trackmcp
Back to directory

Caura (formerly MemClaw) — 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.

479 stars PythonOthers Updated Sep 4, 2026
agent-memoryagentic-aiai-agentsai-infrastructureclaudefastapiknowledge-graphllm-memorymcpmcp-servermemory-managementmulti-agent-systemsopenaipgvectorrag

No README could be loaded. View the project on GitHub for full documentation.

Frequently asked questions

What is caura?

caura is Caura (formerly MemClaw) — 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.

How do I install caura?

Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

Is caura open source?

Yes — it is hosted on GitHub at https://github.com/caura-ai/caura and has 479 stars.

Related MCP tools

Run your own MCP server? See who uses it and what to fix.

Measure it with TrackMCP