{ "data": { "a": { "slug": "everos", "name": "EverOS", "vendor": "Evermind AI, Inc.", "vendorUrl": "https://evermind.ai", "kind": "http-api", "category": "agent-memory", "summary": "EverOS, formerly EverMemOS, is EverMind's open-source memory runtime for agents. It stores conversations, files and agent trajectories as Markdown with SQLite and LanceDB indexes, behind a local HTTP API and MCP server, with a managed EverOS Cloud.", "url": "https://www.anchorterminal.com/tools/everos", "markdownUrl": "https://www.anchorterminal.com/tools/everos.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/everos.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/everos.json", "dns": "everos.grade.anchorterminal.com", "repo": "https://github.com/EverMind-AI/EverOS", "license": "Apache-2.0", "transports": [ "http", "stdio" ], "packages": [ { "registry": "pypi", "name": "everos" }, { "registry": "pypi", "name": "everos-mcp" } ], "auth": "none", "authNotes": "The self-hosted server has no authentication and binds to 127.0.0.1:8000 by default. The owner supplies LLM and embedding provider keys in ~/.everos/everos.toml. EverOS Cloud uses a bearer API key from the console at everos.evermind.ai, and its hosted MCP connector signs in with an EverOS account.", "pricing": "freemium", "pricingNotes": "Free under Apache-2.0 to run locally, with LLM and embedding costs paid to the chosen provider. EverOS Cloud has a console and API keys, but no plan or price was found on evermind.ai or docs.evermind.ai.", "priceSummary": "Freemium", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the repository, the OpenAPI document, llms.txt or the docs (checked 2026-11-06).", "endpoints": [] }, "toolCount": 7, "popularity": { "githubStars": 13839, "npmWeekly": null, "pypiWeekly": 4033, "asOf": "2026-11-06" }, "docsUrl": "https://docs.evermind.ai", "llmsTxt": "https://docs.evermind.ai/llms.txt", "openapi": "https://github.com/EverMind-AI/EverOS/blob/main/docs/openapi.json", "capabilities": [ "memory.store", "memory.search", "memory.user", "memory.delete" ], "tags": [ "open-source", "self-hosted", "local", "hosted", "apache-2.0", "python", "mcp", "openapi", "llms-txt", "markdown", "no-auth" ], "lastRelease": "2026-10-22", "graded": true, "anchor": { "graded": true, "score": 69.4, "grade": "B", "agentReady": false, "rank": 247, "ranked": true, "rankOf": 1510, "categoryRank": 6, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 78, "maintenance": 80, "payments": 40, "reliability": 79, "schema": 89, "security": 47, "transparency": 71 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": 0, "verdict": "EverOS keeps agent and user memory as Markdown with SQLite and LanceDB indexes, behind a described OpenAPI with typed, retryable errors and an MCP server, under Apache-2.0 at version 1.5.1. The local server has no authentication, EverOS Cloud prices are not published, and the cloud terms forbid automated data extraction.", "bestFor": "Self-hosted memory for agents and apps that want Markdown as the source of truth and separate user and agent tracks.", "strengths": [ "Apache-2.0 Python library and local server at 1.5.1, with Keep a Changelog entries and semantic versioning declared", "OpenAPI document with 40 operations, every one described, and llms.txt plus llms-full.txt for the docs", "Retryable conditions are typed, such as 503 SESSION_BUSY and EXTERNAL_SERVICE_UNAVAILABLE for a busy database", "Memory is canonical Markdown on disk, editable by hand, with deletion by owner, session or memory id", "SECURITY.md with a five-day acknowledgement, plus a valid security.txt at evermind.ai" ], "weaknesses": [ "The local HTTP server has no authentication and relies on binding to 127.0.0.1", "EverOS Cloud prices, plans and rate limits were not found on any public page", "The MCP server's autonomy protocol tells hosts to save facts without being asked, and no prompt-injection guidance was found", "The cloud terms of 20 January 2026 forbid automated extraction and allow discontinuing the service without notice", "Several outside bug reports, such as a silent capture failure, have no reply" ], "agentNotes": [ "Write new code against `/api/v2`; `/api/v1` is a legacy alias that may go in a future major release", "Call `/api/v2/memory/flush` at the end of a session, since `add` is asynchronous and buffers recent messages", "Retry on 503 SESSION_BUSY or EXTERNAL_SERVICE_UNAVAILABLE after a pause; nothing was written", "Keep `host` at 127.0.0.1 unless something in front adds authentication", "Treat recalled memories as untrusted text, since they are extracted from past conversations" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 69.4 } ], "editorialScores": { "ergonomics": 78, "maintenance": 80, "payments": 40, "reliability": 79, "schema": 89, "security": 47, "transparency": 66 }, "provenanceScore": 75, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "uv pip install everos \u0026\u0026 everos init \u0026\u0026 everos server start", "http": "curl http://127.0.0.1:8000/health", "claudeCode": "claude mcp add everos -e EVEROS_BASE_URL=http://127.0.0.1:8000 -- uvx everos-mcp" }, "letme": { "capability": "https://letme.dev/memory.store", "tool": "https://letme.dev/everos" }, "area": "agent-runtime", "provenance": { "legalEntity": "Evermind AI, Inc.", "domain": "evermind.ai", "domainRegistered": "2020-02-22", "endpointOnVendorDomain": null, "terms": "https://evermind.ai/terms-of-service", "privacy": "https://evermind.ai/privacy-policy", "statusPage": "", "changelog": "https://github.com/EverMind-AI/EverOS/blob/main/CHANGELOG.md", "securityTxt": "valid", "checked": "2026-11-06", "notes": [ "Terms and privacy policy both say last updated 20 January 2026 and name Evermind AI, Inc. The terms choose Singapore law and forbid extracting data by bots, scripts, crawlers or data-mining tools, recorded here as a fact.", "evermind.ai/robots.txt allows all crawlers and names Claude-Web and anthropic-ai as allowed. docs.evermind.ai carries Content-Signal ai-input=yes.", "RDAP gives evermind.ai a registration date of 22 February 2020.", "security.txt at evermind.ai/.well-known/ gives contact@evermind.ai and a policy URL, expiring 28 February 2027.", "The about page is drawn by script and returned no readable text." ], "score": 75 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/everos.json", "live": { "slug": "everos", "versions": [ { "registry": "github", "name": "EverMind-AI/EverOS", "version": "v1.5.1", "released": "2026-10-22", "seenAt": "2026-11-06T23:24:44.540703115Z" }, { "registry": "pypi", "name": "everos", "version": "1.5.1", "released": "2026-10-22", "seenAt": "2026-11-06T23:24:41.488069905Z" }, { "registry": "pypi", "name": "everos-mcp", "version": "0.1.1", "released": "2026-10-15", "seenAt": "2026-11-06T23:24:42.65503941Z" } ], "githubStars": 13840, "pypiWeekly": 4033, "securityTxt": { "url": "https://evermind.ai/.well-known/security.txt", "state": "valid", "expires": "2027-02-28T00:00:00Z", "checkedAt": "2026-11-07T16:01:32.419431813Z" }, "llmsTxt": { "url": "https://docs.evermind.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:26.933711899Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/EverMind-AI/EverOS/main/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:18:19.185692468Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "40ab92cf4d99" }, { "url": "https://evermind.ai/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:09:24.819286526Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "dcd843ca72fe" }, { "url": "https://evermind.ai/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:09:28.72898661Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "009377ab61a3" } ], "updatedAt": "2026-11-07T16:01:32.419431813Z" } }, "answer": "EverOS scores 69.4 (B) on agent readiness against TencentDB Agent Memory's 50.9 (D), and leads in 6 of 7 scored categories. TencentDB Agent Memory leads on payments \u0026 pricing.", "b": { "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", "dns": "tencentdb-agent-memory.grade.anchorterminal.com", "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/feat/server_team/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/feat/server_team/INSTALL.md", "openapi": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/feat/server_team/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": 50.9, "grade": "D", "agentReady": false, "rank": 1049, "ranked": true, "rankOf": 1510, "categoryRank": 20, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 68, "maintenance": 70, "payments": 60, "reliability": 51, "schema": 61, "security": 35, "transparency": 68 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": -6, "negativeNotes": [ "-3, a released fix of the project's own described flaw with no advisory. Memory Core's asset/get and asset/list ran with an unrestricted admin view, so any team member holding a valid user key could list and read other members' private assets, which the commit calls horizontal privilege escalation. Fixed on 21 September 2026 and released in 2.0.2 on 9 October 2026, with no advisory or changelog line found (https://github.com/TencentCloud/TencentDB-Agent-Memory/commit/5017e2bb927c65bd8302af2d984b04db46303f1b).", "-3, a security fix in no release. A commit of 28 October 2026 on the default branch scopes Agent and Task get and list reads to the caller, with regression tests for outsiders reading private Agents. The latest release, 2.0.3 of 26 October 2026, doesn't carry it on 4 November (https://github.com/TencentCloud/TencentDB-Agent-Memory/commit/afadb9aade42e524a350fcb38a2092f56b77c7c1)." ], "verdict": "A self-hosted team memory stack with layered recall, per-asset visibility and ACLs, documented HTTP APIs and frequent releases, 2.0.1 to 2.0.3 since August. The default deployment publishes its ports on all interfaces with the core's bearer gate off, the proxy's admin routes have no authentication, and two 2026 access-control fixes came without advisories.", "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", "Six releases from 2.0.1-beta.1 on 13 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", "Asset reads were scoped to the caller only in 2.0.2, with no advisory, and Agent and Task reads only in an unreleased commit of 28 October 2026", "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", "Build from the default branch past 2.0.3, or wait for the next release, before giving several users one Memory Core. Agent and Task reads were unscoped until 28 October" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 50.9 } ], "editorialScores": { "ergonomics": 68, "maintenance": 70, "payments": 60, "reliability": 51, "schema": 61, "security": 35, "transparency": 61 }, "provenanceScore": 75, "checked": { "categories": { "ergonomics": "2026-11-04", "maintenance": "2026-11-04", "payments": "2026-11-04", "reliability": "2026-11-04", "schema": "2026-11-04", "security": "2026-11-04", "transparency": "2026-11-04" }, "last": "2026-11-04", "lastMoved": "2026-11-04", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "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" ], "area": "agent-runtime", "provenance": { "legalEntity": "Tencent", "domain": "tencent.com", "domainRegistered": "1998-09-14", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/feat/server_team/CHANGELOG.md", "securityTxt": "none", "checked": "2026-11-04", "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 robots.txt with a bot check, so that host is treated as blocked. No branch has SECURITY.md; CONTRIBUTING.md names agentmemory@tencent.com for vulnerability reports.", "github.com pages and api.github.com weren't read (closed by the session's proxy). The repository was read from a clone on 4 November 2026. Its default branch is now feat/server_team, and the master branch the 30 October check read no longer exists.", "cloud.tencent.com allows general crawling in robots.txt, but its service agreement answered with a bot check on 4 November 2026, so Tencent Cloud's terms weren't read and nothing else on that host was requested." ], "score": 75 }, "requirements": { "setupChecked": true, "complianceChecked": true, "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", "live": { "slug": "tencentdb-agent-memory", "versions": [ { "registry": "github", "name": "TencentCloud/TencentDB-Agent-Memory", "version": "v2.0.3", "released": "2026-10-26", "seenAt": "2026-11-07T00:11:03.066814774Z" }, { "registry": "npm", "name": "@tencentdb-agent-memory/memory-sdk-ts-v2", "version": "1.0.0-beta.1", "seenAt": "2026-11-07T00:11:01.36963606Z" }, { "registry": "npm", "name": "@tencentdb-agent-memory/memory-tencentdb", "version": "1.0.3", "seenAt": "2026-11-07T00:11:00.859500824Z" } ], "githubStars": 30577, "npmWeekly": 2589, "securityTxt": { "url": "https://tencent.com/.well-known/security.txt", "state": "unknown", "checkedAt": "2026-11-07T16:01:57.23927149Z" }, "domain": { "domain": "tencent.com", "registered": "1998-09-14", "source": "https://rdap.verisign.com/com/v1/domain/tencent.com", "checkedAt": "2026-11-01T14:16:02.443593707Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/TencentCloud/TencentDB-Agent-Memory/feat/server_team/CHANGELOG.md", "kind": "changelog", "status": 304, "checkedAt": "2026-11-07T14:19:35.679034443Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e213f9445c48" }, { "url": "https://raw.githubusercontent.com/TencentCloud/TencentDB-Agent-Memory/master/CHANGELOG.md", "kind": "changelog", "status": 304, "checkedAt": "2026-11-04T08:32:32.15651231Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e213f9445c48" } ], "github": { "repo": "tencentcloud/tencentdb-agent-memory", "checkedAt": "2026-11-02T08:23:41.922514512Z", "stars": 30347, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-28T14:33:21Z", "openIssues": 312, "openPRs": 578, "issuesOpened90d": 347, "issuesClosed90d": 99, "prsMerged90d": 77, "replies": { "sampled": 25, "unanswered": 25 } }, "updatedAt": "2026-11-07T16:01:57.23927149Z" } }, "edges": [ { "by": 28, "category": "reliability", "leads": "everos", "name": "Reliability", "reasons": { "a": "Local-software lines, as a library and server the owner runs. `everos` on PyPI with Python 3.12 or newer stated, plus a Windows guide (20). ci.yml runs on pushes and pull requests and the repository has a tests tree, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 43 open issues and pull requests against 82 commits in 90 days; several outside bug reports, including a silent capture failure in the DSH plugin, have no reply (14 of 25). Keep a Changelog with semantic versioning declared and a 1.0 migration guide (15). Version 1.5.1 (15). Total 79.", "b": "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. The one CI workflow, pr-ci.yml, runs on pull requests to the main branch (the OpenClaw plugin) and installs, packs and checks the manifest, package size and skill-queue isolation without running the test suites, and nothing runs on the default branch, now feat/server_team. GitHub's Actions pages weren't readable, so no result was read (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 on 4 November (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)." }, "scores": { "a": 79, "b": 51 } }, { "by": 28, "category": "schema", "leads": "everos", "name": "Schema \u0026 documentation", "reasons": { "a": "OpenAPI document in the repository with 40 operations, every one with a description (25). llms.txt and llms-full.txt on docs.evermind.ai (10). Operation descriptions state purpose; when-not-to-use guidance appears in the docs, such as flush after add, rather than per operation (15 of 20). Typed request models with filter operators eq, ne, gt, gte, lt, lte and in, and 422 on malformed ids (12 of 15). curl examples for add, flush and search, and typed error codes such as SESSION_BUSY and EXTERNAL_SERVICE_UNAVAILABLE (12 of 15). `/api/v2` with `/api/v1` kept as a legacy alias, a changelog and release notes (15). Total 89.", "b": "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)." }, "scores": { "a": 89, "b": 61 } }, { "by": 20, "category": "payments", "leads": "tencentdb-agent-memory", "name": "Payments \u0026 pricing", "reasons": { "a": "Self-hosted rule, with the price lines read for EverOS Cloud. No x402, MPP or L402 (0 of 40). No cloud price or plan found on evermind.ai, its FAQ, terms or docs (0). The open-source runtime is free with no card (20). An agent can install it from PyPI and run it with no account (20). Total 40.", "b": "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." }, "scores": { "a": 40, "b": 60 } }, { "by": 12, "category": "security", "leads": "everos", "name": "Security \u0026 auth", "reasons": { "a": "Framework reading for software the owner runs. The local server has no authentication and no security scheme in the OpenAPI document, relying on a 127.0.0.1 bind by default (15 of 30). No read-only mode; the cloud purge is two-step (8 of 20). Memories are extracted from conversations and returned into prompts, and everos-mcp tells hosts to save facts unprompted, with no injection guidance found (4 of 15). Structured logs and lock metrics, no audit log (6 of 15). SECURITY.md with a reporting address, five-day acknowledgement, supported versions and a published-advisories section, plus a valid security.txt (14 of 20). Total 47.", "b": "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. Asset reads were scoped to the caller only in 2.0.2, and Agent and Task reads only in an unreleased commit of 28 October (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). CONTRIBUTING.md asks for vulnerability reports by email to agentmemory@tencent.com rather than public issues, with no acknowledgement time, so a disclosure route without a stated time (7). No SECURITY.md on any branch, no security.txt on www.tencent.com, and no bounty or audit named. The npm plugin's postinstall runs a bash script that rewrites OpenClaw's installed files, with output sent to /dev/null. Two access-control fixes in 2026 are under the negative events." }, "scores": { "a": 47, "b": 35 } }, { "by": 10, "category": "ergonomics", "leads": "everos", "name": "Agent ergonomics", "reasons": { "a": "Read for the API, with seven MCP tools on top. Searches take `top_k` and a method, and responses can be scoped by five ids (20 of 25). Filters nest with AND and OR, and `/get` pages results (18 of 20). Errors carry typed codes and say which are retryable (16 of 20). `add` is queued and returns 202, a busy session refuses deletion with nothing deleted, and the cloud purge needs a nonce confirmed within five minutes (12 of 20). A demo runs with no key and the minimal setup needs one OpenRouter key, with a Python library and the MCP server, one language (12 of 15). Total 78.", "b": "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)." }, "scores": { "a": 78, "b": 68 } }, { "by": 10, "category": "maintenance", "leads": "everos", "name": "Maintenance \u0026 community", "reasons": { "a": "v1.5.1 on 22 October 2026 (30). Five tagged releases in 90 days and 12 PyPI uploads (20). Maintainer replies on some issues, others from outside users unanswered for weeks (12 of 25). Python library and the everos-mcp package, not in the official MCP registry (10 of 15). uv.lock, CI, docs and release workflows (8 of 10). Total 80.", "b": "Release 2.0.3 on 26 October 2026 by the changelog and its tag, 9 days before this check (30). Six changelog releases in the 90 days from 6 August, 2.0.1-beta.1 (13 August), 2.0.1 (25 August), 2.0.2-beta.1 (7 September), 2.0.2 (9 October), 2.0.3-beta.1 (13 October) and 2.0.3, with image tags v1.0.2 (8 September) and v1.0.3 (22 September) between. The three stable releases 2.0.1, 2.0.2 and 2.0.3 meet the line without the pre-releases, which this run doesn't count (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. A workflow added on 28 October posts an automatic acknowledgement on new external pull requests, which isn't a maintainer reply (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, the one CI workflow skips the tests and doesn't run on the default branch, and 2.0.3 fixed a Knowledge service broken by OpenTelemetry dependency drift (4 of 10)." }, "scores": { "a": 80, "b": 70 } } ], "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Evermind AI, Inc.", "b": "Tencent Cloud", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP, stdio", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "API key", "name": "Auth" }, { "a": "Freemium", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "MIT", "name": "Licence" }, { "a": "7", "b": "none", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-10-22", "b": "2026-10-26", "name": "Last release" }, { "a": "2026-01-20", "b": "no document linked", "name": "Terms last updated" }, { "a": "2026-01-20", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "yes", "b": "not read yet", "name": "Customer content may train models" }, { "a": "yes", "b": "not read yet", "name": "Terms restrict automated access" }, { "a": "yes", "b": "not read yet", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "not read yet", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not read yet", "name": "Arbitration or class-action waiver" }, { "a": "14k stars, 4k PyPI/wk", "b": "2.2k npm/wk", "name": "Popularity" } ], "faq": [ { "answer": "EverOS scores 69.4 (B) on agent readiness against TencentDB Agent Memory's 50.9 (D), and leads in 6 of 7 scored categories. TencentDB Agent Memory leads on payments \u0026 pricing.", "question": "Which is better for AI agents, EverOS or TencentDB Agent Memory?" }, { "answer": "EverOS needs no key. TencentDB Agent Memory needs an API key.", "question": "Do EverOS and TencentDB Agent Memory need an API key?" }, { "answer": "EverOS runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for TencentDB Agent Memory.", "question": "Can an agent call EverOS and TencentDB Agent Memory without installing anything?" }, { "answer": "Yes. EverOS is open source (Apache-2.0). TencentDB Agent Memory is open source (MIT).", "question": "Are EverOS and TencentDB Agent Memory open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 79 against 51", "Schema \u0026 documentation, 89 against 61", "Agent ergonomics, 78 against 68", "Security \u0026 auth, 47 against 35", "Maintenance \u0026 community, 80 against 70" ], "also": [ "No key needed to call it", "Runs on your own machine", "No incidents deducted, where TencentDB Agent Memory loses 6 points for them" ], "goodFor": "Self-hosted memory for agents and apps that want Markdown as the source of truth and separate user and agent tracks.", "slug": "everos", "watchFor": "The local HTTP server has no authentication and relies on binding to 127.0.0.1" }, { "aheadOn": [ "Payments \u0026 pricing, 60 against 40" ], "also": [ "Free to start without a card" ], "goodFor": "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.", "slug": "tencentdb-agent-memory", "watchFor": "The core's bearer gate is off by default, and the deploy notes say enabling it breaks the proxy's auth and session setup" } ], "history": { "everos": null, "tencentdb-agent-memory": [ { "causes": [ "security", "correction" ], "date": "2026-11-04", "delta": -5.1, "from": 56, "fromGrade": "C", "to": 50.9, "toGrade": "D" } ] }, "job": { "capability": "memory.store", "name": "Agent memory" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-everos.json", "title": "Amazon Bedrock AgentCore Memory vs EverOS", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-tencentdb-agent-memory.json", "title": "Amazon Bedrock AgentCore Memory vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/basic-memory-vs-everos.json", "title": "Basic Memory vs EverOS", "url": "https://www.anchorterminal.com/compare/basic-memory-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/basic-memory-vs-tencentdb-agent-memory.json", "title": "Basic Memory vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/basic-memory-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/claude-mem-vs-everos.json", "title": "claude-mem vs EverOS", "url": "https://www.anchorterminal.com/compare/claude-mem-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/claude-mem-vs-tencentdb-agent-memory.json", "title": "claude-mem vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/claude-mem-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-everos.json", "title": "Cognee vs EverOS", "url": "https://www.anchorterminal.com/compare/cognee-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-tencentdb-agent-memory.json", "title": "Cognee vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/cognee-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-google-memory-bank.json", "title": "EverOS vs Agent Platform Memory Bank", "url": "https://www.anchorterminal.com/compare/everos-vs-google-memory-bank" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-graphicle.json", "title": "EverOS vs Graphicle", "url": "https://www.anchorterminal.com/compare/everos-vs-graphicle" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-graphiti.json", "title": "EverOS vs Graphiti", "url": "https://www.anchorterminal.com/compare/everos-vs-graphiti" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-hindsight.json", "title": "EverOS vs Hindsight", "url": "https://www.anchorterminal.com/compare/everos-vs-hindsight" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-honcho.json", "title": "EverOS vs Honcho", "url": "https://www.anchorterminal.com/compare/everos-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-hy-memory.json", "title": "EverOS vs Hy Memory", "url": "https://www.anchorterminal.com/compare/everos-vs-hy-memory" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-langmem.json", "title": "EverOS vs LangMem", "url": "https://www.anchorterminal.com/compare/everos-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-localghost.json", "title": "EverOS vs LocalGhost", "url": "https://www.anchorterminal.com/compare/everos-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-mem0.json", "title": "EverOS vs Mem0 Platform + MCP", "url": "https://www.anchorterminal.com/compare/everos-vs-mem0" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-memmachine.json", "title": "EverOS vs MemMachine", "url": "https://www.anchorterminal.com/compare/everos-vs-memmachine" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-memori.json", "title": "EverOS vs Memori", "url": "https://www.anchorterminal.com/compare/everos-vs-memori" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-memory-reference-server.json", "title": "EverOS vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/everos-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-mempalace.json", "title": "EverOS vs MemPalace", "url": "https://www.anchorterminal.com/compare/everos-vs-mempalace" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-past-dev.json", "title": "EverOS vs past.dev", "url": "https://www.anchorterminal.com/compare/everos-vs-past-dev" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-supermemory.json", "title": "EverOS vs Supermemory API + MCP", "url": "https://www.anchorterminal.com/compare/everos-vs-supermemory" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-tokenrip.json", "title": "EverOS vs Tokenrip", "url": "https://www.anchorterminal.com/compare/everos-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/everos-vs-zep.json", "title": "EverOS vs Zep", "url": "https://www.anchorterminal.com/compare/everos-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/google-memory-bank-vs-tencentdb-agent-memory.json", "title": "Agent Platform Memory Bank vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/google-memory-bank-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/graphiti-vs-tencentdb-agent-memory.json", "title": "Graphiti vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/graphiti-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-tencentdb-agent-memory.json", "title": "Hindsight vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/hindsight-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-tencentdb-agent-memory.json", "title": "Honcho vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/honcho-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-vs-tencentdb-agent-memory.json", "title": "Hy Memory vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/hy-memory-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/langmem-vs-tencentdb-agent-memory.json", "title": "LangMem vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/langmem-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-tencentdb-agent-memory.json", "title": "LocalGhost vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/localghost-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/mem0-vs-tencentdb-agent-memory.json", "title": "Mem0 Platform + MCP vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/mem0-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/memmachine-vs-tencentdb-agent-memory.json", "title": "MemMachine vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/memmachine-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/memori-vs-tencentdb-agent-memory.json", "title": "Memori vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/memori-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/memory-reference-server-vs-tencentdb-agent-memory.json", "title": "Memory (MCP reference server) vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/memory-reference-server-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/mempalace-vs-tencentdb-agent-memory.json", "title": "MemPalace vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/mempalace-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/past-dev-vs-tencentdb-agent-memory.json", "title": "past.dev vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/past-dev-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/supermemory-vs-tencentdb-agent-memory.json", "title": "Supermemory API + MCP vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/supermemory-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/tencentdb-agent-memory-vs-tokenrip.json", "title": "TencentDB Agent Memory vs Tokenrip", "url": "https://www.anchorterminal.com/compare/tencentdb-agent-memory-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/tencentdb-agent-memory-vs-zep.json", "title": "TencentDB Agent Memory vs Zep", "url": "https://www.anchorterminal.com/compare/tencentdb-agent-memory-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-everos.json", "title": "AI Memory vs EverOS", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-tencentdb-agent-memory.json", "title": "AI Memory vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/context-mode-vs-everos.json", "title": "Context Mode Engine vs EverOS", "url": "https://www.anchorterminal.com/compare/context-mode-vs-everos" }, { "json": "https://www.anchorterminal.com/compare/context-mode-vs-tencentdb-agent-memory.json", "title": "Context Mode Engine vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/context-mode-vs-tencentdb-agent-memory" }, { "json": "https://www.anchorterminal.com/compare/graphicle-vs-tencentdb-agent-memory.json", "title": "Graphicle vs TencentDB Agent Memory", "url": "https://www.anchorterminal.com/compare/graphicle-vs-tencentdb-agent-memory" } ], "panel": null, "scores": [ { "by": 28, "edge": "everos", "everos": 79, "key": "reliability", "name": "Reliability", "tencentdb-agent-memory": 51, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 28, "edge": "everos", "everos": 89, "key": "schema", "name": "Schema \u0026 documentation", "tencentdb-agent-memory": 61, "weight": 13 }, { "by": 10, "edge": "everos", "everos": 78, "key": "ergonomics", "name": "Agent ergonomics", "tencentdb-agent-memory": 68, "weight": 13 }, { "by": 12, "edge": "everos", "everos": 47, "key": "security", "name": "Security \u0026 auth", "tencentdb-agent-memory": 35, "weight": 14 }, { "by": 20, "edge": "tencentdb-agent-memory", "everos": 40, "key": "payments", "name": "Payments \u0026 pricing", "tencentdb-agent-memory": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 10, "edge": "everos", "everos": 80, "key": "maintenance", "name": "Maintenance \u0026 community", "tencentdb-agent-memory": 70, "weight": 7 }, { "by": 3, "edge": "everos", "everos": 71, "key": "transparency", "name": "Transparency \u0026 trust", "tencentdb-agent-memory": 68, "weight": 7 } ], "summary": "EverOS scores 69.4 (B) on agent readiness against TencentDB Agent Memory's 50.9 (D), and leads in 6 of 7 scored categories. TencentDB Agent Memory leads on payments \u0026 pricing. Both do agent memory.", "tasks": null, "tutorials": [], "verdicts": { "everos": "EverOS keeps agent and user memory as Markdown with SQLite and LanceDB indexes, behind a described OpenAPI with typed, retryable errors and an MCP server, under Apache-2.0 at version 1.5.1. The local server has no authentication, EverOS Cloud prices are not published, and the cloud terms forbid automated data extraction.", "tencentdb-agent-memory": "A self-hosted team memory stack with layered recall, per-asset visibility and ACLs, documented HTTP APIs and frequent releases, 2.0.1 to 2.0.3 since August. The default deployment publishes its ports on all interfaces with the core's bearer gate off, the proxy's admin routes have no authentication, and two 2026 access-control fixes came without advisories." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/everos-vs-tencentdb-agent-memory", "json": "https://www.anchorterminal.com/compare/everos-vs-tencentdb-agent-memory.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/everos-vs-tencentdb-agent-memory.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/everos-vs-tencentdb-agent-memory.min.md" }, "markdown": "EverOS scores 69.4 (B) on agent readiness against TencentDB Agent Memory's 50.9 (D), and leads in 6 of 7 scored categories. TencentDB Agent Memory leads on payments \u0026 pricing. Both do agent memory.\n\n- EverOS: grade B, 69.4/100, rank #247 of 1510. Markdown https://www.anchorterminal.com/tools/everos.md · JSON https://www.anchorterminal.com/api/v1/tools/everos.json\n- TencentDB Agent Memory: grade D, 50.9/100, rank #1049 of 1510. Markdown https://www.anchorterminal.com/tools/tencentdb-agent-memory.md · JSON https://www.anchorterminal.com/api/v1/tools/tencentdb-agent-memory.json\n- Best memory layers for AI agents: https://www.anchorterminal.com/best/agent-memory/index.md\n- All 353 memory comparisons: https://www.anchorterminal.com/compare/agent-memory/index.md\n\n## Which one, for what\n\n### EverOS (B)\n\nGood for: Self-hosted memory for agents and apps that want Markdown as the source of truth and separate user and agent tracks.\n\nAhead on:\n- Reliability, 79 against 51\n- Schema \u0026 documentation, 89 against 61\n- Agent ergonomics, 78 against 68\n- Security \u0026 auth, 47 against 35\n- Maintenance \u0026 community, 80 against 70\n\nAlso in its favour:\n- No key needed to call it\n- Runs on your own machine\n- No incidents deducted, where TencentDB Agent Memory loses 6 points for them\n\nWatch for: The local HTTP server has no authentication and relies on binding to 127.0.0.1\n\n### TencentDB Agent Memory (D)\n\nGood for: 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.\n\nAhead on:\n- Payments \u0026 pricing, 60 against 40\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: 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\n\n## Why the edge\n\n### Reliability: EverOS +28\n\n- EverOS (79): Local-software lines, as a library and server the owner runs. `everos` on PyPI with Python 3.12 or newer stated, plus a Windows guide (20). ci.yml runs on pushes and pull requests and the repository has a tests tree, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 43 open issues and pull requests against 82 commits in 90 days; several outside bug reports, including a silent capture failure in the DSH plugin, have no reply (14 of 25). Keep a Changelog with semantic versioning declared and a 1.0 migration guide (15). Version 1.5.1 (15). Total 79.\n- TencentDB Agent Memory (51): 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. The one CI workflow, pr-ci.yml, runs on pull requests to the main branch (the OpenClaw plugin) and installs, packs and checks the manifest, package size and skill-queue isolation without running the test suites, and nothing runs on the default branch, now feat/server_team. GitHub's Actions pages weren't readable, so no result was read (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 on 4 November (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\n### Schema \u0026 documentation: EverOS +28\n\n- EverOS (89): OpenAPI document in the repository with 40 operations, every one with a description (25). llms.txt and llms-full.txt on docs.evermind.ai (10). Operation descriptions state purpose; when-not-to-use guidance appears in the docs, such as flush after add, rather than per operation (15 of 20). Typed request models with filter operators eq, ne, gt, gte, lt, lte and in, and 422 on malformed ids (12 of 15). curl examples for add, flush and search, and typed error codes such as SESSION_BUSY and EXTERNAL_SERVICE_UNAVAILABLE (12 of 15). `/api/v2` with `/api/v1` kept as a legacy alias, a changelog and release notes (15). Total 89.\n- TencentDB Agent Memory (61): 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\n### Payments \u0026 pricing: TencentDB Agent Memory +20\n\n- EverOS (40): Self-hosted rule, with the price lines read for EverOS Cloud. No x402, MPP or L402 (0 of 40). No cloud price or plan found on evermind.ai, its FAQ, terms or docs (0). The open-source runtime is free with no card (20). An agent can install it from PyPI and run it with no account (20). Total 40.\n- TencentDB Agent Memory (60): 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\n### Security \u0026 auth: EverOS +12\n\n- EverOS (47): Framework reading for software the owner runs. The local server has no authentication and no security scheme in the OpenAPI document, relying on a 127.0.0.1 bind by default (15 of 30). No read-only mode; the cloud purge is two-step (8 of 20). Memories are extracted from conversations and returned into prompts, and everos-mcp tells hosts to save facts unprompted, with no injection guidance found (4 of 15). Structured logs and lock metrics, no audit log (6 of 15). SECURITY.md with a reporting address, five-day acknowledgement, supported versions and a published-advisories section, plus a valid security.txt (14 of 20). Total 47.\n- TencentDB Agent Memory (35): 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. Asset reads were scoped to the caller only in 2.0.2, and Agent and Task reads only in an unreleased commit of 28 October (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). CONTRIBUTING.md asks for vulnerability reports by email to agentmemory@tencent.com rather than public issues, with no acknowledgement time, so a disclosure route without a stated time (7). No SECURITY.md on any branch, no security.txt on www.tencent.com, and no bounty or audit named. The npm plugin's postinstall runs a bash script that rewrites OpenClaw's installed files, with output sent to /dev/null. Two access-control fixes in 2026 are under the negative events.\n\n### Agent ergonomics: EverOS +10\n\n- EverOS (78): Read for the API, with seven MCP tools on top. Searches take `top_k` and a method, and responses can be scoped by five ids (20 of 25). Filters nest with AND and OR, and `/get` pages results (18 of 20). Errors carry typed codes and say which are retryable (16 of 20). `add` is queued and returns 202, a busy session refuses deletion with nothing deleted, and the cloud purge needs a nonce confirmed within five minutes (12 of 20). A demo runs with no key and the minimal setup needs one OpenRouter key, with a Python library and the MCP server, one language (12 of 15). Total 78.\n- TencentDB Agent Memory (68): 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\n### Maintenance \u0026 community: EverOS +10\n\n- EverOS (80): v1.5.1 on 22 October 2026 (30). Five tagged releases in 90 days and 12 PyPI uploads (20). Maintainer replies on some issues, others from outside users unanswered for weeks (12 of 25). Python library and the everos-mcp package, not in the official MCP registry (10 of 15). uv.lock, CI, docs and release workflows (8 of 10). Total 80.\n- TencentDB Agent Memory (70): Release 2.0.3 on 26 October 2026 by the changelog and its tag, 9 days before this check (30). Six changelog releases in the 90 days from 6 August, 2.0.1-beta.1 (13 August), 2.0.1 (25 August), 2.0.2-beta.1 (7 September), 2.0.2 (9 October), 2.0.3-beta.1 (13 October) and 2.0.3, with image tags v1.0.2 (8 September) and v1.0.3 (22 September) between. The three stable releases 2.0.1, 2.0.2 and 2.0.3 meet the line without the pre-releases, which this run doesn't count (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. A workflow added on 28 October posts an automatic acknowledgement on new external pull requests, which isn't a maintainer reply (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, the one CI workflow skips the tests and doesn't run on the default branch, and 2.0.3 fixed a Knowledge service broken by OpenTelemetry dependency drift (4 of 10).\n\n## Score by category\n\n| Category | Weight | EverOS | TencentDB Agent Memory | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 79 | 51 | EverOS +28 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 89 | 61 | EverOS +28 |\n| Agent ergonomics | 13% (16.2 this run) | 78 | 68 | EverOS +10 |\n| Security \u0026 auth | 14% (17.5 this run) | 47 | 35 | EverOS +12 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 60 | TencentDB Agent Memory +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 80 | 70 | EverOS +10 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 71 | 68 | EverOS +3 |\n| Negative events | ≤15 | 0 | -6 | |\n| **Total** | | **69.4 · B** | **50.9 · D** | |\n\n## Facts side by side\n\n| Fact | EverOS | TencentDB Agent Memory |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Evermind AI, Inc. | Tencent Cloud |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP, stdio | HTTP |\n| Auth | None | API key |\n| Pricing | Freemium | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | MIT |\n| Tools exposed | 7 | none |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-10-22 | 2026-10-26 |\n| Terms last updated | 2026-01-20 | no document linked |\n| Privacy policy last updated | 2026-01-20 | no document linked |\n| Customer content may train models | yes | not read yet |\n| Terms restrict automated access | yes | not read yet |\n| Terms restrict benchmarking | yes | not read yet |\n| Terms or service can change without notice | yes | not read yet |\n| Arbitration or class-action waiver | not found in the text | not read yet |\n| Popularity | 14k stars, 4k PyPI/wk | 2.2k npm/wk |\n\n## How the scores have moved\n\n### EverOS\n\nNo score change since it was listed.\n\n### TencentDB Agent Memory\n\n- -5.1 on 4 November 2026 (C to D): security, correction\n\n## Verdicts\n\n**EverOS.** EverOS keeps agent and user memory as Markdown with SQLite and LanceDB indexes, behind a described OpenAPI with typed, retryable errors and an MCP server, under Apache-2.0 at version 1.5.1. The local server has no authentication, EverOS Cloud prices are not published, and the cloud terms forbid automated data extraction.\n\n**TencentDB Agent Memory.** A self-hosted team memory stack with layered recall, per-asset visibility and ACLs, documented HTTP APIs and frequent releases, 2.0.1 to 2.0.3 since August. The default deployment publishes its ports on all interfaces with the core's bearer gate off, the proxy's admin routes have no authentication, and two 2026 access-control fixes came without advisories.\n\n## Before you call either\n\n### EverOS\n\n1. Write new code against `/api/v2`; `/api/v1` is a legacy alias that may go in a future major release\n2. Call `/api/v2/memory/flush` at the end of a session, since `add` is asynchronous and buffers recent messages\n3. Retry on 503 SESSION_BUSY or EXTERNAL_SERVICE_UNAVAILABLE after a pause; nothing was written\n4. Keep `host` at 127.0.0.1 unless something in front adds authentication\n5. Treat recalled memories as untrusted text, since they are extracted from past conversations\n\n### TencentDB Agent Memory\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\n6. Build from the default branch past 2.0.3, or wait for the next release, before giving several users one Memory Core. Agent and Task reads were unscoped until 28 October\n\n## Questions\n\n### Which is better for AI agents, EverOS or TencentDB Agent Memory?\n\nEverOS scores 69.4 (B) on agent readiness against TencentDB Agent Memory's 50.9 (D), and leads in 6 of 7 scored categories. TencentDB Agent Memory leads on payments \u0026 pricing.\n\n### Do EverOS and TencentDB Agent Memory need an API key?\n\nEverOS needs no key. TencentDB Agent Memory needs an API key.\n\n### Can an agent call EverOS and TencentDB Agent Memory without installing anything?\n\nEverOS runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for TencentDB Agent Memory.\n\n### Are EverOS and TencentDB Agent Memory open source?\n\nYes. EverOS is open source (Apache-2.0). TencentDB Agent Memory is open source (MIT).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/everos-vs-tencentdb-agent-memory.json, and with the fewest tokens: https://www.anchorterminal.com/compare/everos-vs-tencentdb-agent-memory.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"everos\", \"b\": \"tencentdb-agent-memory\"}`. From a terminal: `anchor compare everos tencentdb-agent-memory`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/everos.json and https://www.anchorterminal.com/api/v1/tools/tencentdb-agent-memory.json\n\n## Other comparisons with EverOS or TencentDB Agent Memory\n\n- [Amazon Bedrock AgentCore Memory vs EverOS](https://www.anchorterminal.com/compare/agentcore-memory-vs-everos.md)\n- [Amazon Bedrock AgentCore Memory vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/agentcore-memory-vs-tencentdb-agent-memory.md)\n- [Basic Memory vs EverOS](https://www.anchorterminal.com/compare/basic-memory-vs-everos.md)\n- [Basic Memory vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/basic-memory-vs-tencentdb-agent-memory.md)\n- [claude-mem vs EverOS](https://www.anchorterminal.com/compare/claude-mem-vs-everos.md)\n- [claude-mem vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/claude-mem-vs-tencentdb-agent-memory.md)\n- [Cognee vs EverOS](https://www.anchorterminal.com/compare/cognee-vs-everos.md)\n- [Cognee vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/cognee-vs-tencentdb-agent-memory.md)\n- [EverOS vs Agent Platform Memory Bank](https://www.anchorterminal.com/compare/everos-vs-google-memory-bank.md)\n- [EverOS vs Graphicle](https://www.anchorterminal.com/compare/everos-vs-graphicle.md)\n- [EverOS vs Graphiti](https://www.anchorterminal.com/compare/everos-vs-graphiti.md)\n- [EverOS vs Hindsight](https://www.anchorterminal.com/compare/everos-vs-hindsight.md)\n- [EverOS vs Honcho](https://www.anchorterminal.com/compare/everos-vs-honcho.md)\n- [EverOS vs Hy Memory](https://www.anchorterminal.com/compare/everos-vs-hy-memory.md)\n- [EverOS vs LangMem](https://www.anchorterminal.com/compare/everos-vs-langmem.md)\n- [EverOS vs LocalGhost](https://www.anchorterminal.com/compare/everos-vs-localghost.md)\n- [EverOS vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/everos-vs-mem0.md)\n- [EverOS vs MemMachine](https://www.anchorterminal.com/compare/everos-vs-memmachine.md)\n- [EverOS vs Memori](https://www.anchorterminal.com/compare/everos-vs-memori.md)\n- [EverOS vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/everos-vs-memory-reference-server.md)\n- [EverOS vs MemPalace](https://www.anchorterminal.com/compare/everos-vs-mempalace.md)\n- [EverOS vs past.dev](https://www.anchorterminal.com/compare/everos-vs-past-dev.md)\n- [EverOS vs Supermemory API + MCP](https://www.anchorterminal.com/compare/everos-vs-supermemory.md)\n- [EverOS vs Tokenrip](https://www.anchorterminal.com/compare/everos-vs-tokenrip.md)\n- [EverOS vs Zep](https://www.anchorterminal.com/compare/everos-vs-zep.md)\n- [Agent Platform Memory Bank vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/google-memory-bank-vs-tencentdb-agent-memory.md)\n- [Graphiti vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/graphiti-vs-tencentdb-agent-memory.md)\n- [Hindsight vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/hindsight-vs-tencentdb-agent-memory.md)\n- [Honcho vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/honcho-vs-tencentdb-agent-memory.md)\n- [Hy Memory vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/hy-memory-vs-tencentdb-agent-memory.md)\n- [LangMem vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/langmem-vs-tencentdb-agent-memory.md)\n- [LocalGhost vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/localghost-vs-tencentdb-agent-memory.md)\n- [Mem0 Platform + MCP vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/mem0-vs-tencentdb-agent-memory.md)\n- [MemMachine vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/memmachine-vs-tencentdb-agent-memory.md)\n- [Memori vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/memori-vs-tencentdb-agent-memory.md)\n- [Memory (MCP reference server) vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/memory-reference-server-vs-tencentdb-agent-memory.md)\n- [MemPalace vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/mempalace-vs-tencentdb-agent-memory.md)\n- [past.dev vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/past-dev-vs-tencentdb-agent-memory.md)\n- [Supermemory API + MCP vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/supermemory-vs-tencentdb-agent-memory.md)\n- [TencentDB Agent Memory vs Tokenrip](https://www.anchorterminal.com/compare/tencentdb-agent-memory-vs-tokenrip.md)\n- [TencentDB Agent Memory vs Zep](https://www.anchorterminal.com/compare/tencentdb-agent-memory-vs-zep.md)\n- [AI Memory vs EverOS](https://www.anchorterminal.com/compare/ai-memory-vs-everos.md)\n- [AI Memory vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/ai-memory-vs-tencentdb-agent-memory.md)\n- [Context Mode Engine vs EverOS](https://www.anchorterminal.com/compare/context-mode-vs-everos.md)\n- [Context Mode Engine vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/context-mode-vs-tencentdb-agent-memory.md)\n- [Graphicle vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/graphicle-vs-tencentdb-agent-memory.md)\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": "2026-11-07", "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": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "EverOS vs TencentDB Agent Memory", "url": "" } ], "description": "EverOS scores 69.4 (B) to TencentDB Agent Memory's 50.9 (D) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "EverOS B 69.4", "TencentDB Agent Memory D 50.9", "scores" ], "h1": "EverOS vs TencentDB Agent Memory", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/everos-vs-tencentdb-agent-memory", "published": "2026-10-01", "section": "tools", "title": "EverOS vs TencentDB Agent Memory for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/everos-vs-tencentdb-agent-memory" }, "tokens": { "markdown": 6000, "slim": 3430 }, "version": 1 }