Osgrep

Visit Tool

osgrep is an open-source coding & development tool that provides semantic search for AI agents within codebases. It offers fast, local, and private code analysis, including call graph tracing and role detection.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is osgrep?

osgrep is an open-source semantic search tool designed for AI agents, enabling natural language searches within codebases to find concepts rather than just strings. It operates locally and privately, using 100% local embeddings via onnxruntime-node, ensuring data privacy. Key features include call graph tracing to map dependencies, role detection to distinguish orchestration from definition logic, and automatic repository isolation for separate indexing. osgrep is built for speed, offering sub-50ms responses with a lightweight HTTP server and live file watching. It integrates with Claude Code and Opencode plugins, allowing AI agents to query codebases efficiently and save LLM tokens.

Best used for

Ideal for developers who need to quickly understand complex codebases, trace function dependencies, and integrate semantic search capabilities into their AI agents. Especially valuable for optimizing LLM token usage and speeding up code analysis by providing relevant context.

Common actions

search code semantically

trace code dependencies

analyze code structure

integrate with AI agents

optimize LLM token usage

github copilotface swapping"AI Agents"deepfakelow-code/no-codeautomated workflowworkflowsopen-sourcecollaboration

Capabilities

Key features

Semantic code search
Call graph tracing
Role detection
Local embeddings
Agent-ready output
Automatic repository isolation
Incremental re-indexing

Target Audience

developer

Integrations

claude-codeopencode

Pricing & Plans

Open Source

Free

FAQs

How does osgrep ensure privacy and local operation?

osgrep operates 100% locally by using onnxruntime-node for embeddings, meaning all code analysis and data processing occur on your machine. This ensures that your codebase remains private and is not sent to external servers for semantic search or indexing.

What programming languages does osgrep support for semantic chunking?

osgrep supports semantic chunking using TreeSitter grammars for a wide range of languages, including TypeScript, JavaScript, Python, Go, Rust, C/C++, Java, C#, Ruby, PHP, JSON, YAML, Kotlin, Swift, and Dart. It can also index files without TreeSitter grammar support if explicitly allowed.

How does osgrep help AI agents save LLM tokens?

By providing precise semantic search results, call graph tracing, and role detection, osgrep helps AI agents retrieve only the most relevant code snippets. This reduces the amount of code an LLM needs to process, leading to an estimated 20% saving in LLM tokens and a 30% speedup in analysis.

Trending

Subcategories trending in Coding & Development

Open Source & Models DevOps & Infrastructure No-Code / Low-Code Testing & QA Backend & APIs Prompt Engineering

Trending

Also listed in

This tool also appears in

AI Agents & Automation › AI Frameworks & Infra

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce