osgrep
A local semantic code search tool that works like grep but takes natural-language questions. It is built to help coding agents find relevant code faster and with fewer tokens.
Share on XLicense: Apache-2.0
Overview
osgrep is a local semantic code search tool that works like grep but accepts natural-language questions. It is built for coding agents, helping them find relevant code with fewer tokens. Embeddings run locally through onnxruntime-node, and each repository gets its own index that is created on the first search. You install it with npm and search from inside a repo.
Key features
- Finds concepts such as where authentication is handled
- Call graph tracing with the trace command
- Labels code roles such as orchestration and definition
- Fully local embeddings, with a separate index per repository
- Output includes symbols, roles and call graphs for agents
Best for
Developers and coding agents that need to find code by meaning in a repository. Embedding models of about 150MB are downloaded during setup or on first use.
- Upstream
- Ryandonofrio3/osgrep
- Fork on GitHub
- Guo-astro/osgrep
- Upstream stars
- 1.1k
- Category
- AI agents and LLM tools
- Language
- TypeScript
- License
- Apache-2.0
- Forked
- 2025-11-23
- Sync status
- In syncLast synced 2026-10-06
More in AI agents and LLM tools
A curated library of DESIGN.md files for AI coding agents, helping teams reuse real design system patterns to generate matching UI from a reference design.
Forked 2026-10-05Last synced 2026-10-06License: MITAI agents and LLM toolsGitHub
A library of marketing skills for AI coding agents, covering CRO, copywriting, SEO, analytics, and growth engineering. Add the skills to a project so agents can apply marketing workflows to their work.
Forked 2026-10-05Last synced 2026-10-06License: MITAI agents and LLM toolsGitHub
An agent skill that turns natural language and system sources into editable architecture diagrams. It helps teams keep system views aligned with code, infrastructure, and APIs as architecture changes.
Forked 2026-10-05Last synced 2026-10-06License: MITAI agents and LLM toolsGitHub
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA, and ROCm. It helps run capable open-weight models on consumer hardware without relying on a cloud service.
Forked 2026-10-03Last synced 2026-10-06License: MITAI agents and LLM toolsGitHub