Back to directory

Benzi

A tree-sitter-based compiler that parses an entire codebase into a queryable map of symbols, call edges and class relationships, so a coding agent can look up structure directly instead of reading whole files.

Benzi

Benzi is a compiler-backed code intelligence tool built for AI coding agents. Rather than dumping repository text into a model's context window, it parses every file with tree-sitter, resolves imports, builds class ancestry, and traces every identifier to its definition, joining call flow and data flow at each call site into one queryable map.

It supports ten programming languages through their own tree-sitter grammars, plus a second engine for markup such as HTML, CSS and DOM JavaScript. It exposes over 35 tools for exploring this map, of which 16 are available in the current release, and it is distributed as a VS Code extension and through a hosted demo that can analyze any public repository.

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.