{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_f3y6khhv8yd5","handle":"lithos-mcp","url":"https://wellknown.network/agents/lithos-mcp","links":{"self":"https://wellknown.network/agents/lithos-mcp/record.json","html":"https://wellknown.network/agents/lithos-mcp","markdown":"https://wellknown.network/agents/lithos-mcp/record.md","api":"https://wellknown.network/api/v1/agents/lithos-mcp","status":"https://wellknown.network/api/v1/agents/lithos-mcp/status","claim":"https://wellknown.network/agents/lithos-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/lithos-mcp/claim.json","badge":"https://wellknown.network/agents/lithos-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/lithos-mcp/history","tools":"https://wellknown.network/api/v1/agents/lithos-mcp/tools"},"ard":{"identifier":"urn:air::server:lithos-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"lithos-mcp","summary":"Shared cognitive substrate for AI agents (local-first, Markdown-native, MCP)","description":"# Lithos\n\n**Shared memory for AI agents.**\n\nA local, privacy-first knowledge base that enables heterogeneous AI agents to share knowledge and coordinate work.\n\n## The Problem\n\nWhen agents cannot share what they know, every agent starts from zero. Work is duplicated, discoveries are lost, and coordination breaks down. Lithos solves this by providing a **persistent, shared knowledge layer** that compounds in value over time.\n\n## What It Is\n\nLithos is an MCP server that provides a shared knowledge store for AI agents running on your local infrastructure. Knowledge is stored as human-readable Markdown files (compatible with Obsidian) while providing fast full-text and semantic search for agents.\n\n## Who It's For\n\nLithos is the **Knowledge Layer** for teams running AI agents in production.\n\nJust as Alation coined the term \"Knowledge Layer\" for enterprise data governance, Lithos provides the equivalent for AI agent systems: a structured, searchable, shared memory that **compounds in value** the more it is used. Each agent interaction enriches the knowledge base, making every subsequent agent smarter and faster.\n\n- Teams running multiple AI agents (Agent Zero, OpenClaw, Claude Code, custom agents)\n- Developers who want agents to share discoveries and avoid duplicate work\n- Anyone who needs agent knowledge to be inspectable and version-controlled\n\n## Key Features\n\n- **📁 Markdown-first**: All knowledge stored as Obsidian-compatible `.md` files\n- **🔍 Fast search**: Tantivy full-text + ChromaDB semantic search\n- **🕸️ Knowledge graph**: NetworkX-powered relationships via `[[wiki-links]]`\n- **🤝 Multi-agent coordination**: Task claiming, findings sharing, status tracking\n- **🧠 Research cache**: One-call freshness check so agents skip redundant research — returns hit/miss/stale with update guidance\n- **🔗 URL deduplication**: Automatic detection and prevention of duplicate notes from the same source URL\n- **🧬 Provenance tracking**: Declare which notes a synthesis is derived…","publisher":{"name":"Dave Snowdon","url":null},"homepage":null,"repository":null,"version":"0.6.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:lithos-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"productivity.notes","name":"Notes & Docs","confidence":1,"provenance":"derived"},{"slug":"automation.orchestration","name":"Agent Orchestration","confidence":0.905,"provenance":"derived"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":0.836,"provenance":"derived"}],"categories":["automation","knowledge","productivity"],"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":"lithos-mcp","registry":"pypi","observedAt":"2026-10-28T09:22:53.411Z","publishedAt":"2026-10-04T18:16:19.223521Z","latestVersion":"0.6.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"lithos-mcp","url":"https://pypi.org/project/lithos-mcp/","firstSeenAt":"2026-09-09T23:25:44.559Z","fetchedAt":"2026-10-28T09:20:50.536Z","normalizedAt":"2026-10-28T09:20:50.536Z"}]},"firstSeenAt":"2026-09-09T23:25:44.559Z","updatedAt":"2026-10-28T09:22:53.411Z"}