in the package files and CONTRIBUTING.md mentions CI, but no workflow file was found at the usual paths on either branch and GitHub's Actions pages weren't readable, so a passing default branch is not confirmed (8 of 25). GitHub issues weren't readable, so open crash reports weren't counted. The changelogs list fixes for empty recall, lost memories, duplicated history and a Knowledge service that failed to start on OpenTelemetry drift, and outside pull requests (#31, #59, #79, #85) were merged into the plugin (8 of 25). Keep a Changelog with SemVer declared and upgrade notes, such as backend switches not migrating data and a v2 to v3 migration tool, but three version streams disagree (image tags 1.0.x for releases 2.0.x, the npm plugin at 1.0.3 while main's changelog stops at 0.3.6) and ROADMAP.md still says 2.0.1-beta.1 is current (9 of 15). Release 2.0.3, but the README heads the Hub 'Team Memory Beta' and the SDKs are beta-only (8 of 15).\n- Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes.\n- Schema \u0026 documentation 61 (checked 2026-10-30): API reading for a self-hosted HTTP service. The Knowledge service has an OpenAPI 3.0.3 file of 28 paths with no security scheme. Memory Core's 109 endpoints and the proxy's routes are described only in Markdown references, and the proxy's main LLM paths are outside them (10 of 25). No website and no llms.txt. The docs are Markdown in the repository and readable raw (5 of 10). Each Core endpoint states what it does, its limits and caveats, such as which deletes skip user checks, and Knowledge's tool list marks its tools read-only. The API references and the changelog are in Chinese; the README and install guide are in English (11 of 20). Zod-checked inputs with bounds (1 to 100 messages, 8,192 characters per message, `limit` up to 100) and enums for atom types, but the reference records that `version` comes back as a string from `atomic/update` and a number from `query` (10 of 15). Worked request and response examples per endpoint and error tables per module, with the three different error-message formats set out (12 of 15). `/v3` paths with v1 and v2 routes listed as deprecated, and a dated public changelog for every release since 0.1.0 (13 of 15).\n- Agent ergonomics 68 (checked 2026-10-30): Read with the API lines. `limit` defaults of 5 or 20 up to 100, `recall.maxResults` 5, and character budgets and a token ratio for what the proxy injects, but no field selection, and the proxy adds memory to every request's system prompt whether or not the agent asks (16 of 25). `limit` and `offset` on list and query routes, `{items, total}` on meta lists, filters by session, time range, atom type and team, agent, user and task IDs (18 of 20). HTTP codes with documented meanings (400, 401, 403, 404, 409, 422, 429, 503), but three message formats by module, `/v3/meta/auth/verify` answering 200 with `valid: false` for a bad key, and `tools/call` failing as HTTP 500 inside a `code: 0` envelope (12 of 20). Wiki and code-graph creation and knowledge upserts are idempotent by name or repository, while `/v3/session/add` is documented as not idempotent and `conversation/add` takes no idempotency key (10 of 20). Zero-configuration defaults and an interactive start script, official TypeScript and Python SDKs in beta, and agents join by changing a base URL. Header preselection for Hermes and OpenClaw needs a task ID made in the panel first (12 of 15).\n- Security \u0026 auth 30 (checked 2026-10-30): Read as self-hosted software with a network API. Per-user `sk-mem-` keys, several per user and revocable, and OAuth2 for panel login. Against that, Memory Core's bearer gate is off by default and the .env template says setting it breaks the proxy's auth and session setup, the data plane takes team, agent and user IDs from the caller and needs only `x-tdai-service-id`, the proxy's rate-limit and session admin routes have no authentication, `/v3/instance/destroy` rests on the same unset bearer, the deploy README's defaults include an `admin` key, and the start scripts publish every port on all interfaces (8 of 30). Private-by-default assets with team, restricted and agent visibility, ACLs by user, role and agent, and read-only Knowledge tools. Data-plane deletes and `chat-memory/clear` make no user-level check and nothing asks for confirmation (8 of 20). The proxy injects stored memory, skills, imported documents and code into the system prompt, and we found no guidance on prompt injection or memory poisoning. Personal skills are private until shared after review (3 of 15). Participation logs, memory-generation logs and the raw L0 record let the operator trace what was written, and per-call analytics to ClickHouse is available but off by default (9 of 15). No SECURITY.md on either branch, no security.txt on www.tencent.com, and no disclosure route, bounty or audit named for the project. The npm plugin's postinstall runs a bash script that rewrites OpenClaw's installed files, with output sent to /dev/null (2 of 20).\n- Payments \u0026 pricing 60 (checked 2026-10-30): Read with the self-hosted rule. MIT software with nothing to buy from Tencent, so 20 for pricing, 20 for a free start and 20 for use without an account. No x402, MPP or L402 (0). Memory extraction, wiki and code-graph building and the proxied model are paid to whichever LLM provider the owner configures.\n- Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored.\n- Maintenance \u0026 community 70 (checked 2026-10-30): Release 2.0.3 on 26 October 2026 by the changelog, with images tagged 1.0.3 on Docker Hub the same day, 4 days before this check (30). Seven releases in the 90 days to 30 October, 2.0.0 (3 August), 2.0.1-beta.1, 2.0.1, 2.0.2-beta.1, 2.0.2 (9 October), 2.0.3-beta.1 and 2.0.3 (20). GitHub issues and pull requests weren't readable, so reply times weren't judged. The plugin changelog credits fixes to numbered issues and outside pull requests, and the README says issues get a reply within 24 hours, which we couldn't check (10 of 25). Official TypeScript and Python SDKs exist but only as betas, the TypeScript one last published on 14 August 2026, and the Python package name differs between the changelog and its pyproject. No MCP server, so the registry line doesn't apply (6 of 15). npm packages carry registry signatures but no provenance attestations, the deploy pulls `:latest` images, no CI file was found, and 2.0.3 fixed a Knowledge service broken by OpenTelemetry dependency drift (4 of 10).\n- Transparency \u0026 trust 68 (checked 2026-10-30): MIT on both branches and in npm metadata, with the codegraph and Hermes Agent code it reuses credited in the README (30 of 30). The README says new chat memory and skills are private by default and sets out what each visibility means. No privacy statement says what each layer keeps or for how long. The proxy records every turn's upstream messages and model replies, the plugin's L0 and L1 retention defaults to never, `chat-memory/clear` empties L0, L1 and profile content while keeping the asset, and switching storage backends leaves data behind (12 of 30). v1 and v2 routes are marked deprecated with removal 'planned' and no date, and known limitations promise fixes 'in the next version' without dates (6 of 20). The plugin's metrics reporting is off by default and writes to local logs only, and ClickHouse analytics are off by default and documented. Core depends on OpenTelemetry exporters, and we didn't audit whether anything exports by default. The Hermes Docker image's default model endpoint is Tencent Cloud LKE, which the README states (13 of 20).\n\nFix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (20 items): https://www.anchorterminal.com/fixes/tencentdb-agent-memory.md (JSON https://www.anchorterminal.com/fixes/tencentdb-agent-memory.json)\n\n### What we couldn't check\n\n- Judgement call. Graded on the default branch's 2.x stack (Memory Core, Hub and Proxy), the surface the repository now leads with, read as kind http-api run locally. The OpenClaw plugin on npm (main branch, 2,218 downloads in the week to 29 October) is described in details, not graded on its own.\n- firstReleased is 2026-03-31, the npm upload of `@tencentdb-agent-memory/memory-tencentdb` 0.1.0. The plugin changelog dates 0.1.0 to 25 March 2026, and the repository's creation date and GitHub releases weren't read.\n- unchecked: GitHub issues, pull requests, Actions results, stars, contributors, releases and the repository's creation date. github.com/robots.txt couldn't be fetched (WebFetch timed out and curl to github.com is intercepted by the session's proxy), so github.com wasn't read, and api.github.com is closed to this session. Files were read from raw.githubusercontent.com.\n- unchecked: whether a .github/workflows directory exists. Common workflow file names returned 404 on master, and the directory couldn't be listed.\n- unchecked: the Python SDK on PyPI. pypi.org answered the project page with a bot check, and its JSON API is disallowed by robots.txt. The changelog's package name and pyproject.toml's differ.\n- unchecked: any Tencent Cloud hosted version. cloud.tencent.com and www.tencentcloud.com answered with a bot check. The code mentions COS storage, STS pools, TCVDB and Tencent Cloud LKE, which suggest a hosted deployment, but no public page was read.\n- unchecked: whether `/v3/internal/meta/instance-upstream/list`, which the Core reference says returns upstream API keys in plain text behind only the Layer 1 bearer, holds the proxy's upstream key in the default local deployment.\n- The deploy README lists default gateway and admin keys of `local` and `admin`, while .env.example leaves the gateway key empty and start-all.sh generates a random admin key on first boot. Which default applies depends on the script path; we didn't run it.\n- Project claims, not verified. The README's WideSearch, SWE-bench, AA-LCR and PersonaMem figures (up to 61.38% fewer tokens, 48% to 76% on PersonaMem) and 'we respond within 24 hours'. Blog posts repeating the figures were found; no independent reproduction. Launch-post framing about vector databases is left out.\n- No deduction. The unauthenticated admin routes and default-off gate are documented by the project itself and scored under Security, not deducted, as for AgentGate's default key on 15 October.\n\n### Sources\n\n- README, default branch (master): \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/README.md\u003e (seen 2026-10-30)\n- README, main branch (OpenClaw plugin): \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/main/README.md\u003e (seen 2026-10-30)\n- changelog, 2.x Hub line: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/CHANGELOG.md\u003e (seen 2026-10-30)\n- changelog, OpenClaw plugin line: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/main/CHANGELOG.md\u003e (seen 2026-10-30)\n- licence: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/LICENSE\u003e (seen 2026-10-30)\n- installation guide: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/INSTALL.md\u003e (seen 2026-10-30)\n- roadmap: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/ROADMAP.md\u003e (seen 2026-10-30)\n- contributing guide: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/CONTRIBUTING.md\u003e (seen 2026-10-30)\n- Memory Core v3 API reference: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/MemoryCore/v3-api-memorycore-doc.md\u003e (seen 2026-10-30)\n- Memory Proxy v3 API reference: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/MemoryProxy/v3-api-memoryproxy-doc.md\u003e (seen 2026-10-30)\n- Memory Knowledge v3 API reference: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/MemoryKnowledge/v3-api-memoryknowledge-doc.md\u003e (seen 2026-10-30)\n- Knowledge OpenAPI file: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/MemoryKnowledge/openapi.yaml\u003e (seen 2026-10-30)\n- Memory Panel API reference: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/MemoryPanel/panel-api-doc.md\u003e (seen 2026-10-30)\n- deploy README, default keys: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/deploy/global-images/README.md\u003e (seen 2026-10-30)\n- deploy .env template, gateway key note: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/deploy/global-images/.env.example\u003e (seen 2026-10-30)\n- start-all.sh: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/deploy/global-images/start-all.sh\u003e (seen 2026-10-30)\n- start-memory-core.sh, port publishing: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/deploy/global-images/start-memory-core.sh\u003e (seen 2026-10-30)\n- agents README, proxy setup skill: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/agents/README.md\u003e (seen 2026-10-30)\n- Python SDK pyproject: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/sdk/memory-core/python/pyproject.toml\u003e (seen 2026-10-30)\n- Memory Core package.json: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/MemoryCore/package.json\u003e (seen 2026-10-30)\n- OpenClaw plugin package.json: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/main/package.json\u003e (seen 2026-10-30)\n- OpenClaw plugin manifest and config schema: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/main/openclaw.plugin.json\u003e (seen 2026-10-30)\n- plugin postinstall hook (main): \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/main/scripts/postinstall.mjs\u003e (seen 2026-10-30)\n- OpenClaw patch script: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/main/scripts/openclaw-after-tool-call-messages.patch.sh\u003e (seen 2026-10-30)\n- npm metadata, OpenClaw plugin: \u003chttps://registry.npmjs.org/@tencentdb-agent-memory%2Fmemory-tencentdb\u003e (seen 2026-10-30)\n- npm metadata, TypeScript SDK: \u003chttps://registry.npmjs.org/@tencentdb-agent-memory%2Fmemory-sdk-ts-v2\u003e (seen 2026-10-30)\n- npm metadata, memory-tencentdb-v2: \u003chttps://registry.npmjs.org/@tencentdb-agent-memory%2Fmemory-tencentdb-v2\u003e (seen 2026-10-30)\n- npm weekly downloads, plugin: \u003chttps://api.npmjs.org/downloads/point/last-week/@tencentdb-agent-memory/memory-tencentdb\u003e (seen 2026-10-30)\n- Docker Hub repositories, agentmemory: \u003chttps://hub.docker.com/v2/repositories/agentmemory/\u003e (seen 2026-10-30)\n- Docker Hub tags, memory-core: \u003chttps://hub.docker.com/v2/repositories/agentmemory/memory-core/tags/\u003e (seen 2026-10-30)\n- security.txt (404): \u003chttps://www.tencent.com/.well-known/security.txt\u003e (seen 2026-10-30)\n- RDAP for tencent.com: \u003chttps://rdap.verisign.com/com/v1/domain/tencent.com\u003e (seen 2026-10-30)\n\n## Score history\n\nEvery move of a score since the listing was graded, newest first, with its cause. A score can't move without an entry here. JSON: https://www.anchorterminal.com/api/v1/tools/tencentdb-agent-memory/history.json\n\n- 2026-10-30: graded 56 C (methodology 0.7)\n\n## Who's behind it (provenance 75/100, checked 2026-10-30)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | Tencent | 20/20 |\n| Domain age | tencent.com, registered 1998-09-14 (28 years) | 15/15 |\n| Endpoint on the vendor's domain | no hosted endpoint | n/a |\n| Terms of service | nothing hosted, so the MIT licence stands in | 10/10 |\n| Privacy policy | nothing hosted, not scored | n/a |\n| Status page | not found | 0/10 |\n| Changelog | published | 10/10 |\n| security.txt | not found | 0/10 |\n| People named | 6 named with their role, none with a public profile | 7/10 |\n| Support route | help pages, a community | 5/5 |\n\nLICENSE reads 'Copyright (C) 2026 Tencent. All rights reserved.' above the MIT text, and the README footer reads '© TencentDB Agent Memory Team'. No fuller legal name was found.\n\nThe repository is in GitHub's TencentCloud organisation. The 2.0.0 changelog and main-branch links still use github.com/Tencent/TencentDB-Agent-Memory, and raw files answer at both paths. The project has no website of its own. RDAP at Verisign gives tencent.com a registration date of 14 September 1998.\n\nNo terms or privacy policy applies beyond the MIT licence. Self-hosted, so no status page.\n\nsecurity.txt returns 404 on www.tencent.com. www.tencentcloud.com answers with a bot check, so its security.txt wasn't read. Neither branch has SECURITY.md.\n\ngithub.com pages and api.github.com weren't read. github.com/robots.txt couldn't be fetched from our session, so the host was left alone, and api.github.com is closed by the session's proxy. Files were read from raw.githubusercontent.com, which has no robots.txt (404).\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service**. Nothing is hosted by the vendor, so there are no terms of service to read. The MIT licence stands in and the check scores in full.\n\n\n**Privacy policy**. Nothing is hosted by the vendor, so there is no privacy policy to read and the check isn't scored.\n\n\n## For companies (read 2026-10-30 from the vendor's own pages)\n\n- Where data is processed: self-hosted\n- EU data residency: not stated\n- Trains on your data: no\n- Zero retention: not stated\n- Certifications: none stated\n- Self-hosting: yes\n- Retention: unknown\n\n\"Not stated\" means we couldn't find it on the vendor's pages, not that the answer is no.\n\n## Humans behind the project (researched 2026-10-30 from public pages, not part of the grade)\n\n### Key people\n\n- Ma Huateng (Pony Ma), Co-founder, Chairman of the Board and Chief Executive Officer, Tencent\n- Xu Chenye (Daniel Xu), Co-founder and Chief Information Officer, Tencent\n- Zhang Zhidong (Tony Zhang), Co-founder and Advisor Emeritus, Tencent\n- Chen Yidan (Charles Chen), Co-founder and Advisor Emeritus, Tencent\n- Zeng Liqing (Jason Zeng), Co-founder and Advisor Emeritus, Tencent\n- Tong Taosang (Dowson Tong), Senior Executive Vice President, Tencent, and President of Cloud and Smart Industries Group\n- Note: tencentdb agent memory is credited to the 'tencentdb agent memory team' in its readme, license and package metadata, with no named lead, read on 30 october 2026. the npm packages under the @tencentdb-agent-memory scope list five maintainer accounts (peng-zou, cloudluo, zarekzhang, yoimiyaxu and chrishuan) with no names or roles, so they aren't listed as people. company-level people are carried over from the octop listing (data/humans/octop.json, checked 29 october 2026), which read tencent's management page for the five co-founders and dowson tong, president of the cloud and smart industries group, which runs tencent cloud. github's contributors page wasn't read, because github.com/robots.txt couldn't be fetched from our session.\n- Tencent Cloud: LinkedIn https://www.linkedin.com/company/tencent-cloud X https://x.com/tencentcloud GitHub https://github.com/TencentCloud\n\n### Ownership and investors\n\n- Ownership: Part of Tencent Holdings Limited\n\n### Getting support\n\n- Discord: https://discord.gg/dJQM6mKMF\n- Help: https://github.com/TencentCloud/TencentDB-Agent-Memory/issues\n- Help: https://github.com/TencentCloud/TencentDB-Agent-Memory/discussions\n- Sources: https://raw.githubusercontent.com/TencentCloud/TencentDB-Agent-Memory/master/README.md, https://raw.githubusercontent.com/TencentCloud/TencentDB-Agent-Memory/master/LICENSE, https://registry.npmjs.org/@tencentdb-agent-memory%2Fmemory-tencentdb, https://www.tencent.com/who-we-are/our-team/, https://en.wikipedia.org/wiki/Chen_Yidan\n\n## Probe metrics\n\nNot measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.\n\n## Strengths\n\n- MIT licence in the repository and on every npm package, with three multi-architecture Docker images on Docker Hub's agentmemory account\n- Layered recall from L3 persona and L2 scenarios down to L1 atoms and raw L0 conversation, with hybrid BM25 and vector search\n- Assets are private by default, with team, restricted (user, role and agent ACLs) and agent visibility, and per-user revocable keys\n- Coding agents join through the proxy by changing a base URL, for Claude Code, Codex, CodeBuddy, OpenCode, DeepSeek Harness and others\n- Seven releases from 2.0.0 on 3 August to 2.0.3 on 26 October 2026, each in a dated Keep a Changelog file\n\n## Weaknesses\n\n- The core's bearer gate is off by default, and the deploy notes say enabling it breaks the proxy's auth and session setup\n- Data-plane deletes and chat-memory clears make no user-level check, trusting the bearer gate and `x-tdai-service-id`, per the API reference\n- The proxy's rate-limit routes (GET, PUT, DELETE) and session admin routes have no authentication, per its own API reference\n- No SECURITY.md on either branch, no security.txt and no disclosure route named for the project\n- The npm OpenClaw plugin's postinstall rewrites the installed OpenClaw's files with sed, output silenced, unless skipped\n\n\n\n## Before you call it (notes for agents)\n\n1. Set `MEMORY_CORE_GATEWAY_API_KEY`, `KNOWLEDGE_SERVICE_KEY` and a non-default admin key before exposing ports 8420, 8424, 8096 or 8125 beyond the host\n2. In headless runs send `x-team-id`, `x-agent-id` and `x-task-id` headers to the proxy. Without all three it falls back to an interactive picker and skips memory\n3. Expect every proxied turn to be stored. The proxy records upstream messages and model replies to Memory Core, and injected memory lands in your system prompt\n4. Check `data.valid` on `/v3/meta/auth/verify` and `data.isError` on `/v3/tools/call`. Both can fail inside a success envelope\n5. Retry `/v3/session/add` only on 500, 503 or a network error. The API reference says it isn't idempotent and writes a new object each call\n\n## Getting set up (needs a person once, about 30 minutes, read 2026-10-30)\n\n1. On a machine with Docker, clone the repository, run deploy/global-images/start-all.sh and enter the two LLM groups (memory and proxy) when it asks (https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/INSTALL.md)\n2. Set MEMORY_CORE_GATEWAY_API_KEY, KNOWLEDGE_SERVICE_KEY and a random admin key in .env, or keep the ports on a trusted host, before anyone else can reach them (https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/deploy/global-images/README.md)\n3. In the panel at port 8125, create a user, a team, an agent and optionally a task, and give the agent the user's sk-mem- key (https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/INSTALL.md)\n- Card: no card. Free: Free and open source under MIT. The memory LLM and the proxied upstream model are paid to whichever provider the person configures, or run on a local OpenAI-compatible server.\n- Credential: api-key as `MEMORY_LLM_BASE_URL, MEMORY_LLM_API_KEY and MEMORY_LLM_MODEL for extraction, PROXY_UPSTREAM_URL, PROXY_UPSTREAM_API_KEY and PROXY_UPSTREAM_MODEL for the proxied model, then the user's sk-mem- key as ANTHROPIC_AUTH_TOKEN or the OpenAI key`, The agent sends its sk-mem- user key to the proxy as its Anthropic or OpenAI auth token. The proxy calls the upstream model with the operator's PROXY_UPSTREAM_API_KEY\n- Least privilege: Use a business user's sk-mem- key, not the admin key that start-all.sh prints, keep assets private unless sharing is intended, and use spend-limited keys for the memory and upstream LLM groups.\n- Ask your human: \"Please run TencentDB Agent Memory (Tencent Cloud's free MIT memory stack) with Docker, set its gateway and knowledge keys, create a team, agent and task for me in the panel, and give me the proxy URL and a non-admin sk-mem- user key. Note that every proxied turn is stored and sent to the LLMs you configure.\"\n- Quickstart: https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/INSTALL.md\n\n## Connect\n\nInstall:\n\n```bash\ngit clone https://github.com/TencentCloud/TencentDB-Agent-Memory.git\ncd TencentDB-Agent-Memory/deploy/global-images\ncp .env.example .env\n./start-all.sh\n```\n\nFirst request:\n\n```bash\nexport ANTHROPIC_BASE_URL=http://127.0.0.1:8096/claude-code/default\nexport ANTHROPIC_AUTH_TOKEN='\u003csk-mem- user key\u003e'\nclaude --model \u003cPROXY_UPSTREAM_MODEL\u003e\n```\n\nThrough letme: https://letme.dev/tencentdb-agent-memory. letme answers with the pick and how to call it direct. How it works: https://www.anchorterminal.com/letme/index.md\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| Amazon Bedrock AgentCore Memory | A | 79.7 | 10 | memory.store, memory.search, memory.user, memory.delete | no | https://www.anchorterminal.com/tools/agentcore-memory.md |\n| Zep | BB | 74 | 83 | memory.store, memory.search, memory.user, memory.delete | no | https://www.anchorterminal.com/tools/zep.md |\n| Honcho | B | 64.2 | 422 | memory.store, memory.search, memory.user, memory.delete | yes | https://www.anchorterminal.com/tools/honcho.md |\n| Supermemory API + MCP | B | 63.8 | 438 | memory.store, memory.search, memory.user, memory.delete | no | https://www.anchorterminal.com/tools/supermemory.md |\n| past.dev | B | 63.7 | 441 | memory.store, memory.search, memory.user, memory.delete | no | https://www.anchorterminal.com/tools/past-dev.md |\n| Hy Memory | C | 57.8 | 701 | memory.store, memory.search, memory.user, memory.delete | no | https://www.anchorterminal.com/tools/hy-memory.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md\n\n## Notable\n\n- `@tencentdb-agent-memory/memory-tencentdb` 0.1.0, the OpenClaw plugin, reached npm on 31 March 2026, and 1.0.3 on 22 September 2026 (source: \u003chttps://registry.npmjs.org/@tencentdb-agent-memory%2Fmemory-tencentdb\u003e)\n- The default branch (master) carries the 2.x Memory Hub stack. The main branch keeps the 0.3.x OpenClaw plugin source and its own changelog (source: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/main/CHANGELOG.md\u003e)\n- CHANGELOG.md dates 2.0.0-beta.1, the first public release of the 2.x line, to 21 July 2026 and 2.0.3 to 26 October 2026 (source: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/CHANGELOG.md\u003e)\n- Docker Hub counts 81,300 pulls of agentmemory/memory-core, 90,137 of memory-hub and 58,238 of memory-proxy, read on 30 October 2026. Image tags run 1.0.0 to 1.0.3 for releases 2.0.0 to 2.0.3 (source: \u003chttps://hub.docker.com/v2/repositories/agentmemory/\u003e)\n- The README says the OpenClaw plugin cuts tokens by up to 61.38% on WideSearch and raises PersonaMem accuracy from 48% to 76%. Project-reported, not reproduced by an independent source we found (source: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/main/README.md\u003e)\n- The Memory Proxy API reference says its rate-limit and session admin routes have no authentication, and that two handlers' comments claim admin auth the code doesn't call (source: \u003chttps://github.com/TencentCloud/TencentDB-Agent-Memory/blob/master/MemoryProxy/v3-api-memoryproxy-doc.md\u003e)\n\n- #14 of 20 in Best memory layers for AI agents: https://www.anchorterminal.com/best/agent-memory/index.md\n- All 188 memory comparisons: https://www.anchorterminal.com/compare/agent-memory/index.md\n\n## Compare\n\n- [Amazon Bedrock AgentCore Memory vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/agentcore-memory-vs-tencentdb-agent-memory.md): A 79.7 vs C 56\n- [claude-mem vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/claude-mem-vs-tencentdb-agent-memory.md): C 58.6 vs C 56\n- [Cognee vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/cognee-vs-tencentdb-agent-memory.md): C 54.6 vs C 56\n- [Graphiti vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/graphiti-vs-tencentdb-agent-memory.md): D 53.4 vs C 56\n- [Hindsight vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/hindsight-vs-tencentdb-agent-memory.md): D 50.2 vs C 56\n- [Honcho vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/honcho-vs-tencentdb-agent-memory.md): B 64.2 vs C 56\n- [Hy Memory vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/hy-memory-vs-tencentdb-agent-memory.md): C 57.8 vs C 56\n- [LangMem vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/langmem-vs-tencentdb-agent-memory.md): D 48.3 vs C 56\n- [LocalGhost vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/localghost-vs-tencentdb-agent-memory.md): C 55.7 vs C 56\n- [Mem0 Platform + MCP vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/mem0-vs-tencentdb-agent-memory.md): C 56.2 vs C 56\n- [Memory (MCP reference server) vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/memory-reference-server-vs-tencentdb-agent-memory.md): C 54.4 vs C 56\n- [MemPalace vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/mempalace-vs-tencentdb-agent-memory.md): B 65.7 vs C 56\n- [past.dev vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/past-dev-vs-tencentdb-agent-memory.md): B 63.7 vs C 56\n- [Supermemory API + MCP vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/supermemory-vs-tencentdb-agent-memory.md): B 63.8 vs C 56\n- [TencentDB Agent Memory vs Tokenrip](https://www.anchorterminal.com/compare/tencentdb-agent-memory-vs-tokenrip.md): C 56 vs C 59.7\n- [TencentDB Agent Memory vs Zep](https://www.anchorterminal.com/compare/tencentdb-agent-memory-vs-zep.md): C 56 vs BB 74\n- [AI Memory vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/ai-memory-vs-tencentdb-agent-memory.md): C 56.1 vs C 56\n- [Context Mode Engine vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/context-mode-vs-tencentdb-agent-memory.md): D 46.2 vs C 56\n- [Graphicle vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/graphicle-vs-tencentdb-agent-memory.md): BB 70.1 vs C 56\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on tencent.com or one of its subdomains, a page under github.com/tencentcloud, or the README of github.com/TencentCloud/TencentDB-Agent-Memory. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{\"slug\": \"tencentdb-agent-memory\", \"url\": \"…\"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/tencentdb-agent-memory\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/tencentdb-agent-memory.svg\" alt=\"TencentDB Agent Memory on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![TencentDB Agent Memory on Anchor Terminal](https://www.anchorterminal.com/badges/tencentdb-agent-memory.svg)](https://www.anchorterminal.com/tools/tencentdb-agent-memory)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/tencentdb-agent-memory\"\u003eTencentDB Agent Memory on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say TencentDB Agent Memory is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/tencentdb-agent-memory-dark.png\n- Light: https://www.anchorterminal.com/assets/share/tencentdb-agent-memory-light.png\n- Create a video and download its frames: https://www.anchorterminal.com/assets/listing-video/index.html?listing=tencentdb-agent-memory\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-31", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "Agent memory", "url": "https://www.anchorterminal.com/categories/agent-memory" }, { "name": "TencentDB Agent Memory", "url": "" } ], "description": "TencentDB Agent Memory is Tencent Cloud's MIT-licensed, self-hosted memory stack for coding agents. A proxy injects layered conversation memory, skills, wiki pages and code graphs into each request, with a team panel and HTTP API over SQLite.", "facts": [ "rank #767 of 1239", "API key auth", "0 desk reviews" ], "h1": "TencentDB Agent Memory", "image": "https://www.anchorterminal.com/assets/og/tools-tencentdb-agent-memory.png", "path": "/tools/tencentdb-agent-memory", "published": "2026-10-01", "section": "tools", "title": "TencentDB Agent Memory review: pricing, alternatives, grade C", "toc": null, "updated": "2026-10-30", "url": "https://www.anchorterminal.com/tools/tencentdb-agent-memory" }, "tokens": { "markdown": 10700, "slim": 2730 }, "version": 1 }