Gives Claude a persistent knowledge graph it can write to and read from across sessions. Instead of starting from scratch every conversation, your agent loads context automatically through three main operations: agent_context() for session bootstrapping, remember() for storing facts as subject-predicate-object triples, and recall() for querying entities and relationships. You describe things in natural language and the server structures them into typed relationships like "decided", "works_at", "competes_with". Useful when you're tired of re-explaining your project setup, team structure, or architectural decisions every time you open a new chat. The knowledge graph lives at dejaview.io and works through their REST API with bearer token auth.
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent