Back to directory

Probe

Probe is a code and markdown search engine that combines ripgrep-speed text search with tree-sitter AST parsing, giving AI coding agents structured, complete code context in a single call.

Probe

Probe is a context engine for reading and reasoning about large codebases, built for AI coding agents as well as human use. It parses code with tree-sitter so results return complete functions or classes rather than arbitrary text fragments or line-based matches, and it ranks results using BM25 and TF-IDF style relevance instead of plain line order.

It ships as a CLI, an MCP server, a Node.js SDK, and includes the Probe Agent, a purpose-built agent that searches, extracts and reasons across a codebase for tasks such as spec-driven development, code review and onboarding. It requires no indexing step or embedding service and works offline.

Probe 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.