GitHub 仓库

caura-ai/caura-memclaw

Python 首次收录 2026-04-27 更新于 2026-07-16 查看源 ↗

GitHub 仓库 中按Star排名第 771 / 共 783

323 Star

Governed shared memory for AI agent fleets — multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

项目介绍

Fleet memory for AI agents — governed, shared, self-improving.

Quick Start · Features · Performance · MCP · API Reference · Plugin Docs · Contributing · Discord

MemClaw is open-source memory for multi-tenant, multi-agent AI fleets. Your agents store what they learn, find what the fleet knows, and get smarter with every interaction — learning from each other instead of repeating mistakes.

Agents write plain text. MemClaw turns it into searchable, governed, self-improving memory.

One loop, three pillars: write, recall, compound — every interaction makes the next one smarter.

Built for fleets, not single agents. Public agent-memory…

摘自 github.com/caura-ai/caura-memclaw

最新指标

Star 323 2026-07-16
Fork 42 2026-07-16
提交 439 2026-07-16
发布 36 2026-07-16
Watcher 2 2026-07-16
开放 issue 13 2026-07-16
开放 PR 40 2026-07-16