probe
AI-friendly semantic code search engine for large codebases. Combines ripgrep speed with tree-sitter AST parsing. Powers AI coding assistants with precise, cont
What is 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.
Overview of probe
What it is
Probe is a code and markdown context engine with a built-in agent, designed for enterprise-scale codebases. It combines ripgrep speed with tree-sitter AST parsing to provide AI-friendly semantic code search. It powers AI coding assistants with precise, context-aware code understanding.
Key features
- Code-Aware: Tree-sitter AST parsing understands code structure - Semantic Search: Elasticsearch-style queries (AND, OR, NOT, phrases, filters)
- Complete Context: Returns entire functions, classes, or structs, not text chunks - Zero Indexing: No embedding models, vector databases, or setup required - Deterministic: Same query always returns the same results - Fully Local: Code never leaves the machine; no API calls for search - Built-in Agent: Multi-provider support (Anthropic, OpenAI, Google, Bedrock) with retry, fallback, and context compaction
Use cases
- Spec-driven development - Code reviews - Onboarding new developers - Any task where understanding code comes before writing - AI coding assistants needing precise context
Getting started
json { “mcpServers”: { “probe”: { “command”: “npx”, “args”: [“-y”, “@probelabs/probe@latest”, “agent”, “--mcp”] } } } Or use the CLI directly: bash npx -y @probelabs/probe search “authentication AND login” ./src
License and pricing
Licensed under Apache-2.0. Open source and free to use.
Based on the project's public README and repository metadata.
