ogham-mcp/ogham-mcp

Shared memory MCP server — persistent, searchable, cross-client

45
/ 100
Emerging

Implements hybrid search combining dense embeddings (pgvector) with sparse lexical matching (tsvector) in a single PostgreSQL query—achieving 97.2% recall@10 on LongMemEval without cross-encoder reranking. Deploys as an MCP server supporting both stdio mode (per-client isolation) and SSE mode (shared persistent process), with pluggable embedding providers (OpenAI, Ollama, Mistral, local ONNX) and optional FlashRank reranking for self-hosted setups. Targets AI coding agents across Claude Code, Cursor, VS Code, and other MCP clients with automatic schema migration and environment setup via CLI wizard.

No Package No Dependents
Maintenance 13 / 25
Adoption 9 / 25
Maturity 9 / 25
Community 14 / 25

How are scores calculated?

Stars

82

Forks

11

Language

Python

License

MIT

Last pushed

Mar 28, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/ogham-mcp/ogham-mcp"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.