Line-level attribution for AI-assisted code. Audit every agent, model, and prompt across your git history.
# agentdiff — Know What Every AI Agent Wrote <p align="center"> <strong>Line-level attribution for AI-assisted code. Audit every agent, model, and prompt across your entire git history.</strong> </p> <p align="center"> <a href="https://github.com/codeprakhar25/agentdiff/releases"><img src="https://img.shields.io/github/v/release/codeprakhar25/agentdiff?style=flat-square" alt="Latest release"></a> <a href="LICENSE-MIT"><img src="https://img.shields.io/badge/license-MIT%20%2F%20Apache--2.0-blue?style=flat-square" alt="License"></a> <a href="https://github.com/codeprakhar25/agentdiff/actions"><img src="https://img.shields.io/github/actions/workflow/status/codeprakhar25/agentdiff/ci.yml?style=flat-square&label=CI" alt="CI"></a> <img src="https://img.shields.io/badge/agents-7%2B-blueviolet?style=flat-square" alt="Agents supported"> <img src="https://img.shields.io/badge/built_with-Rust-orange?style=flat-square" alt="Built with Rust"> </p> --- agentdiff hooks into every major AI coding agent — Claude Code, Cursor, Codex, Cursor, Windsurf, OpenCode, Cursor — and writes a permanent, commit-scoped attribution record to your repository. Each record captures the agent name, model, prompt excerpt, and exact line ranges. All of it queryable from the CLI, no server required. ``` agentdiff list agentdiff list — 5 entries # COMMIT TIME AGENT MODEL FILE(S) LINES TRUST PROMPT ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────── 1 a1b2c3d4 Apr 14 09:12 claude-code cursor-sonnet-4-6 src/commands/push.rs 1-47 92 "fix ordering: write local ref before…" 2 b2c3d4e5 Apr 14 09:44 codex o4-mini src/store.rs +2 112-198, 201-230 — "add fetch_ref_content helper" 3 c3d4e5f6 Apr 13 18:
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.