{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_unyhd5xus3z7","handle":"ogham-mcp","url":"https://wellknown.network/agents/ogham-mcp","links":{"self":"https://wellknown.network/agents/ogham-mcp/record.json","html":"https://wellknown.network/agents/ogham-mcp","markdown":"https://wellknown.network/agents/ogham-mcp/record.md","api":"https://wellknown.network/api/v1/agents/ogham-mcp","status":"https://wellknown.network/api/v1/agents/ogham-mcp/status","claim":"https://wellknown.network/agents/ogham-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/ogham-mcp/claim.json","badge":"https://wellknown.network/agents/ogham-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:ogham-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"ogham-mcp","summary":"Shared memory MCP server — persistent, searchable, cross-client","description":"# Ogham MCP\n\n*Ogham* (pronounced \"OH-um\") -- persistent, searchable shared memory for AI coding agents. Works across clients.\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Docker](https://img.shields.io/badge/Docker-ghcr.io%2Fogham--mcp%2Fogham--mcp-blue)](https://github.com/ogham-mcp/ogham-mcp/pkgs/container/ogham-mcp)\n[![Python 3.13+](https://img.shields.io/badge/Python-3.13%2B-blue)](https://python.org)\n[![PyPI](https://img.shields.io/pypi/v/ogham-mcp)](https://pypi.org/project/ogham-mcp/)\n\n## What it is\n\nAI coding agents forget everything between sessions. Switch from Claude Code to Cursor to Kiro to OpenCode and the context is gone -- decisions, gotchas, the shape of your codebase -- so you repeat yourself, re-explain, and re-debug the same issues.\n\nOgham gives your agents one shared memory that persists across sessions and clients. It is a **retrieval engine**: it stores what matters and finds it again, and your LLM reads the results.\n\nThe retrieval is **structured** -- hybrid search plus a typed-edge graph, not just vector similarity. That is what lets it answer questions whose answer is a *path between two facts*, the case where plain vector RAG falls down.\n\n## Quick start\n\n```bash\nuvx --from ogham-mcp ogham init\n```\n\n`ogham init` runs a setup wizard: it connects your database, picks an embedding provider, migrates the schema, and writes the MCP client config (Claude Code, Cursor, VS Code, and others). For Claude Code it runs `claude mcp add` for you; for other clients it prints the snippet to copy.\n\n**You need a database first** -- a free [Supabase](https://supabase.com) project or a [Neon](https://neon.tech) database. On Neon or self-hosted Postgres, install the postgres extra so the driver is available:\n\n```bash\nuvx --from 'ogham-mcp[postgres]' ogham init\n```\n\nThen tell your agent to remember something and ask about it later -- from the same client or a different one. They share the databa…","publisher":null,"homepage":"https://ogham-mcp.dev/docs/","repository":"https://github.com/ogham-mcp/ogham-mcp/blob/main/CHANGELOG.md","version":"0.19.0","license":null,"protocols":["mcp"],"tags":["agent-memory","embeddings","knowledge-graph","llm","mcp","memory","model-context-protocol","pgvector","postgres","rag","semantic-search","supabase"],"pricing":null,"endpoints":[{"url":"pypi:ogham-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"data.database","name":"Databases","confidence":1,"provenance":"declared"},{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"},{"slug":"knowledge.memory","name":"Agent Memory","confidence":1,"provenance":"declared"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"declared"},{"slug":"dev.version-control","name":"Version Control","confidence":0.779,"provenance":"derived"}],"categories":["data","dev","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":"ogham-mcp","registry":"pypi","observedAt":"2026-09-10T08:27:36.519Z","publishedAt":"2026-08-20T14:07:04.847252Z","latestVersion":"0.19.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"ogham-mcp","url":"https://pypi.org/project/ogham-mcp/","firstSeenAt":"2026-09-10T08:26:14.035Z","fetchedAt":"2026-09-10T08:26:14.035Z","normalizedAt":"2026-09-10T08:26:14.035Z"}]},"firstSeenAt":"2026-09-10T08:26:14.035Z","updatedAt":"2026-09-10T08:27:36.519Z"}