

Desktop app for reviewing AI-agent code changes in the local git worktree before they are ever committed or pushed.

Desktop app for reviewing AI-agent code changes in the local git worktree before they are ever committed or pushed.
GitWarren is a local, offline desktop application for reviewing code that AI coding agents write, at the point where the changes still live in the git worktree rather than in a pull request. It finds the worktree for a checked-out branch wherever it sits on disk and folds staged, unstaged and untracked files into a single readable diff you can comment on line by line. It also ships an MCP server over stdio that exposes the same seventeen tools the app itself uses, so Claude Code, Codex or any other MCP client can open a review, read the discussion, reply in a thread, comment on a line and resolve it. Every machine-written comment is attributed from the MCP handshake rather than a self-reported name, and each MCP session gets its own id so two agents working concurrently stay distinguishable. Nothing leaves the machine: there is no account, no cache, and all reviews and comments live in one SQLite file in the application-data directory.
Desktop app for reviewing AI-agent code changes in the local git worktree before they are ever committed or pushed.
GitWarren works by combining Pre-Commit Worktree Review: Reads staged, unstaged and untracked files straight from the git worktree and folds them into one diff, so agent output is reviewed before it becomes a commit or a pull request., MCP Server for Coding Agents: Ships a stdio MCP server exposing the same seventeen tools the app uses, letting Claude Code, Codex or any MCP client open reviews, read threads, reply, comment on lines and resolve them., Guaranteed Comment Attribution: Machine-written comments are always marked as such and the agent's name comes from the MCP handshake rather than whatever the model calls itself, so a human comment can never be mistaken for an agent one., Per-Session Agent Identity: Each MCP session receives its own id, so two agents reviewing at the same time are told apart in a thread without either needing to cooperate., Editable Human Ownership: You can edit or delete anything in a review, while an agent is held to its own messages — it can fix its own typo but cannot rewrite yours. to help users with Reviewing Agent Output Before Commit: Read and comment on everything a coding agent produced while the changes are still a dirty worktree and corrections are cheap., Interrogating an Agent About Its Own Diff: Ask the agent that wrote the code to explain a change or answer a line comment directly inside the review thread where the answer stays., Coordinating Multiple Agents: Keep two or more concurrently running agents distinguishable in a shared review thread when parallelizing work across a repository., Air-Gapped or Confidential Code Review: Review proprietary code on machines that cannot send diffs to a hosted service, since GitWarren never leaves the local machine., Catching Untracked Files: Spot and review files an agent created but never added to git, which pull-request-based tools never surface..
Key features include Pre-Commit Worktree Review: Reads staged, unstaged and untracked files straight from the git worktree and folds them into one diff, so agent output is reviewed before it becomes a commit or a pull request., MCP Server for Coding Agents: Ships a stdio MCP server exposing the same seventeen tools the app uses, letting Claude Code, Codex or any MCP client open reviews, read threads, reply, comment on lines and resolve them., Guaranteed Comment Attribution: Machine-written comments are always marked as such and the agent's name comes from the MCP handshake rather than whatever the model calls itself, so a human comment can never be mistaken for an agent one., Per-Session Agent Identity: Each MCP session receives its own id, so two agents reviewing at the same time are told apart in a thread without either needing to cooperate., Editable Human Ownership: You can edit or delete anything in a review, while an agent is held to its own messages — it can fix its own typo but cannot rewrite yours..
GitWarren is useful for anyone interested in Reviewing Agent Output Before Commit: Read and comment on everything a coding agent produced while the changes are still a dirty worktree and corrections are cheap., Interrogating an Agent About Its Own Diff: Ask the agent that wrote the code to explain a change or answer a line comment directly inside the review thread where the answer stays., Coordinating Multiple Agents: Keep two or more concurrently running agents distinguishable in a shared review thread when parallelizing work across a repository., Air-Gapped or Confidential Code Review: Review proprietary code on machines that cannot send diffs to a hosted service, since GitWarren never leaves the local machine., Catching Untracked Files: Spot and review files an agent created but never added to git, which pull-request-based tools never surface..
GitWarren is free to use.
Visit https://gitwarren.com/ to sign up and explore GitWarren.
Browse by use case: Code Generation
Compare GitWarren: vs Ponytail · vs dif.sh · vs Chalked · vs Causal