{"id":48969110,"url":"https://github.com/mempalace/mempalace","last_synced_at":"2026-04-24T22:01:05.822Z","repository":{"id":349643754,"uuid":"1201656210","full_name":"MemPalace/mempalace","owner":"MemPalace","description":"The best-benchmarked open-source AI memory system. And it's free.","archived":false,"fork":false,"pushed_at":"2026-04-21T04:47:58.000Z","size":15832,"stargazers_count":48552,"open_issues_count":421,"forks_count":6358,"subscribers_count":294,"default_branch":"develop","last_synced_at":"2026-04-21T06:42:01.123Z","etag":null,"topics":["ai","chromadb","llm","mcp","memory","python"],"latest_commit_sha":null,"homepage":"http://mempalaceofficial.com/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/MemPalace.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":"ROADMAP.md","authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-04-05T01:12:07.000Z","updated_at":"2026-04-21T06:40:43.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/MemPalace/mempalace","commit_stats":null,"previous_names":["milla-jovovich/mempalace","mempalace/mempalace"],"tags_count":6,"template":false,"template_full_name":null,"purl":"pkg:github/MemPalace/mempalace","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MemPalace%2Fmempalace","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MemPalace%2Fmempalace/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MemPalace%2Fmempalace/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MemPalace%2Fmempalace/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MemPalace","download_url":"https://codeload.github.com/MemPalace/mempalace/tar.gz/refs/heads/develop","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MemPalace%2Fmempalace/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32242315,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-24T13:21:15.438Z","status":"ssl_error","status_checked_at":"2026-04-24T13:21:15.005Z","response_time":64,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","chromadb","llm","mcp","memory","python"],"created_at":"2026-04-18T06:08:44.318Z","updated_at":"2026-04-24T22:01:05.816Z","avatar_url":"https://github.com/MemPalace.png","language":"Python","readme":"\u003e [!CAUTION]\n\u003e **Scam alert.** The only official sources for MemPalace are this\n\u003e [GitHub repository](https://github.com/MemPalace/mempalace), the\n\u003e [PyPI package](https://pypi.org/project/mempalace/), and the docs site at\n\u003e **[mempalaceofficial.com](https://mempalaceofficial.com)**. Any other\n\u003e domain — including `mempalace.tech` — is an impostor and may distribute\n\u003e malware. Details and timeline: [docs/HISTORY.md](docs/HISTORY.md).\n\n\u003cdiv align=\"center\"\u003e\n\n\u003cimg src=\"assets/mempalace_logo.png\" alt=\"MemPalace\" width=\"240\"\u003e\n\n# MemPalace\n\nLocal-first AI memory. Verbatim storage, pluggable backend, 96.6% R@5 raw on LongMemEval — zero API calls.\n\n[![][version-shield]][release-link]\n[![][python-shield]][python-link]\n[![][license-shield]][license-link]\n[![][discord-shield]][discord-link]\n\n\u003c/div\u003e\n\n---\n\n## What it is\n\nMemPalace stores your conversation history as verbatim text and retrieves\nit with semantic search. It does not summarize, extract, or paraphrase.\nThe index is structured — people and projects become *wings*, topics\nbecome *rooms*, and original content lives in *drawers* — so searches\ncan be scoped rather than run against a flat corpus.\n\nThe retrieval layer is pluggable. The current default is ChromaDB; the\ninterface is defined in [`mempalace/backends/base.py`](mempalace/backends/base.py)\nand alternative backends can be dropped in without touching the rest of\nthe system.\n\nNothing leaves your machine unless you opt in.\n\nArchitecture, concepts, and mining flows:\n[mempalaceofficial.com/concepts/the-palace](https://mempalaceofficial.com/concepts/the-palace.html).\n\n---\n\n## Install\n\n```bash\npip install mempalace\nmempalace init ~/projects/myapp\n```\n\n## Quickstart\n\n```bash\n# Mine content into the palace\nmempalace mine ~/projects/myapp                    # project files\nmempalace mine ~/.claude/projects/ --mode convos   # Claude Code sessions (scope with --wing per project)\n\n# Search\nmempalace search \"why did we switch to GraphQL\"\n\n# Load context for a new session\nmempalace wake-up\n```\n\nFor Claude Code, Gemini CLI, MCP-compatible tools, and local models, see\n[mempalaceofficial.com/guide/getting-started](https://mempalaceofficial.com/guide/getting-started.html).\n\n---\n\n## Benchmarks\n\nAll numbers below are reproducible from this repository with the commands\nin [`benchmarks/BENCHMARKS.md`](benchmarks/BENCHMARKS.md). Full\nper-question result files are committed under `benchmarks/results_*`.\n\n**LongMemEval — retrieval recall (R@5, 500 questions):**\n\n| Mode | R@5 | LLM required |\n|---|---|---|\n| Raw (semantic search, no heuristics, no LLM) | **96.6%** | None |\n| Hybrid v4, held-out 450q (tuned on 50 dev, not seen during training) | **98.4%** | None |\n| Hybrid v4 + LLM rerank (full 500) | ≥99% | Any capable model |\n\nThe raw 96.6% requires no API key, no cloud, and no LLM at any stage. The\nhybrid pipeline adds keyword boosting, temporal-proximity boosting, and\npreference-pattern extraction; the held-out 98.4% is the honest\ngeneralisable figure.\n\nThe rerank pipeline promotes the best candidate out of the top-20\nretrieved sessions using an LLM reader. It works with any reasonably\ncapable model — we have reproduced it with Claude Haiku, Claude Sonnet,\nand minimax-m2.7 via Ollama Cloud (no Anthropic dependency). The gap\nbetween raw and reranked is model-agnostic; we do not headline a \"100%\"\nnumber because the last 0.6% was reached by inspecting specific wrong\nanswers, which `benchmarks/BENCHMARKS.md` flags as teaching to the test.\n\n**Other benchmarks (full results in [`benchmarks/BENCHMARKS.md`](benchmarks/BENCHMARKS.md)):**\n\n| Benchmark | Metric | Score | Notes |\n|---|---|---|---|\n| LoCoMo (session, top-10, no rerank) | R@10 | 60.3% | 1,986 questions |\n| LoCoMo (hybrid v5, top-10, no rerank) | R@10 | 88.9% | Same set |\n| ConvoMem (all categories, 250 items) | Avg recall | 92.9% | 50 per category |\n| MemBench (ACL 2025, 8,500 items) | R@5 | 80.3% | All categories |\n\nWe deliberately do not include a side-by-side comparison against Mem0,\nMastra, Hindsight, Supermemory, or Zep. Those projects publish different\nmetrics on different splits, and placing retrieval recall next to\nend-to-end QA accuracy is not an honest comparison. See each project's\nown research page for their published numbers.\n\n**Reproducing every result:**\n\n```bash\ngit clone https://github.com/MemPalace/mempalace.git\ncd mempalace\npip install -e \".[dev]\"\n# see benchmarks/README.md for dataset download commands\npython benchmarks/longmemeval_bench.py /path/to/longmemeval_s_cleaned.json\n```\n\n---\n\n## Knowledge graph\n\nMemPalace includes a temporal entity-relationship graph with validity\nwindows — add, query, invalidate, timeline — backed by local SQLite.\nUsage and tool reference:\n[mempalaceofficial.com/concepts/knowledge-graph](https://mempalaceofficial.com/concepts/knowledge-graph.html).\n\n## MCP server\n\n29 MCP tools cover palace reads/writes, knowledge-graph operations,\ncross-wing navigation, drawer management, and agent diaries. Installation\nand the full tool list:\n[mempalaceofficial.com/reference/mcp-tools](https://mempalaceofficial.com/reference/mcp-tools.html).\n\n## Agents\n\nEach specialist agent gets its own wing and diary in the palace.\nDiscoverable at runtime via `mempalace_list_agents` — no bloat in your\nsystem prompt:\n[mempalaceofficial.com/concepts/agents](https://mempalaceofficial.com/concepts/agents.html).\n\n## Auto-save hooks\n\nTwo Claude Code hooks save periodically and before context compression:\n[mempalaceofficial.com/guide/hooks](https://mempalaceofficial.com/guide/hooks.html).\n\n---\n\n## Requirements\n\n- Python 3.9+\n- A vector-store backend (ChromaDB by default)\n- ~300 MB disk for the default embedding model\n\nNo API key is required for the core benchmark path.\n\n## Docs\n\n- Getting started → [mempalaceofficial.com/guide/getting-started](https://mempalaceofficial.com/guide/getting-started.html)\n- CLI reference → [mempalaceofficial.com/reference/cli](https://mempalaceofficial.com/reference/cli.html)\n- Python API → [mempalaceofficial.com/reference/python-api](https://mempalaceofficial.com/reference/python-api.html)\n- Full benchmark methodology → [benchmarks/BENCHMARKS.md](benchmarks/BENCHMARKS.md)\n- Release notes → [CHANGELOG.md](CHANGELOG.md)\n- Corrections and public notices → [docs/HISTORY.md](docs/HISTORY.md)\n\n## Contributing\n\nPRs welcome. See [CONTRIBUTING.md](CONTRIBUTING.md).\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n\n\u003c!-- Link Definitions --\u003e\n[version-shield]: https://img.shields.io/badge/version-3.3.0-4dc9f6?style=flat-square\u0026labelColor=0a0e14\n[release-link]: https://github.com/MemPalace/mempalace/releases\n[python-shield]: https://img.shields.io/badge/python-3.9+-7dd8f8?style=flat-square\u0026labelColor=0a0e14\u0026logo=python\u0026logoColor=7dd8f8\n[python-link]: https://www.python.org/\n[license-shield]: https://img.shields.io/badge/license-MIT-b0e8ff?style=flat-square\u0026labelColor=0a0e14\n[license-link]: https://github.com/MemPalace/mempalace/blob/main/LICENSE\n[discord-shield]: https://img.shields.io/badge/discord-join-5865F2?style=flat-square\u0026labelColor=0a0e14\u0026logo=discord\u0026logoColor=5865F2\n[discord-link]: https://discord.com/invite/ycTQQCu6kn\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmempalace%2Fmempalace","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmempalace%2Fmempalace","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmempalace%2Fmempalace/lists"}