{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_y9ccdxu387p9","handle":"rekall-mcp","url":"https://wellknown.network/agents/rekall-mcp","links":{"self":"https://wellknown.network/agents/rekall-mcp/record.json","html":"https://wellknown.network/agents/rekall-mcp","markdown":"https://wellknown.network/agents/rekall-mcp/record.md","api":"https://wellknown.network/api/v1/agents/rekall-mcp","status":"https://wellknown.network/api/v1/agents/rekall-mcp/status","claim":"https://wellknown.network/agents/rekall-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/rekall-mcp/claim.json","badge":"https://wellknown.network/agents/rekall-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:rekall-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"rekall-mcp","summary":"Persistent memory for AI assistants via MCP","description":"# Rekall MCP\n\n**Give coding agents memory with associative recall.** Rekall works with Claude Code and Codex while keeping each harness’s native memory separate.\n\nRekall MCP is a persistent memory system with a **knowledge graph** layer. It stores memories as YAML + vector embeddings, connects them with typed relationships, and retrieves context using graph-enhanced semantic search.\n\n![A real Claude Code session with Rekall: memory recall answers an incident question, then a destructive terraform command gets refused by quoting a danger-zone memory (recorded live, synthetic demo memories)](docs/demo/rekall-cc-real.gif)\n\n![Rekall cockpit — aggregates dashboard with live recall feed and neural graph](docs/screenshots/cockpit.png)\n\n---\n\n## Local-First Agent Nervous System\n\nRekall gives local agents durable, inspectable, cross-session and cross-project memory for software work. Harness memory stores assistant preferences; Rekall stores what the work has taught the agent: decisions, root causes, procedures, danger zones, and project familiarity with provenance.\n\n---\n\n## Install\n\n### Try it — no Docker, one command\n\n```bash\nclaude mcp add rekall -- uvx rekall-mcp\n```\n\nThat's the trial tier: stdio transport, embedded vector store at `~/.rekall/qdrant`, memories as YAML at `~/.claude/memory`. First run downloads the ~90 MB embedding model (progress on stderr). No hooks/auto-capture, single session at a time — upgrade below when it earns a daily slot.\n\n### Daily driver — all-in-one Docker\n\n```bash\ndocker run -d -v rekall-data:/data -p 127.0.0.1:8000:8000 ghcr.io/jfr992/rekall-mcp\nclaude mcp add --transport http rekall http://localhost:8000\n```\n\nOne container, embedding model baked in, data on a named volume. Verify with `curl http://localhost:8000/health`.\n\n### Full stack — compose (adds the cockpit UI)\n\n```bash\ngit clone https://github.com/jfr992/rekall-mcp.git\ncd rekall-mcp\ndocker compose up -d    # Qdrant (:6333) + MCP backend (:8000) + cockpit (:3333)\nclaude mcp add --t…","publisher":{"name":"jfr992","url":null},"homepage":null,"repository":null,"version":"1.15.0","license":"Apache-2.0","protocols":["mcp"],"tags":["ai","claude","context","llm","mcp","memory"],"pricing":null,"endpoints":[{"url":"pypi:rekall-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"derived"},{"slug":"knowledge.memory","name":"Agent Memory","confidence":1,"provenance":"declared"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":0.836,"provenance":"derived"},{"slug":"infra.cloud","name":"Cloud Platforms","confidence":0.814,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["data","dev","infra","knowledge"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"rekall-mcp","registry":"pypi","observedAt":"2026-09-10T11:28:21.881Z","publishedAt":"2026-08-24T21:21:28.812269Z","latestVersion":"1.15.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"rekall-mcp","url":"https://pypi.org/project/rekall-mcp/","firstSeenAt":"2026-09-10T11:26:38.638Z","fetchedAt":"2026-09-10T11:26:38.638Z","normalizedAt":"2026-09-10T11:26:38.638Z"}]},"firstSeenAt":"2026-09-10T11:26:38.638Z","updatedAt":"2026-09-10T11:28:21.881Z"}