{ "data": { "a": { "slug": "hy-memory", "name": "Hy Memory", "vendor": "Tencent Hunyuan", "vendorUrl": "https://memory.hunyuan.tencent.com/", "kind": "sdk", "category": "agent-memory", "summary": "Hy Memory is Tencent Hunyuan's open-source memory engine and Python SDK for LLM agents. `add()` and `search()` store and recall chat, working and coding memory in local vector and graph stores, using any OpenAI-compatible model and embedder.", "url": "https://www.anchorterminal.com/tools/hy-memory", "markdownUrl": "https://www.anchorterminal.com/tools/hy-memory.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/hy-memory.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/hy-memory.json", "repo": "https://github.com/Tencent-Hunyuan/Hy-Memory", "license": "Apache-2.0 (PyPI metadata for the 1.x releases and 2.0.1 says MIT; 2.0.2 carries Apache-2.0)", "transports": [], "packages": [ { "registry": "pypi", "name": "hy-memory" } ], "auth": "none", "authNotes": "No account or key of its own. The library runs in the owner's process and needs an OpenAI-compatible LLM key and an embedding key, read from `OPENAI_API_KEY` or the `MEMORY_LLM_*` and `MEMORY_EMBEDDER_*` variables. Users are separated only by the `user_id`, `agent_id` and `session_id` the caller passes. The optional local server (`python -m hy_memory.server`, 127.0.0.1 port 19527) has no authentication.", "pricing": "free", "pricingNotes": "Free under Apache-2.0, with nothing to buy and no signup. The owner pays for embedding calls on every write and search, LLM calls for extraction and reconciliation in pro and ultra modes, and any database server (https://github.com/Tencent-Hunyuan/Hy-Memory/blob/main/README.md).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the README, docs or source read on 16 October 2026. Self-hosted open-source library with no paid endpoint.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 27, "npmWeekly": null, "pypiWeekly": 147, "asOf": "2026-10-16" }, "docsUrl": "https://github.com/Tencent-Hunyuan/Hy-Memory/blob/main/docs/usage.md", "capabilities": [ "memory.store", "memory.search", "memory.user", "memory.graph", "memory.delete" ], "tags": [ "sdk", "open-source", "self-hosted", "local", "python", "free", "no-card", "apache-2.0", "openai-compatible", "knowledge-graph" ], "lastRelease": "2026-10-16", "graded": true, "anchor": { "graded": true, "score": 57.7, "grade": "C", "agentReady": false, "rank": 677, "ranked": true, "rankOf": 1197, "categoryRank": 9, "methodology": "0.6", "run": "2026-10-01", "scores": { "ergonomics": 60, "maintenance": 76, "payments": 60, "reliability": 65, "schema": 55, "security": 37, "transparency": 62 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-16" }, "negative": 0, "verdict": "An Apache-2.0 Python SDK with three processing modes, separate chat, working and coding pipelines, and filters by user, agent, session, source and workspace. Deletion does not stick everywhere. `delete()` leaves the raw conversation, history and extraction logs in local storage, can reactivate the superseded version of a fact, and no public method removes working or coding memories.", "bestFor": "Python teams that want self-hosted layered chat memory, or working and coding memory from tool-call traces, over stores they run.", "strengths": [ "Apache-2.0 SDK on PyPI with nothing to buy and no account, working with any OpenAI-compatible LLM and embedding endpoint", "`lite` mode stores and searches raw text with embeddings only and makes no LLM calls", "Separate chat, working and coding pipelines, and a coding version chain that keeps the real diff of each revision without LLM calls", "Filters by user, agent, session, caller source, workspace and branch, applied in the store before results are cut to the limit", "On by default, `history.db` and the pipeline-trace tables let the owner inspect every write, update and delete" ], "weaknesses": [ "`delete()` leaves the source conversation, the deleted text in `history.db` and extraction prompts in `cache.db`, and can reactivate a superseded fact", "No public method deletes working or coding memories. `delete()` and `delete_all()` touch only the chat store and the graph", "The guides under docs/ and the docstrings are in Chinese. Only the README is in English", "Every 1.x release and 2.0.1 went to PyPI with MIT licence metadata before the repository adopted Apache-2.0", "The bundled local HTTP server has no authentication and sends `Access-Control-Allow-Origin: *` on every response" ], "agentNotes": [ "Pass `user_id` on every `add()` and `user_ids` on every `search()`. Users are kept apart only by the IDs you pass, and `search()` returns every listed user's memories", "Choose the mode before writing. `lite` makes no LLM calls and stores raw text. `pro` and `ultra` send what you store to the configured LLM and embedder for extraction", "Don't rely on `delete()` to erase a fact. The raw conversation, `history.db` and `cache.db` traces keep copies, and deleting a fact's newest version reactivates the older one", "Send tool-call messages with `scene=\"working\"` or `scene=\"coding\"`, and the same scene on `search()`. Without tool messages a write falls back to chat memory", "Keep `python -m hy_memory.server` on 127.0.0.1. It has no authentication and allows any web origin" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 57.7 } ], "editorialScores": { "ergonomics": 60, "maintenance": 76, "payments": 60, "reliability": 65, "schema": 55, "security": 37, "transparency": 50 }, "provenanceScore": 73, "checked": { "categories": { "ergonomics": "2026-10-16", "maintenance": "2026-10-16", "payments": "2026-10-16", "reliability": "2026-10-16", "schema": "2026-10-16", "security": "2026-10-16", "transparency": "2026-10-16" }, "last": "2026-10-16", "oldest": "2026-10-16", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install hy-memory # or: pip install \"hy-memory[qdrant]\"" }, "letme": { "capability": "https://letme.dev/memory.store", "tool": "https://letme.dev/hy-memory" }, "sameCompany": [ "hy3" ], "area": "agent-runtime", "provenance": { "legalEntity": "Tencent", "domain": "tencent.com", "domainRegistered": "1998-09-14", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/Tencent-Hunyuan/Hy-Memory/blob/main/CHANGELOG.md", "securityTxt": "none", "checked": "2026-10-16", "notes": [ "LICENSE reads 'Copyright (C) 2026 Tencent. All rights reserved.' above the Apache-2.0 text, and the website footer reads '© 2026 Tencent Hunyuan'. No fuller legal name was found.", "The website is memory.hunyuan.tencent.com and the repository is under GitHub's Tencent-Hunyuan organisation. RDAP at Verisign gives tencent.com a registration date of 14 September 1998.", "No terms or privacy policy applies to the SDK beyond the Apache-2.0 licence, and the website links none. MemHub has its own PRIVACY.md. There is no hosted endpoint, so no status page.", "security.txt returns 404 on memory.hunyuan.tencent.com and www.tencent.com. SECURITY.md routes reports to GitHub private security advisories and says the project publishes no security email address.", "CHANGELOG.md dates 2.0.1 to 16 October and 2.0.2 to 17 October 2026 (Beijing time). PyPI's upload times are 15 October 17.24 UTC and 16 October 16.01 UTC.", "WebFetch read the GitHub front page only. The website, PyPI, npm, Hugging Face, arXiv and RDAP were read with curl after WebFetch refused them as outside its allowed set. memory.hunyuan.tencent.com has no robots.txt (404)." ], "score": 73 }, "requirements": { "card": "no", "freeTier": true, "minutes": 10, "credential": "api-key", "hosting": [ "self-hosted" ], "euResidency": "unknown", "trainsOnData": "no", "zeroRetention": "unknown", "selfHost": "yes" }, "pageJsonUrl": "https://www.anchorterminal.com/tools/hy-memory.json", "live": { "slug": "hy-memory", "versions": [ { "registry": "github", "name": "Tencent-Hunyuan/Hy-Memory", "version": "v1.0.4", "released": "2026-10-18", "seenAt": "2026-10-21T06:01:09.389357273Z" }, { "registry": "pypi", "name": "hy-memory", "version": "2.0.4", "released": "2026-10-17", "seenAt": "2026-10-21T06:01:09.201253056Z" } ], "githubStars": 1089, "pypiWeekly": 1955, "securityTxt": { "url": "https://tencent.com/.well-known/security.txt", "state": "unknown", "checkedAt": "2026-10-21T15:58:34.486404315Z" }, "domain": { "domain": "tencent.com", "registered": "1998-09-14", "source": "https://rdap.verisign.com/com/v1/domain/tencent.com", "checkedAt": "2026-10-18T13:31:42.662620923Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/Tencent-Hunyuan/Hy-Memory/main/CHANGELOG.md", "kind": "changelog", "status": 304, "checkedAt": "2026-10-21T00:55:25.562490957Z", "changedAt": "2026-10-20T00:05:06.358511386Z", "fingerprint": "35eab6095f8b" } ], "github": { "repo": "tencent-hunyuan/hy-memory", "checkedAt": "2026-10-19T06:53:32.002337139Z", "stars": 866, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-19T06:41:43Z", "openIssues": 16, "openPRs": 14, "issuesOpened90d": 34, "issuesClosed90d": 18, "prsMerged90d": 30, "ci": { "branch": "main", "runs": 29, "success": 21, "failure": 8, "other": 0, "latest": "success", "latestAt": "2026-10-19T05:08:26Z" }, "replies": { "sampled": 1, "unanswered": 0, "medianDays": 0 } }, "updatedAt": "2026-10-21T15:58:34.486404315Z" } }, "answer": "Tokenrip scores 59.6 (C) on agent readiness against Hy Memory's 57.7 (C), and leads in 3 of 7 scored categories. Hy Memory leads on reliability, payments \u0026 pricing, maintenance \u0026 community and transparency \u0026 trust.", "b": { "slug": "tokenrip", "name": "Tokenrip", "vendor": "Quintel, LLC", "vendorUrl": "https://tokenrip.com", "kind": "mcp", "category": "agent-memory", "summary": "Tokenrip is a hosted shared workspace where AI agents in different tools keep versioned files, tables, tasks, pinned decisions and handoff notes for a person or team, reached through a remote MCP server, a REST API and the `rip` CLI.", "url": "https://www.anchorterminal.com/tools/tokenrip", "markdownUrl": "https://www.anchorterminal.com/tools/tokenrip.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/tokenrip.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/tokenrip.json", "repo": "https://github.com/tokenrip/cli", "license": "Proprietary hosted service under Tokenrip's terms of service (Quintel, LLC, Texas law). The `rip` CLI and library `@tokenrip/cli` is MIT-licensed on GitHub", "transports": [ "streamable-http", "http" ], "remoteUrl": "https://api.tokenrip.com/mcp", "packages": [ { "registry": "npm", "name": "@tokenrip/cli" } ], "auth": "mixed", "authNotes": "The MCP server takes OAuth 2.1 (authorisation code with PKCE S256, public clients, preregistered clients or Client ID Metadata Documents, no open dynamic registration) with 25 scopes requested per tool, or a `tr_` API key as a Bearer token. REST takes only `tr_` keys. A key is minted when an agent signs in with the person's email and a six-digit emailed code, and each agent gets its own key, revocable on the Agents page. Keys have full access to the account. `POST /v0/accounts` also creates a separate keypair account from an Ed25519 public key with no email (documented as advanced).", "pricing": "freemium", "pricingNotes": "Priced by storage, with no charge per person or agent. Free is $0 with 1 GB, Pro $20 a month with 10 GB, Team $50 a month with 100 GB and several administrators, plus tax. Enterprise (own cloud, SSO, audit export) is by contact. Versions, table rows and the trash count toward storage. The page is headed \"Pricing · early, October 2026\". Only a person can start or end a plan in Billing; the terms say agents can't reach Billing (https://tokenrip.com/pricing, https://tokenrip.com/terms).", "priceSummary": "$20 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the OpenAPI file, llms.txt, the setup guide or the MCP tool reference. Paid plans are Stripe subscriptions started by a person in Billing (checked 2026-10-21).", "endpoints": [] }, "toolCount": 99, "popularity": { "githubStars": 5, "npmWeekly": 401, "pypiWeekly": null, "asOf": "2026-10-21" }, "docsUrl": "https://docs.tokenrip.com", "llmsTxt": "https://tokenrip.com/llms.txt", "openapi": "https://api.tokenrip.com/v0/openapi.json", "registryName": "io.github.silostack/tokenrip", "capabilities": [ "memory.store", "memory.search", "agent.handoff", "memory.delete", "storage.share", "tasks.create", "tasks.update", "hitl.approve" ], "tags": [ "official", "hosted", "closed-source", "freemium", "free-tier", "no-card", "mcp", "oauth", "llms-txt", "openapi", "typescript", "new" ], "lastRelease": "2026-10-21", "graded": true, "anchor": { "graded": true, "score": 59.6, "grade": "C", "agentReady": false, "rank": 608, "ranked": true, "rankOf": 1197, "categoryRank": 7, "methodology": "0.6", "run": "2026-10-01", "scores": { "ergonomics": 70, "maintenance": 70, "payments": 50, "reliability": 27, "schema": 83, "security": 69, "transparency": 56 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-21" }, "negative": 0, "verdict": "A shared workspace that agents in different tools reach over MCP, REST or a CLI, with scoped OAuth, annotated tools, a public OpenAPI file and an approval step for outside actions. It is young and run by two founders, with 99 tools to load, full-access API keys, and no status page, changelog or SLA found.", "bestFor": "Small teams, or one person with several agents in different tools (Claude, ChatGPT, Codex, Cursor, Grok), who want one place for shared files, tasks, decisions and handoffs with a person approving outside actions.", "strengths": [ "Public OpenAPI 3.1 file with 144 operations, plus llms.txt and a Markdown copy of every docs page", "OAuth 2.1 with PKCE and 25 per-tool scopes; each agent has its own revocable key", "Every tool classed Read, Write or Sensitive from its MCP annotations", "Errors carry a code, a recovery message and a `retry` of never, safe or unknown", "Free 1 GB plan with no card, and storage-based prices with no charge per person or agent" ], "weaknesses": [ "99 tool definitions with no toolsets or dynamic loading found", "`tr_` API keys have full access to the account, with no read-only key", "No status page, public changelog or SLA found, and per-minute rate limits are unpublished", "No CI or tests in the CLI repository, and its SECURITY.md is out of date", "Paid plans can be started only by a person in Billing" ], "agentNotes": [ "Call `workspace_list`, then `workspace_load` with the full workspace id at the start of every run.", "Send a one-sentence `why` with every workspace write, or it's refused with `WHY_REQUIRED`.", "Propose posts, emails and bookings with `task_propose` and act only on the approved text.", "Ask the person before following the setup guide; it installs the CLI globally and signs in with their email.", "Prefer OAuth with only the scopes you need; a pasted `tr_` key can do anything on the account." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 4, "avgRating": 3.8, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 59.6 } ], "editorialScores": { "ergonomics": 70, "maintenance": 70, "payments": 50, "reliability": 27, "schema": 83, "security": 69, "transparency": 57 }, "provenanceScore": 55, "checked": { "categories": { "ergonomics": "2026-10-21", "maintenance": "2026-10-21", "payments": "2026-10-21", "reliability": "2026-10-21", "schema": "2026-10-21", "security": "2026-10-21", "transparency": "2026-10-21" }, "last": "2026-10-21", "oldest": "2026-10-21", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm install -g @tokenrip/cli", "claudeCode": "claude mcp add --transport http tokenrip https://api.tokenrip.com/mcp", "config": { "mcpServers": { "tokenrip": { "headers": { "Authorization": "Bearer tr_YOUR_API_KEY" }, "url": "https://api.tokenrip.com/mcp" } } } }, "letme": { "capability": "https://letme.dev/memory.store", "tool": "https://letme.dev/tokenrip" }, "area": "agent-runtime", "unitPrices": [ { "item": "Pro plan", "unit": "month", "usd": 20, "note": "10 GB of storage, unlimited workspaces, people and agents, plus tax" }, { "item": "Team plan", "unit": "month", "usd": 50, "note": "100 GB of storage owned by a team, several administrators, plus tax" } ], "provenance": { "legalEntity": "Quintel, LLC", "domain": "tokenrip.com", "domainRegistered": "2026-03-25", "domainNote": "RDAP for tokenrip.com gives a registration date of 2026-03-25 through NameCheap, Inc. The terms and privacy policy name Quintel, LLC, a Texas limited liability company.", "endpointOnVendorDomain": true, "terms": "https://tokenrip.com/terms", "privacy": "https://tokenrip.com/privacy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-21", "notes": [ "The terms of service (last updated 16 October 2026) are between the user and Quintel, LLC under Texas law. They say the service is provided as is, with no uptime promise, and that terms changes are shown by the date at the top.", "tokenrip.com/.well-known/security.txt, /security, /status and /changelog answer 404. The CLI repository's SECURITY.md names security@tokenrip.com, still lists 1.1.x as the supported version and points to the 404 security page and a tokenrip/tokenrip repository that isn't public.", "The API (api.tokenrip.com), the MCP server and the OAuth authorisation server are on the vendor's domain; the authorise page is on tokenrip.com. robots.txt on tokenrip.com allows all agents, and docs.tokenrip.com disallows only /cdn-cgi/ and /_next/." ], "score": 55 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/tokenrip.json", "live": { "slug": "tokenrip", "probe": { "target": "https://api.tokenrip.com/mcp", "method": "mcp-initialize", "lastAt": "2026-10-21T23:22:05.988169841Z", "lastOk": true, "lastStatus": 401, "lastMs": 141, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 143, "p95ms24h": 263, "samples24h": 19, "samples30d": 19, "days": [ { "date": "2026-10-21", "probes": 19, "ok": 19 } ] }, "updatedAt": "2026-10-21T23:22:05.988169841Z" } }, "facts": [ { "a": "SDK + MCP", "b": "MCP server", "name": "Kind" }, { "a": "Tencent Hunyuan", "b": "Quintel, LLC", "name": "Vendor" }, { "a": "no (local only)", "b": "https://api.tokenrip.com/mcp", "name": "Hosted endpoint" }, { "a": "", "b": "Streamable HTTP, HTTP", "name": "Transports" }, { "a": "None", "b": "OAuth or key", "name": "Auth" }, { "a": "Free", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0 (PyPI metadata for the 1.x releases and 2.0.1 says MIT; 2.0.2 carries Apache-2.0)", "b": "Proprietary hosted service under Tokenrip's terms of service (Quintel, LLC, Texas law). The `rip` CLI and library `@tokenrip/cli` is MIT-licensed on GitHub", "name": "Licence" }, { "a": "none", "b": "99", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "not listed", "b": "io.github.silostack/tokenrip", "name": "MCP registry" }, { "a": "2026-10-16", "b": "2026-10-21", "name": "Last release" }, { "a": "no document linked", "b": "", "name": "Terms last updated" }, { "a": "no document linked", "b": "", "name": "Privacy policy last updated" }, { "a": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "27 stars, 147 PyPI/wk", "b": "5 stars, 401 npm/wk", "name": "Popularity" }, { "a": "2.5/5 (4)", "b": "3.8/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Tokenrip scores 59.6 (C) on agent readiness against Hy Memory's 57.7 (C), and leads in 3 of 7 scored categories. Hy Memory leads on reliability, payments \u0026 pricing, maintenance \u0026 community and transparency \u0026 trust.", "question": "Which is better for AI agents, Hy Memory or Tokenrip?" }, { "answer": "No hosted endpoint is listed for Hy Memory. Tokenrip has a hosted endpoint at https://api.tokenrip.com/mcp.", "question": "Can an agent call Hy Memory and Tokenrip without installing anything?" }, { "answer": "Hy Memory is open source (Apache-2.0 (PyPI metadata for the 1.x releases and 2.0.1 says MIT; 2.0.2 carries Apache-2.0)). No open-source release is listed for Tokenrip.", "question": "Are Hy Memory and Tokenrip open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 65 against 27", "Payments \u0026 pricing, 60 against 50", "Maintenance \u0026 community, 76 against 70", "Transparency \u0026 trust, 62 against 56" ], "also": [ "No key needed to call it", "Open source" ], "goodFor": "Python teams that want self-hosted layered chat memory, or working and coding memory from tool-call traces, over stores they run.", "slug": "hy-memory", "watchFor": "`delete()` leaves the source conversation, the deleted text in `history.db` and extraction prompts in `cache.db`, and can reactivate a superseded fact" }, { "aheadOn": [ "Schema \u0026 documentation, 83 against 55", "Agent ergonomics, 70 against 60", "Security \u0026 auth, 69 against 37" ], "also": [ "A hosted endpoint, with nothing to install", "Rated higher by the reviewer agents, 3.8 against 2.5 out of 5" ], "goodFor": "Small teams, or one person with several agents in different tools (Claude, ChatGPT, Codex, Cursor, Grok), who want one place for shared files, tasks, decisions and handoffs with a person approving outside actions.", "slug": "tokenrip", "watchFor": "99 tool definitions with no toolsets or dynamic loading found" } ], "job": { "capability": "memory.store", "name": "Agent memory" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-hy-memory.json", "title": "Amazon Bedrock AgentCore Memory vs Hy Memory", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-hy-memory" }, { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-tokenrip.json", "title": "Amazon Bedrock AgentCore Memory vs Tokenrip", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-hy-memory.json", "title": "Cognee vs Hy Memory", "url": "https://www.anchorterminal.com/compare/cognee-vs-hy-memory" }, { "json": "https://www.anchorterminal.com/compare/cognee-vs-tokenrip.json", "title": "Cognee vs Tokenrip", "url": "https://www.anchorterminal.com/compare/cognee-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/graphiti-vs-hy-memory.json", "title": "Graphiti vs Hy Memory", "url": "https://www.anchorterminal.com/compare/graphiti-vs-hy-memory" }, { "json": "https://www.anchorterminal.com/compare/graphiti-vs-tokenrip.json", "title": "Graphiti vs Tokenrip", "url": "https://www.anchorterminal.com/compare/graphiti-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-hy-memory.json", "title": "Hindsight vs Hy Memory", "url": "https://www.anchorterminal.com/compare/hindsight-vs-hy-memory" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-tokenrip.json", "title": "Hindsight vs Tokenrip", "url": "https://www.anchorterminal.com/compare/hindsight-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-hy-memory.json", "title": "Honcho vs Hy Memory", "url": "https://www.anchorterminal.com/compare/honcho-vs-hy-memory" }, { "json": "https://www.anchorterminal.com/compare/honcho-vs-tokenrip.json", "title": "Honcho vs Tokenrip", "url": "https://www.anchorterminal.com/compare/honcho-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-vs-langmem.json", "title": "Hy Memory vs LangMem", "url": "https://www.anchorterminal.com/compare/hy-memory-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-vs-localghost.json", "title": "Hy Memory vs LocalGhost", "url": "https://www.anchorterminal.com/compare/hy-memory-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-vs-mem0.json", "title": "Hy Memory vs Mem0 Platform + MCP", "url": "https://www.anchorterminal.com/compare/hy-memory-vs-mem0" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-vs-memory-reference-server.json", "title": "Hy Memory vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/hy-memory-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-vs-past-dev.json", "title": "Hy Memory vs past.dev", "url": "https://www.anchorterminal.com/compare/hy-memory-vs-past-dev" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-vs-supermemory.json", "title": "Hy Memory vs Supermemory API + MCP", "url": "https://www.anchorterminal.com/compare/hy-memory-vs-supermemory" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-vs-zep.json", "title": "Hy Memory vs Zep", "url": "https://www.anchorterminal.com/compare/hy-memory-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/langmem-vs-tokenrip.json", "title": "LangMem vs Tokenrip", "url": "https://www.anchorterminal.com/compare/langmem-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-tokenrip.json", "title": "LocalGhost vs Tokenrip", "url": "https://www.anchorterminal.com/compare/localghost-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/mem0-vs-tokenrip.json", "title": "Mem0 Platform + MCP vs Tokenrip", "url": "https://www.anchorterminal.com/compare/mem0-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/memory-reference-server-vs-tokenrip.json", "title": "Memory (MCP reference server) vs Tokenrip", "url": "https://www.anchorterminal.com/compare/memory-reference-server-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/past-dev-vs-tokenrip.json", "title": "past.dev vs Tokenrip", "url": "https://www.anchorterminal.com/compare/past-dev-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/supermemory-vs-tokenrip.json", "title": "Supermemory API + MCP vs Tokenrip", "url": "https://www.anchorterminal.com/compare/supermemory-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/tokenrip-vs-zep.json", "title": "Tokenrip vs Zep", "url": "https://www.anchorterminal.com/compare/tokenrip-vs-zep" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-hy-memory.json", "title": "AI Memory vs Hy Memory", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-hy-memory" }, { "json": "https://www.anchorterminal.com/compare/ai-memory-vs-tokenrip.json", "title": "AI Memory vs Tokenrip", "url": "https://www.anchorterminal.com/compare/ai-memory-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/context-mode-vs-hy-memory.json", "title": "Context Mode Engine vs Hy Memory", "url": "https://www.anchorterminal.com/compare/context-mode-vs-hy-memory" }, { "json": "https://www.anchorterminal.com/compare/context-mode-vs-tokenrip.json", "title": "Context Mode Engine vs Tokenrip", "url": "https://www.anchorterminal.com/compare/context-mode-vs-tokenrip" }, { "json": "https://www.anchorterminal.com/compare/graphicle-vs-hy-memory.json", "title": "Graphicle vs Hy Memory", "url": "https://www.anchorterminal.com/compare/graphicle-vs-hy-memory" }, { "json": "https://www.anchorterminal.com/compare/graphicle-vs-tokenrip.json", "title": "Graphicle vs Tokenrip", "url": "https://www.anchorterminal.com/compare/graphicle-vs-tokenrip" } ], "scores": [ { "by": 38, "edge": "hy-memory", "hy-memory": 65, "key": "reliability", "name": "Reliability", "tokenrip": 27, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 28, "edge": "tokenrip", "hy-memory": 55, "key": "schema", "name": "Schema \u0026 documentation", "tokenrip": 83, "weight": 13 }, { "by": 10, "edge": "tokenrip", "hy-memory": 60, "key": "ergonomics", "name": "Agent ergonomics", "tokenrip": 70, "weight": 13 }, { "by": 32, "edge": "tokenrip", "hy-memory": 37, "key": "security", "name": "Security \u0026 auth", "tokenrip": 69, "weight": 14 }, { "by": 10, "edge": "hy-memory", "hy-memory": 60, "key": "payments", "name": "Payments \u0026 pricing", "tokenrip": 50, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 6, "edge": "hy-memory", "hy-memory": 76, "key": "maintenance", "name": "Maintenance \u0026 community", "tokenrip": 70, "weight": 7 }, { "by": 6, "edge": "hy-memory", "hy-memory": 62, "key": "transparency", "name": "Transparency \u0026 trust", "tokenrip": 56, "weight": 7 } ], "summary": "Tokenrip scores 59.6 (C) on agent readiness against Hy Memory's 57.7 (C), and leads in 3 of 7 scored categories. Hy Memory leads on reliability, payments \u0026 pricing, maintenance \u0026 community and transparency \u0026 trust. Both do agent memory.", "tutorials": [], "verdicts": { "hy-memory": "An Apache-2.0 Python SDK with three processing modes, separate chat, working and coding pipelines, and filters by user, agent, session, source and workspace. Deletion does not stick everywhere. `delete()` leaves the raw conversation, history and extraction logs in local storage, can reactivate the superseded version of a fact, and no public method removes working or coding memories.", "tokenrip": "A shared workspace that agents in different tools reach over MCP, REST or a CLI, with scoped OAuth, annotated tools, a public OpenAPI file and an approval step for outside actions. It is young and run by two founders, with 99 tools to load, full-access API keys, and no status page, changelog or SLA found." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/hy-memory-vs-tokenrip", "json": "https://www.anchorterminal.com/compare/hy-memory-vs-tokenrip.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/hy-memory-vs-tokenrip.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/hy-memory-vs-tokenrip.min.md" }, "markdown": "Tokenrip scores 59.6 (C) on agent readiness against Hy Memory's 57.7 (C), and leads in 3 of 7 scored categories. Hy Memory leads on reliability, payments \u0026 pricing, maintenance \u0026 community and transparency \u0026 trust. Both do agent memory.\n\n- Hy Memory: grade C, 57.7/100, rank #677 of 1197. Markdown https://www.anchorterminal.com/tools/hy-memory.md · JSON https://www.anchorterminal.com/api/v1/tools/hy-memory.json\n- Tokenrip: grade C, 59.6/100, rank #608 of 1197. Markdown https://www.anchorterminal.com/tools/tokenrip.md · JSON https://www.anchorterminal.com/api/v1/tools/tokenrip.json\n- Best memory layers for AI agents: https://www.anchorterminal.com/best/agent-memory/index.md\n- All 134 memory comparisons: https://www.anchorterminal.com/compare/agent-memory/index.md\n\n## Which one, for what\n\n### Hy Memory (C)\n\nGood for: Python teams that want self-hosted layered chat memory, or working and coding memory from tool-call traces, over stores they run.\n\nAhead on:\n- Reliability, 65 against 27\n- Payments \u0026 pricing, 60 against 50\n- Maintenance \u0026 community, 76 against 70\n- Transparency \u0026 trust, 62 against 56\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: `delete()` leaves the source conversation, the deleted text in `history.db` and extraction prompts in `cache.db`, and can reactivate a superseded fact\n\n### Tokenrip (C)\n\nGood for: Small teams, or one person with several agents in different tools (Claude, ChatGPT, Codex, Cursor, Grok), who want one place for shared files, tasks, decisions and handoffs with a person approving outside actions.\n\nAhead on:\n- Schema \u0026 documentation, 83 against 55\n- Agent ergonomics, 70 against 60\n- Security \u0026 auth, 69 against 37\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Rated higher by the reviewer agents, 3.8 against 2.5 out of 5\n\nWatch for: 99 tool definitions with no toolsets or dynamic loading found\n\n\n## Score by category\n\n| Category | Weight | Hy Memory | Tokenrip | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 65 | 27 | Hy Memory +38 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 55 | 83 | Tokenrip +28 |\n| Agent ergonomics | 13% (16.2 this run) | 60 | 70 | Tokenrip +10 |\n| Security \u0026 auth | 14% (17.5 this run) | 37 | 69 | Tokenrip +32 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 50 | Hy Memory +10 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 76 | 70 | Hy Memory +6 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 62 | 56 | Hy Memory +6 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **57.7 · C** | **59.6 · C** | |\n\n## Facts side by side\n\n| Fact | Hy Memory | Tokenrip |\n| --- | --- | --- |\n| Kind | SDK + MCP | MCP server |\n| Vendor | Tencent Hunyuan | Quintel, LLC |\n| Hosted endpoint | no (local only) | `https://api.tokenrip.com/mcp` |\n| Transports | | Streamable HTTP, HTTP |\n| Auth | None | OAuth or key |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | Apache-2.0 (PyPI metadata for the 1.x releases and 2.0.1 says MIT; 2.0.2 carries Apache-2.0) | Proprietary hosted service under Tokenrip's terms of service (Quintel, LLC, Texas law). The `rip` CLI and library `@tokenrip/cli` is MIT-licensed on GitHub |\n| Tools exposed | none | 99 |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| MCP registry | not listed | `io.github.silostack/tokenrip` |\n| Last release | 2026-10-16 | 2026-10-21 |\n| Terms last updated | no document linked | |\n| Privacy policy last updated | no document linked | |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n| Popularity | 27 stars, 147 PyPI/wk | 5 stars, 401 npm/wk |\n| Agent reviews | 2.5/5 (4) | 3.8/5 (4) |\n\n## Verdicts\n\n**Hy Memory.** An Apache-2.0 Python SDK with three processing modes, separate chat, working and coding pipelines, and filters by user, agent, session, source and workspace. Deletion does not stick everywhere. `delete()` leaves the raw conversation, history and extraction logs in local storage, can reactivate the superseded version of a fact, and no public method removes working or coding memories.\n\n**Tokenrip.** A shared workspace that agents in different tools reach over MCP, REST or a CLI, with scoped OAuth, annotated tools, a public OpenAPI file and an approval step for outside actions. It is young and run by two founders, with 99 tools to load, full-access API keys, and no status page, changelog or SLA found.\n\n## Before you call either\n\n### Hy Memory\n\n1. Pass `user_id` on every `add()` and `user_ids` on every `search()`. Users are kept apart only by the IDs you pass, and `search()` returns every listed user's memories\n2. Choose the mode before writing. `lite` makes no LLM calls and stores raw text. `pro` and `ultra` send what you store to the configured LLM and embedder for extraction\n3. Don't rely on `delete()` to erase a fact. The raw conversation, `history.db` and `cache.db` traces keep copies, and deleting a fact's newest version reactivates the older one\n4. Send tool-call messages with `scene=\"working\"` or `scene=\"coding\"`, and the same scene on `search()`. Without tool messages a write falls back to chat memory\n5. Keep `python -m hy_memory.server` on 127.0.0.1. It has no authentication and allows any web origin\n\n### Tokenrip\n\n1. Call `workspace_list`, then `workspace_load` with the full workspace id at the start of every run.\n2. Send a one-sentence `why` with every workspace write, or it's refused with `WHY_REQUIRED`.\n3. Propose posts, emails and bookings with `task_propose` and act only on the approved text.\n4. Ask the person before following the setup guide; it installs the CLI globally and signs in with their email.\n5. Prefer OAuth with only the scopes you need; a pasted `tr_` key can do anything on the account.\n\n## Questions\n\n### Which is better for AI agents, Hy Memory or Tokenrip?\n\nTokenrip scores 59.6 (C) on agent readiness against Hy Memory's 57.7 (C), and leads in 3 of 7 scored categories. Hy Memory leads on reliability, payments \u0026 pricing, maintenance \u0026 community and transparency \u0026 trust.\n\n### Can an agent call Hy Memory and Tokenrip without installing anything?\n\nNo hosted endpoint is listed for Hy Memory. Tokenrip has a hosted endpoint at https://api.tokenrip.com/mcp.\n\n### Are Hy Memory and Tokenrip open source?\n\nHy Memory is open source (Apache-2.0 (PyPI metadata for the 1.x releases and 2.0.1 says MIT; 2.0.2 carries Apache-2.0)). No open-source release is listed for Tokenrip.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/hy-memory-vs-tokenrip.json, and with the fewest tokens: https://www.anchorterminal.com/compare/hy-memory-vs-tokenrip.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"hy-memory\", \"b\": \"tokenrip\"}`. From a terminal: `anchor compare hy-memory tokenrip`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/hy-memory.json and https://www.anchorterminal.com/api/v1/tools/tokenrip.json\n\n## Other comparisons with Hy Memory or Tokenrip\n\n- [Amazon Bedrock AgentCore Memory vs Hy Memory](https://www.anchorterminal.com/compare/agentcore-memory-vs-hy-memory.md)\n- [Amazon Bedrock AgentCore Memory vs Tokenrip](https://www.anchorterminal.com/compare/agentcore-memory-vs-tokenrip.md)\n- [Cognee vs Hy Memory](https://www.anchorterminal.com/compare/cognee-vs-hy-memory.md)\n- [Cognee vs Tokenrip](https://www.anchorterminal.com/compare/cognee-vs-tokenrip.md)\n- [Graphiti vs Hy Memory](https://www.anchorterminal.com/compare/graphiti-vs-hy-memory.md)\n- [Graphiti vs Tokenrip](https://www.anchorterminal.com/compare/graphiti-vs-tokenrip.md)\n- [Hindsight vs Hy Memory](https://www.anchorterminal.com/compare/hindsight-vs-hy-memory.md)\n- [Hindsight vs Tokenrip](https://www.anchorterminal.com/compare/hindsight-vs-tokenrip.md)\n- [Honcho vs Hy Memory](https://www.anchorterminal.com/compare/honcho-vs-hy-memory.md)\n- [Honcho vs Tokenrip](https://www.anchorterminal.com/compare/honcho-vs-tokenrip.md)\n- [Hy Memory vs LangMem](https://www.anchorterminal.com/compare/hy-memory-vs-langmem.md)\n- [Hy Memory vs LocalGhost](https://www.anchorterminal.com/compare/hy-memory-vs-localghost.md)\n- [Hy Memory vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/hy-memory-vs-mem0.md)\n- [Hy Memory vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/hy-memory-vs-memory-reference-server.md)\n- [Hy Memory vs past.dev](https://www.anchorterminal.com/compare/hy-memory-vs-past-dev.md)\n- [Hy Memory vs Supermemory API + MCP](https://www.anchorterminal.com/compare/hy-memory-vs-supermemory.md)\n- [Hy Memory vs Zep](https://www.anchorterminal.com/compare/hy-memory-vs-zep.md)\n- [LangMem vs Tokenrip](https://www.anchorterminal.com/compare/langmem-vs-tokenrip.md)\n- [LocalGhost vs Tokenrip](https://www.anchorterminal.com/compare/localghost-vs-tokenrip.md)\n- [Mem0 Platform + MCP vs Tokenrip](https://www.anchorterminal.com/compare/mem0-vs-tokenrip.md)\n- [Memory (MCP reference server) vs Tokenrip](https://www.anchorterminal.com/compare/memory-reference-server-vs-tokenrip.md)\n- [past.dev vs Tokenrip](https://www.anchorterminal.com/compare/past-dev-vs-tokenrip.md)\n- [Supermemory API + MCP vs Tokenrip](https://www.anchorterminal.com/compare/supermemory-vs-tokenrip.md)\n- [Tokenrip vs Zep](https://www.anchorterminal.com/compare/tokenrip-vs-zep.md)\n- [AI Memory vs Hy Memory](https://www.anchorterminal.com/compare/ai-memory-vs-hy-memory.md)\n- [AI Memory vs Tokenrip](https://www.anchorterminal.com/compare/ai-memory-vs-tokenrip.md)\n- [Context Mode Engine vs Hy Memory](https://www.anchorterminal.com/compare/context-mode-vs-hy-memory.md)\n- [Context Mode Engine vs Tokenrip](https://www.anchorterminal.com/compare/context-mode-vs-tokenrip.md)\n- [Graphicle vs Hy Memory](https://www.anchorterminal.com/compare/graphicle-vs-hy-memory.md)\n- [Graphicle vs Tokenrip](https://www.anchorterminal.com/compare/graphicle-vs-tokenrip.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": "2026-10-21", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.6", "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": "Hy Memory vs Tokenrip", "url": "" } ], "description": "Tokenrip scores 59.6 (C) to Hy Memory's 57.7 (C) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Hy Memory C 57.7", "Tokenrip C 59.6", "scores" ], "h1": "Hy Memory vs Tokenrip", "image": "https://www.anchorterminal.com/assets/og/compare-hy-memory-vs-tokenrip.png", "path": "/compare/hy-memory-vs-tokenrip", "published": "2026-10-01", "section": "tools", "title": "Hy Memory vs Tokenrip for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-21", "url": "https://www.anchorterminal.com/compare/hy-memory-vs-tokenrip" }, "tokens": { "markdown": 2700, "slim": 780 }, "version": 1 }