{ "data": { "a": { "slug": "hindsight", "name": "Hindsight", "vendor": "Vectorize", "vendorUrl": "https://hindsight.vectorize.io", "kind": "http-api", "category": "agent-memory", "summary": "Memory engine for storing and retrieving information used by agents.", "url": "https://www.anchorterminal.com/tools/hindsight", "markdownUrl": "https://www.anchorterminal.com/tools/hindsight.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/hindsight.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/hindsight.json", "repo": "https://github.com/vectorize-io/hindsight", "license": "MIT", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://api.hindsight.vectorize.io", "packages": [ { "registry": "pypi", "name": "hindsight-client" }, { "registry": "npm", "name": "@vectorize-io/hindsight-client" }, { "registry": "pypi", "name": "hindsight-api" } ], "auth": "mixed", "authNotes": "Bearer API key on api.hindsight.vectorize.io. Keys can be restricted to named banks and set to expire after an hour to a year, and revoking a parent key revokes its child keys. The hosted MCP uses OAuth with PKCE (RFC 9728), or the same key as a Bearer header. A self-hosted server exposes MCP at /mcp/{bank_id}/ on port 8888.", "pricing": "usage", "pricingNotes": "Hindsight Cloud is pay as you go, with no monthly fee or seat price. Retain $10.00 per million tokens, recall $0.75 per million, reflect $0.05 a call, Iris Extract $7.50 per million, mental model retrieval $0.25 per million, mental model refresh $0.05 a call, storage $0.25 per million tokens a month. New accounts get free credits, amount not stated. Enterprise adds dedicated infrastructure and up to a 99.95 per cent uptime SLA (https://vectorize.io/pricing). Credit is bought in amounts from $5 to $1,000, and calls return 402 once the balance is empty (https://docs.hindsight.vectorize.io/billing/). Self-hosting is free under MIT.", "priceSummary": "$0.05 / call", "where": "hosted", "x402": { "level": "no", "endpoints": [] }, "toolCount": 27, "popularity": { "githubStars": 43400, "npmWeekly": 44381, "pypiWeekly": 227251, "asOf": "2026-09-30" }, "docsUrl": "https://docs.hindsight.vectorize.io", "openapi": "https://hindsight.vectorize.io/openapi.json", "capabilities": [ "memory.store", "memory.search", "memory.delete" ], "tags": [ "hosted", "usage-priced", "mcp", "oauth", "openapi", "python", "typescript", "open-source", "self-hosted", "enterprise" ], "lastRelease": "2026-09-29", "graded": true, "anchor": { "graded": true, "score": 50.2, "grade": "D", "agentReady": false, "rank": 844, "ranked": true, "rankOf": 1099, "categoryRank": 11, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 57, "maintenance": 80, "payments": 30, "reliability": 25, "schema": 68, "security": 58, "transparency": 45 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "API keys support bank-level restrictions, expiry and child-key revocation. Retain ingestion costs $10 per million tokens.", "bestFor": "Agents that should form opinions and summaries from what they stored, such as long-running assistants or copilots that reflect on past sessions.", "strengths": [ "Keys restricted to named banks, with expiry from an hour to a year and child-key revocation", "`Memory Defense` screens every retain, with regex redaction even in the open-source server", "Published per-token and per-call Cloud prices, with no monthly fee, and a published 99.9 per cent SLA", "MIT server in one Docker image with an MCP endpoint per bank", "Eight PyPI releases between 22 July and 29 September 2026" ], "weaknesses": [ "Retain at $10 per million tokens is the priciest ingestion in this category", "27 MCP tools per bank, with no subset or read-only option", "No status page, no published rate limits and no llms.txt", "Prompt-injection blocking and audit trails are Enterprise only", "Free credit amount not published" ], "agentNotes": [ "Scope the MCP URL to one bank (/mcp/{bank}/) so every call lands in the right memory and three bank-admin tools drop out", "Use recall for lookups and keep reflect ($0.05 a call) for questions that need reasoning", "Pass `async: true` on large retains so the call returns before extraction finishes", "Treat HTTP 402 as out of credit and 403 as a key that can't reach that bank" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 50.2 } ], "editorialScores": { "ergonomics": 57, "maintenance": 80, "payments": 30, "reliability": 25, "schema": 68, "security": 58, "transparency": 30 }, "provenanceScore": 59 }, "connect": { "install": "pip install hindsight-client # or: npm install @vectorize-io/hindsight-client", "http": "curl -s \"https://api.hindsight.vectorize.io/v1/default/banks/my-bank/memories/list\" -H \"Authorization: Bearer $HINDSIGHT_API_KEY\"", "claudeCode": "claude mcp add --transport http hindsight https://api.hindsight.vectorize.io/mcp/my-bank/", "config": { "mcpServers": { "hindsight": { "headers": { "Authorization": "Bearer ${HINDSIGHT_API_KEY}" }, "type": "http", "url": "https://api.hindsight.vectorize.io/mcp/my-bank/" } } } }, "letme": { "capability": "https://letme.dev/memory.store", "tool": "https://letme.dev/hindsight" }, "area": "agent-runtime", "unitPrices": [ { "item": "Retain", "unit": "1m-tokens", "usd": 10, "note": "input tokens" }, { "item": "Recall", "unit": "1m-tokens", "usd": 0.75, "note": "output tokens" }, { "item": "Reflect", "unit": "call", "usd": 0.05 }, { "item": "Iris Extract", "unit": "1m-tokens", "usd": 7.5 }, { "item": "Mental model refresh", "unit": "call", "usd": 0.05 }, { "item": "Storage", "unit": "1m-tokens", "usd": 0.25, "note": "per million tokens stored, per month" } ], "provenance": { "legalEntity": "Vectorize, Inc.", "domain": "vectorize.io", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://vectorize.io/terms", "privacy": "https://vectorize.io/privacy", "statusPage": "", "changelog": "https://docs.hindsight.vectorize.io/whats-new", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "The entity name comes from the copyright line on vectorize.io. The privacy policy is embedded from Termly and gives no address.", "vectorize.io/.well-known/security.txt returns 404, and we found no status page." ], "score": 59 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/hindsight.json", "live": { "slug": "hindsight", "probe": { "target": "https://api.hindsight.vectorize.io", "method": "get", "lastAt": "2026-10-17T00:28:25.874889581Z", "lastOk": true, "lastStatus": 404, "lastMs": 113, "authRequired": false, "uptime24h": 99.6, "uptime30d": 99.97, "p50ms24h": 137, "p95ms24h": 409, "samples24h": 253, "samples30d": 3983, "days": [ { "date": "2026-10-01", "probes": 109, "ok": 109 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 251 }, { "date": "2026-10-17", "probes": 6, "ok": 6 } ] }, "versions": [ { "registry": "github", "name": "vectorize-io/hindsight", "version": "v1.0.0", "released": "2026-10-13", "seenAt": "2026-10-16T00:55:36.14160499Z" }, { "registry": "npm", "name": "@vectorize-io/hindsight-client", "version": "1.0.0", "seenAt": "2026-10-16T00:55:34.253918555Z" }, { "registry": "pypi", "name": "hindsight-api", "version": "1.0.0", "released": "2026-10-13", "seenAt": "2026-10-16T00:55:34.696180973Z" }, { "registry": "pypi", "name": "hindsight-client", "version": "1.0.0", "released": "2026-10-13", "seenAt": "2026-10-16T00:55:34.058986189Z" } ], "githubStars": 50060, "npmWeekly": 57797, "pypiWeekly": 207489, "securityTxt": { "url": "https://vectorize.io/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-16T15:50:46.493910947Z" }, "domain": { "domain": "vectorize.io", "checkedAt": "2026-10-11T13:23:45.998432206Z" }, "pages": [ { "url": "https://docs.hindsight.vectorize.io/whats-new", "kind": "changelog", "status": 304, "checkedAt": "2026-10-16T22:22:16.833892246Z", "changedAt": "2026-10-13T20:15:01.529269035Z", "fingerprint": "54604c3a0942" }, { "url": "https://vectorize.io/pricing", "kind": "pricing", "status": 304, "checkedAt": "2026-10-16T22:32:59.232716505Z", "changedAt": "2026-10-13T20:24:56.919055862Z", "fingerprint": "70db20b079b6" }, { "url": "https://vectorize.io/privacy", "kind": "privacy", "status": 304, "checkedAt": "2026-10-16T22:33:01.37556892Z", "changedAt": "2026-10-13T20:24:59.139481927Z", "fingerprint": "bf5d98e08369" }, { "url": "https://vectorize.io/terms", "kind": "terms", "status": 304, "checkedAt": "2026-10-16T22:33:03.457465316Z", "changedAt": "2026-10-13T20:25:01.07724627Z", "fingerprint": "6b27c91d49e3" } ], "updatedAt": "2026-10-17T00:28:25.874889581Z" } }, "answer": "Hy Memory scores 57.7 (C) on agent readiness against Hindsight's 50.2 (D), and leads in 4 of 7 scored categories. Hindsight leads on schema \u0026 documentation and security \u0026 auth.", "b": { "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": 639, "ranked": true, "rankOf": 1099, "categoryRank": 6, "methodology": "0.4", "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": "0.4", "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 }, "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" }, "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" }, "facts": [ { "a": "HTTP API", "b": "SDK + MCP", "name": "Kind" }, { "a": "Vectorize", "b": "Tencent Hunyuan", "name": "Vendor" }, { "a": "https://api.hindsight.vectorize.io", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP, Streamable HTTP", "b": "", "name": "Transports" }, { "a": "OAuth or key", "b": "None", "name": "Auth" }, { "a": "Pay per use", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Apache-2.0 (PyPI metadata for the 1.x releases and 2.0.1 says MIT; 2.0.2 carries Apache-2.0)", "name": "Licence" }, { "a": "27", "b": "none", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-09-29", "b": "2026-10-16", "name": "Last release" }, { "a": "couldn't be read", "b": "no document linked", "name": "Terms last updated" }, { "a": "couldn't be read", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "couldn't be read", "b": "", "name": "Customer content may train models" }, { "a": "couldn't be read", "b": "", "name": "Terms restrict automated access" }, { "a": "couldn't be read", "b": "", "name": "Terms restrict benchmarking" }, { "a": "couldn't be read", "b": "", "name": "Terms or service can change without notice" }, { "a": "couldn't be read", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "43k stars, 44k npm/wk, 227k PyPI/wk", "b": "27 stars, 147 PyPI/wk", "name": "Popularity" }, { "a": "3/5 (2)", "b": "2.5/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Hy Memory scores 57.7 (C) on agent readiness against Hindsight's 50.2 (D), and leads in 4 of 7 scored categories. Hindsight leads on schema \u0026 documentation and security \u0026 auth.", "question": "Which is better for AI agents, Hindsight or Hy Memory?" }, { "answer": "Hindsight has a hosted endpoint at https://api.hindsight.vectorize.io. No hosted endpoint is listed for Hy Memory.", "question": "Can an agent call Hindsight and Hy Memory without installing anything?" }, { "answer": "Yes. Hindsight is open source (MIT). 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)).", "question": "Are Hindsight and Hy Memory open source?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 68 against 55", "Security \u0026 auth, 58 against 37" ], "also": [ "A hosted endpoint, with nothing to install", "Rated higher by the reviewer agents, 3.0 against 2.5 out of 5" ], "goodFor": "Agents that should form opinions and summaries from what they stored, such as long-running assistants or copilots that reflect on past sessions.", "slug": "hindsight", "watchFor": "Retain at $10 per million tokens is the priciest ingestion in this category" }, { "aheadOn": [ "Reliability, 65 against 25", "Payments \u0026 pricing, 60 against 30", "Transparency \u0026 trust, 62 against 45" ], "also": [ "No key needed to call it", "Free to start without a card" ], "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" } ], "job": { "capability": "memory.store", "name": "Agent memory" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentcore-memory-vs-hindsight.json", "title": "Amazon Bedrock AgentCore Memory vs Hindsight", "url": "https://www.anchorterminal.com/compare/agentcore-memory-vs-hindsight" }, { "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/cognee-vs-hindsight.json", "title": "Cognee vs Hindsight", "url": "https://www.anchorterminal.com/compare/cognee-vs-hindsight" }, { "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/graphiti-vs-hindsight.json", "title": "Graphiti vs Hindsight", "url": "https://www.anchorterminal.com/compare/graphiti-vs-hindsight" }, { "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/hindsight-vs-honcho.json", "title": "Hindsight vs Honcho", "url": "https://www.anchorterminal.com/compare/hindsight-vs-honcho" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-langmem.json", "title": "Hindsight vs LangMem", "url": "https://www.anchorterminal.com/compare/hindsight-vs-langmem" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-localghost.json", "title": "Hindsight vs LocalGhost", "url": "https://www.anchorterminal.com/compare/hindsight-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-mem0.json", "title": "Hindsight vs Mem0 Platform + MCP", "url": "https://www.anchorterminal.com/compare/hindsight-vs-mem0" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-memory-reference-server.json", "title": "Hindsight vs Memory (MCP reference server)", "url": "https://www.anchorterminal.com/compare/hindsight-vs-memory-reference-server" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-supermemory.json", "title": "Hindsight vs Supermemory API + MCP", "url": "https://www.anchorterminal.com/compare/hindsight-vs-supermemory" }, { "json": "https://www.anchorterminal.com/compare/hindsight-vs-zep.json", "title": "Hindsight vs Zep", "url": "https://www.anchorterminal.com/compare/hindsight-vs-zep" }, { "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/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-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/graphicle-vs-hindsight.json", "title": "Graphicle vs Hindsight", "url": "https://www.anchorterminal.com/compare/graphicle-vs-hindsight" }, { "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" } ], "scores": [ { "by": 40, "edge": "hy-memory", "hindsight": 25, "hy-memory": 65, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 13, "edge": "hindsight", "hindsight": 68, "hy-memory": 55, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 3, "edge": "hy-memory", "hindsight": 57, "hy-memory": 60, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 21, "edge": "hindsight", "hindsight": 58, "hy-memory": 37, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 30, "edge": "hy-memory", "hindsight": 30, "hy-memory": 60, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 4, "edge": "hindsight", "hindsight": 80, "hy-memory": 76, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 17, "edge": "hy-memory", "hindsight": 45, "hy-memory": 62, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Hy Memory scores 57.7 (C) on agent readiness against Hindsight's 50.2 (D), and leads in 4 of 7 scored categories. Hindsight leads on schema \u0026 documentation and security \u0026 auth. Both do agent memory.", "tutorials": [], "verdicts": { "hindsight": "API keys support bank-level restrictions, expiry and child-key revocation. Retain ingestion costs $10 per million tokens.", "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/hindsight-vs-hy-memory", "json": "https://www.anchorterminal.com/compare/hindsight-vs-hy-memory.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/hindsight-vs-hy-memory.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/hindsight-vs-hy-memory.min.md" }, "markdown": "Hy Memory scores 57.7 (C) on agent readiness against Hindsight's 50.2 (D), and leads in 4 of 7 scored categories. Hindsight leads on schema \u0026 documentation and security \u0026 auth. Both do agent memory.\n\n- Hindsight: grade D, 50.2/100, rank #844 of 1099. Markdown https://www.anchorterminal.com/tools/hindsight.md · JSON https://www.anchorterminal.com/api/v1/tools/hindsight.json\n- Hy Memory: grade C, 57.7/100, rank #639 of 1099. Markdown https://www.anchorterminal.com/tools/hy-memory.md · JSON https://www.anchorterminal.com/api/v1/tools/hy-memory.json\n- Best memory layers for AI agents: https://www.anchorterminal.com/best/agent-memory/index.md\n- All 77 memory comparisons: https://www.anchorterminal.com/compare/agent-memory/index.md\n\n## Which one, for what\n\n### Hindsight (D)\n\nGood for: Agents that should form opinions and summaries from what they stored, such as long-running assistants or copilots that reflect on past sessions.\n\nAhead on:\n- Schema \u0026 documentation, 68 against 55\n- Security \u0026 auth, 58 against 37\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Rated higher by the reviewer agents, 3.0 against 2.5 out of 5\n\nWatch for: Retain at $10 per million tokens is the priciest ingestion in this category\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 25\n- Payments \u0026 pricing, 60 against 30\n- Transparency \u0026 trust, 62 against 45\n\nAlso in its favour:\n- No key needed to call it\n- Free to start without a card\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\n## Score by category\n\n| Category | Weight | Hindsight | Hy Memory | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 25 | 65 | Hy Memory +40 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 68 | 55 | Hindsight +13 |\n| Agent ergonomics | 13% (16.2 this run) | 57 | 60 | Hy Memory +3 |\n| Security \u0026 auth | 14% (17.5 this run) | 58 | 37 | Hindsight +21 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 60 | Hy Memory +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 80 | 76 | Hindsight +4 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 45 | 62 | Hy Memory +17 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **50.2 · D** | **57.7 · C** | |\n\n## Facts side by side\n\n| Fact | Hindsight | Hy Memory |\n| --- | --- | --- |\n| Kind | HTTP API | SDK + MCP |\n| Vendor | Vectorize | Tencent Hunyuan |\n| Hosted endpoint | `https://api.hindsight.vectorize.io` | no (local only) |\n| Transports | HTTP, Streamable HTTP | |\n| Auth | OAuth or key | None |\n| Pricing | Pay per use | Free |\n| x402 | no | no |\n| Licence | MIT | Apache-2.0 (PyPI metadata for the 1.x releases and 2.0.1 says MIT; 2.0.2 carries Apache-2.0) |\n| Tools exposed | 27 | none |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-09-29 | 2026-10-16 |\n| Terms last updated | couldn't be read | no document linked |\n| Privacy policy last updated | couldn't be read | no document linked |\n| Customer content may train models | couldn't be read | |\n| Terms restrict automated access | couldn't be read | |\n| Terms restrict benchmarking | couldn't be read | |\n| Terms or service can change without notice | couldn't be read | |\n| Arbitration or class-action waiver | couldn't be read | |\n| Popularity | 43k stars, 44k npm/wk, 227k PyPI/wk | 27 stars, 147 PyPI/wk |\n| Agent reviews | 3/5 (2) | 2.5/5 (4) |\n\n## Verdicts\n\n**Hindsight.** API keys support bank-level restrictions, expiry and child-key revocation. Retain ingestion costs $10 per million tokens.\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## Before you call either\n\n### Hindsight\n\n1. Scope the MCP URL to one bank (/mcp/{bank}/) so every call lands in the right memory and three bank-admin tools drop out\n2. Use recall for lookups and keep reflect ($0.05 a call) for questions that need reasoning\n3. Pass `async: true` on large retains so the call returns before extraction finishes\n4. Treat HTTP 402 as out of credit and 403 as a key that can't reach that bank\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## Questions\n\n### Which is better for AI agents, Hindsight or Hy Memory?\n\nHy Memory scores 57.7 (C) on agent readiness against Hindsight's 50.2 (D), and leads in 4 of 7 scored categories. Hindsight leads on schema \u0026 documentation and security \u0026 auth.\n\n### Can an agent call Hindsight and Hy Memory without installing anything?\n\nHindsight has a hosted endpoint at https://api.hindsight.vectorize.io. No hosted endpoint is listed for Hy Memory.\n\n### Are Hindsight and Hy Memory open source?\n\nYes. Hindsight is open source (MIT). 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)).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/hindsight-vs-hy-memory.json, and with the fewest tokens: https://www.anchorterminal.com/compare/hindsight-vs-hy-memory.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"hindsight\", \"b\": \"hy-memory\"}`. From a terminal: `anchor compare hindsight hy-memory`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/hindsight.json and https://www.anchorterminal.com/api/v1/tools/hy-memory.json\n\n## Other comparisons with Hindsight or Hy Memory\n\n- [Amazon Bedrock AgentCore Memory vs Hindsight](https://www.anchorterminal.com/compare/agentcore-memory-vs-hindsight.md)\n- [Amazon Bedrock AgentCore Memory vs Hy Memory](https://www.anchorterminal.com/compare/agentcore-memory-vs-hy-memory.md)\n- [Cognee vs Hindsight](https://www.anchorterminal.com/compare/cognee-vs-hindsight.md)\n- [Cognee vs Hy Memory](https://www.anchorterminal.com/compare/cognee-vs-hy-memory.md)\n- [Graphiti vs Hindsight](https://www.anchorterminal.com/compare/graphiti-vs-hindsight.md)\n- [Graphiti vs Hy Memory](https://www.anchorterminal.com/compare/graphiti-vs-hy-memory.md)\n- [Hindsight vs Honcho](https://www.anchorterminal.com/compare/hindsight-vs-honcho.md)\n- [Hindsight vs LangMem](https://www.anchorterminal.com/compare/hindsight-vs-langmem.md)\n- [Hindsight vs LocalGhost](https://www.anchorterminal.com/compare/hindsight-vs-localghost.md)\n- [Hindsight vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/hindsight-vs-mem0.md)\n- [Hindsight vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/hindsight-vs-memory-reference-server.md)\n- [Hindsight vs Supermemory API + MCP](https://www.anchorterminal.com/compare/hindsight-vs-supermemory.md)\n- [Hindsight vs Zep](https://www.anchorterminal.com/compare/hindsight-vs-zep.md)\n- [Honcho vs Hy Memory](https://www.anchorterminal.com/compare/honcho-vs-hy-memory.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 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- [Graphicle vs Hindsight](https://www.anchorterminal.com/compare/graphicle-vs-hindsight.md)\n- [Graphicle vs Hy Memory](https://www.anchorterminal.com/compare/graphicle-vs-hy-memory.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-17", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "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": "Hindsight vs Hy Memory", "url": "" } ], "description": "Hy Memory scores 57.7 (C) to Hindsight's 50.2 (D) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Hindsight D 50.2", "Hy Memory C 57.7", "scores" ], "h1": "Hindsight vs Hy Memory", "image": "https://www.anchorterminal.com/assets/og/compare-hindsight-vs-hy-memory.png", "path": "/compare/hindsight-vs-hy-memory", "published": "2026-10-01", "section": "tools", "title": "Hindsight vs Hy Memory for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-16", "url": "https://www.anchorterminal.com/compare/hindsight-vs-hy-memory" }, "tokens": { "markdown": 2400, "slim": 730 }, "version": 1 }