caura MCP server

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.

What caura does

Summarised from the project README; check the repository for the latest details.

Features

• Tenant isolation — row-level database separation per tenant; PII auto-detected and flagged on every write (surfaced in memory metadata as `containspii`/`piitypes`)
• Visibility scopes — every memory is stamped at write time: `scopeagent` (private), `scopeteam` (fleet-wide, default), or `scopeorg` (cross-fleet). Cross-fleet recall is permissioned, not open
• Full audit log — every write, delete, and transition logged with tenant and scope context
• Contradiction detection — RDF triple comparison + LLM semantic analysis detects conflicting memories and automatically supersedes them, with full contradiction chain tracking
• Outcome-based learning (Karpathy Loop) — agents report success/failure after acting on recalled memories; the system reinforces what works and auto-generates preventive `rule`-type memories on failure
• Crystallization — LLM merges near-duplicate memories into canonical atomic facts with full provenance; 8-status lifecycle automation retires stale data

How to install caura

Listed on Socketlist – add this badge to your README:

Badge markdown[](https://socketlist.pages.dev/s/caura-ai-caura/)

Maintain this project? Get it featured for free during launch →

Compare with ruflo →

Related Memory & Knowledge MCP servers