skynetcmd/m3-memory helps turn isolated prompts and tools into repeatable agent workflows

说明与用途

skynetcmd/m3‑memory 是一个本地优先的 AI Agent 记忆框架，能够将零散的提示和工具转化为可重复的工作流，支持混合检索（FTS5+向量+MMR）并实现 99.2% 的 LongMemEval‑S 检索准确率。它通过 API/SDK/CLI 与 Claude、LangChain、Gemini 等主流模型和工具无缝集成，既可完全离线运行（符合 GDPR、FIPS 140‑3），也可按需接入云端。凭借最近的活跃更新、较高的星标数和生态信号，该项目在 OSS 候选中具有较高的生产可用性，适合进行严肃的试点部署。

问题

skynetcmd/m3-memory helps turn isolated prompts and tools into repeatable agent workflows.

结果

High for an OSS candidate: recent activity, adoption, and ecosystem signals are strong enough for a serious pilot.

工作流

• coordinate multi-agent workflows
• add tool-use pipelines
• standardize agent memory

证据

Local-first Memory Framework for AI Agents · 99.2% LongMemEval-S retrieval @ k=10 · Supports Claude · Antigravity · LangChain · Hermes · Gemini · OpenCode · OpenClaw · MCP-native and plugins · Hybrid search (FTS5 + vector + MMR) · GDPR · FIPS 140-3 ready · 100% local (fully offline) or cloud capable

来源