Open-source CLI for AI code attribution & governance. Track which AI agent wrote every line — Claude, Cursor, Gemini, Codex. Blame, audit, search, backfill.
<p align="center"> <img src="https://getorigin.io/favicon.svg" width="80" alt="Origin Logo" /> </p> <h1 align="center">Origin CLI</h1> <p align="center"><strong>Know exactly what your AI agents are writing.</strong></p> <p align="center"> <a href="https://github.com/dolobanko/origin-cli/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-green" alt="License"></a> <a href="https://github.com/dolobanko/origin-cli/stargazers"><img src="https://img.shields.io/github/stars/dolobanko/origin-cli?style=social" alt="GitHub stars"></a> <a href="https://getorigin.io"><img src="https://img.shields.io/badge/web-getorigin.io-6366f1" alt="Website"></a> </p> <p align="center"> Track every AI coding session. Line-level AI/human attribution. Full visibility into AI-authored code.<br/> Zero setup — no server, no login, no API keys. All data stored in git.<br/> <strong>50+ commands</strong> · <strong>10+ agents</strong> · <strong>MIT licensed</strong> </p> --- ## Why Origin? AI now writes **30–70% of the code** that ships to production. But `git blame` still points at the human who pressed **Commit** — not the model, not the prompt, not the session. Once a line lands in `main`, the "why" is gone forever. Origin fixes that. It runs silently next to any AI coding agent (Claude Code, Cursor, Codex, Cursor, Aider, Windsurf, Continue, Cursor CLI, and more), captures the full session context — prompts, responses, tool calls, token counts, cost, duration — and attaches it to your commits as git notes. Everything stays in **your git repo**. No server. No login. No API keys. No data ever leaves your machine unless you explicitly push it. ### The problems Origin solves | Pain | What Origin gives you | |---|---| | 🕵️ **`git blame` is lying to you** — you see the human, not the AI that wrote the line | `origin blame` shows the exact model, agent, session, and prompt behind every single line | | 💸 **You have no idea how much AI is costing you** | Per-sess
Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.