Reviu

Reviu is a native desktop app for reviewing code written by AI agents, sending line comments back as prompts, and managing branches with Git.

Reviu is a native desktop app built with Rust and GPUI for managing coding-agent sessions. It lets developers launch local CLI tools, inspect generated diffs, leave inline comments, and send batched feedback back to the agent as a single prompt. The software runs ACP-registry agents locally, including Claude Code, Codex, Gemini, Copilot, and Cline, using existing subscriptions without metering. Users manage tasks in isolated Git worktrees and handle staging, rebasing, committing, and conflict resolution directly in the app. A Pro tier connects local branches to GitHub pull requests, review threads, checks, and merges.

Reviu at a glance

Best for: Software engineer
Runs on: macOS, Windows, Linux, CLI
Pricing: Free for local agent sessions, diff review, and local Git; Pro adds GitHub PRs, checks, and reviews with a 14-day free trial.
Released: October 2026
Category: AI coding tool
Website: reviu.dev

Key features

Run ACP-registry agents like Claude Code, Codex, and Gemini
Inspect local diffs and batch inline comments back to the agent
Isolate parallel agent tasks across separate Git worktrees
Track agent commands, file edits, permissions, and attention states
Stage hunks, rebase, squash, commit, and resolve Git conflicts
Command palette for keyboard-first Git and session actions
Review GitHub pull requests, reply to threads, and submit reviews
View GitHub checks, merge branches, and receive inbox notifications

Use it for

Reviewing code diffs generated by local AI coding agents
Batching inline code review comments into prompts to request agent fixes
Running multiple coding agents simultaneously in isolated Git worktrees
Shaping and cleaning Git commit history before submitting pull requests
Managing GitHub pull request reviews, status checks, and merges locally

Companions

Tools that articles about Reviu recommend using with it, each with its job.

Context7 — Provides up-to-date documentation for AI agents and code editors.
Ollama — Run local models at zero marginal cost, with code kept on your machine.
OpenRouter — Access over 500 models and 80 providers through one unified API.
Daytona — Runs sessions in isolated sandboxes synced to git branches.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
Oh My OpenCode Slim — Lightweight multi-agent orchestration and background tasks.

Alternatives to Reviu

jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
Revix AI — Extracts custom rules from your codebase to enforce repository standards.
OpenCode — Works with 75+ model providers, local models, and existing subscriptions
Crit — It keeps human feedback localized and precise for AI agent code iterations.
Entire CLI — Mirrors Git repositories globally to increase cloning speeds for AI agents.
Git AutoReview — Parallel AI reviews with human approval and bring-your-own-key security.
Coucou — It provides open-source, real-time agent monitoring and approvals directly from the screen notch.
Reviewer Agent — It uses a separate AI model to review code and prevent premature agent stopping.
Sonah — Verifies agent tasks and decisions against the actual code changes.
GitHub Copilot — Built into GitHub, with Claude and Codex agents on the same plan
pmtui — Manages long-running agent sessions with an automated heartbeat and dashboard.
Git AI — It moves work to the server and handles concurrent tasks without standard Git bottlenecks.

All Reviu alternatives