GraphCanon updated today · GitHub synced today
Decision brief
grepai is designed for developing local semantic search and call graphs for AI agents with an emphasis on privacy.
Good fit when
- When you need to develop a system that prioritizes local processing without cloud dependencies, which is essential in highly regulated environments where data privacy and security are paramount.
- If your project benefits from having detailed code-level insights through call graphs that help in understanding and maintaining complex AI agent systems.
Avoid when
- Not suitable if your application requires real-time updates from cloud-based services, as grepai operates entirely locally without any online components for updating its functionality.
- If the development team prefers not to deal with C language implementation details,grepai might be less attractive given that other tools may support more modern or higher-level languages like Python.
- Pricing:
- freemium - Available at no cost due to its MIT licensing, with the scope of use limited only by any dependencies it requires.
Observed Jul 14, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Steady (61d since push)
- As of today
- Provenance
- Not a fork · Personal account
- As of today
- Security (OSV)
- No MCP manifest
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
git clone https://github.com/yoanbernabeu/grepaiSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
A tool for developing local semantic search and call graphs targeted at AI agents with focus on privacy first
Capability facts
- Languages
- c
Source: github.language · Aug 22, 2026
Categories
Tags
README
Installation
Homebrew (macOS):
brew install yoanbernabeu/tap/grepai
Linux/macOS:
curl -sSL https://raw.githubusercontent.com/yoanbernabeu/grepai/main/install.sh | sh
Windows (PowerShell):
irm https://raw.githubusercontent.com/yoanbernabeu/grepai/main/install.ps1 | iex
Requires an embedding provider — Ollama (default), LM Studio, or OpenAI.
Ollama (recommended):
ollama pull nomic-embed-text
Quick Start
grepai init # Initialize in your project
grepai watch # Start indexing daemon
grepai search "error handling" # Search semantically
grepai trace callers "Login" # Find who calls a function
License
MIT License - Yoan Bernabeu 2026
For agents
This page has a .md twin and JSON over the API.