Back to directory

Infigraph

An AST-powered code intelligence engine that indexes a codebase into a persistent knowledge graph with Cypher queries, cross-file call resolution and hybrid semantic search across 62 languages.

Infigraph

Infigraph runs locally with no API keys and no network calls, aiming to answer questions such as who calls a given function or what breaks if a class changes without an AI agent having to re-read files and re-infer relationships from source on every question, a cost the project puts at 60 to 80 percent of an agent's tokens today. It supports 62 programming languages with full Cypher queries and hybrid semantic search over the resulting graph.

It can serve as a remote MCP server over HTTP for team-wide use, supports indexing more than 30 repositories at once in a remote mode backed by Neo4j and Postgres, and can auto-reindex through a GitHub webhook when a pull request merges. Configurable context compression, with an optional companion component, reduces how much of the graph an agent needs to read at once. It is written in Rust.

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.