#362 · Primary category： AI Coding Assistants
probe
AI-friendly semantic code search engine for large codebases. Combines ripgrep speed with tree-sitter AST parsing. Powers AI coding assistants with precise, context-aware code understanding.
Project last updated：08/29/26
GitHub Stars
695
Forks
63
Contributors
11
License
Apache-2.0
Why we included this project
Most code search tools either hand you raw grep line fragments or force you to stand up an embedding index before they do anything useful. Probe takes a third path: it parses code with tree-sitter, understands structure rather than text, and returns complete functions and classes ranked by BM25/TF-IDF scoring. For AI coding assistants that means a vague request like "find the authentication logic" can become a precise query that returns meaningful context in one call, with no vector database to configure. It runs as an MCP server, a CLI, or a Node.js SDK, works fully offline, and fits into Claude Code, Codex, or your own agent pipeline. Teams building or using AI tools on large codebases will find it a deterministic way to give their assistants real code understanding instead of shallow grep noise.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.