genome
Auditable memory layer for AI agents: zero-LLM-call local ingest (~10ms/msg, air-gapped), matches Mem0 on accuracy at ~1000x lower ingest cost, bi-temporal belief-state, MCP server. Honest LoCoMo/LongMemEval benchmarks. Open source (Apache-2.0).
面向 AI 智能体的可审计记忆层：零 LLM 调用的本地摄取（约 10ms/条消息，气隙部署），准确率与 Mem0 相当而摄取成本低约 1000 倍，双时态信念状态，MCP 服务器。诚实的 LoCoMo/LongMemEval 基准测试。开源（Apache-2.0）。
How to install
No unified install command; see the repository README.
Recommendation signals
Meta
- License
- Apache-2.0
- Language
- Python
- GitHub stars
- 6
- mo. downloads
- –
- Last push
- 2026-09-04
- Created
- 2026-07-14
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:punkpeye/awesome-mcp-servers
- Topics
- agent-memory, ai-agents, ai-memory, benchmarks, llm, local-first, locomo, longmemeval, mcp, mcp-server, mem0-alternative, model-context-protocol, python, rag, retrieval
Related plugins
get-shit-done
gsd-build/get-shit-done
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
markdownify-mcp
zcaceres/markdownify-mcp
A Model Context Protocol server for converting almost anything to Markdown
hindsight
vectorize-io/hindsight/tree/main/hindsight-integrations/coding-agents
Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.
airtable-mcp-server
domdomegg/airtable-mcp-server
🗂️🤖 Airtable Model Context Protocol Server, for allowing AI systems to interact with your Airtable bases