Back to directory

engraph

A local knowledge-graph and hybrid-search server for Obsidian vaults that exposes an MCP server, an HTTP REST API and ChatGPT Actions so AI agents can search, read and edit notes.

engraph

engraph turns a Markdown Obsidian vault into a searchable knowledge graph. It combines semantic embeddings, full-text BM25 search, wikilink graph traversal, temporal awareness and LLM-powered reranking into five search lanes fused with Reciprocal Rank Fusion, with an LLM orchestrator classifying each query to adapt lane weights, including a temporal lane for queries like "notes from last week."

An MCP server exposes 25 tools for search, section-level reads and edits, frontmatter mutation, vault health checks and note creation, usable from Claude Code, Cursor or any MCP client; an optional HTTP REST API adds 26 endpoints with API-key authentication, rate limiting and CORS for web-based agents and scripts. A file watcher keeps the index current as notes change in Obsidian, and vault health diagnostics detect orphan notes, broken wikilinks and stale content.

Everything runs locally as a single binary with no API keys or cloud services required. It is written in Rust and MIT licensed.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.