probelabs/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.
Exposes search via Model Context Protocol (MCP) for seamless Claude integration, and includes a multi-provider agent layer with Elasticsearch-style boolean queries (`AND`, `OR`, filters) that leverage AST boundaries to return complete functions—eliminating mid-block truncation. Offers zero-setup semantic search with BM25 ranking and token-aware session deduplication, all entirely local without embedding models or external indexing.
494 stars.
Stars
494
Forks
50
Language
Rust
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/probelabs/probe"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
cocoindex-io/cocoindex
Data transformation framework for AI. Ultra performant, with incremental processing. 🌟 Star if...
dtsola/xiaoyaosearch
小遥搜索，听懂你的话、看懂你的图，用AI找到本地任何文件。让搜索像聊天一样简单。XiaoyaoSearch: Understands your words, reads your...
Ryandonofrio3/osgrep
Open Source Semantic Search for your AI Agent
justincasher/lean-explore
A search engine for Lean 4 declarations
yoanbernabeu/grepai
Semantic Search & Call Graphs for AI Agents (100% Local)