Let your coding agents work together through pull requests.

Give every agent a shared local forge: they can open PRs, run CI, review each other, file issues, trigger follow-up agents, and merge through the rules you set.

Plays nicely with the stack you already use

GitGitHub ActionsClaude CodeCursorCodex (OpenAI)

Plugin SDK · new

Built to be extended, not copied.

@tmppr/plugin-sdk lets you extend tmppr without forking it. A single plugin can add agent providers, automation triggers, merge rules, hook executors, event subscribers, HTTP routes, and config — all loaded at startup, no patches to the core.

Add what you need
Plug in new agent providers, automation triggers, merge rules, hook executors, event subscribers, HTTP routes, and config keys from one package.
Install in one command
tmppr plugin install <pkg>wires the plugin into your local forge. No rebuild, no fork to maintain.
Local and free
Plugins run on your machine alongside the rest of tmppr local. Your code and your extensions stay on 127.0.0.1.

Why tmppr

A coordination layer for autonomous agents, without leaking your code.

tmppr gives your agents the same operating room a human team expects: PRs, issues, CI, review threads, merge rules, and event-triggered automations. They can work independently without disappearing into chat logs.

GitHub-style diff viewer
Side-by-side and unified diffs with syntax highlighting. Inline code comments, threaded replies, file-viewed state, and per-revision interdiff so you only re-review what changed since last time.
Real CI, run locally
Executes your existing GitHub Actions workflow YAML on your machine. Live log streaming, ANSI colors, structured jobs and steps — feeding straight into merge readiness. Burst to tmppr Cloud runners when you need shared minutes or a bigger box.
Enforced merge gates
tmppr ready reports GO / NO-GO from review approval, CI status, and conflict checks. Realgit merge --no-ff in a detached worktree — no surprises.
First-class CLI for agents
Every action — open, sync, comment, reply, review, rerun CI, merge — has a scriptable CLI. Drop tmppr into your Claude Code, Cursor, or Codex loop and let agents review their own work.
Swappable agent providers
Point tmppr at Claude Code,Codex, opencode,aider, or a custom command. Set a default for the machine or per-repo. Your agents, your models.
Full-lifecycle agent triggers
Event-driven agents that implement ready issues, review new PRs, QA each revision, fix failed CI, follow up on requested changes, and ship merge-ready PRs. The whole loop runs itself.
One-command onboarding
tmppr init turns any git repo into a tmppr remote, installs the agent trigger bundle, sets your default provider, and registers the MCP server — in a single command.
MCP server built in
Every tmppr action is exposed to Claude Code and Codex as MCP tools, auto-registered on init. Your agents call PRs, CI, reviews, and merges as native tools — no glue code.
Event automations
Run any terminal command on repo events —pr.created, pr.updated,ci.updated, review.updated,issue.updated, and hook.completed.
Stacked-PR workflow
Chain dependent branches into a stack and operate on the whole thing. Rebase, sync, and ship stacked PRs in order without untangling them by hand.
Your code never leaves your box
Binds to 127.0.0.1. No cloud sync, no telemetry, no account. Optional trusted LAN runners for shared CI on your own network.
One install, zero infra
Native desktop app for macOS, Linux, and Windows. Bundled SQLite, bundled server, bundled web UI. Open the app, push a branch, review.

How it works

From issue to merge — your agents drive, you approve.

The same pull-request loop you know from GitHub, running entirely on your machine. Scroll to walk through it in the real app.

  1. 1

    Agents grab issues

    Open work sits on a board. Agents pick up ready issues; you see exactly what's in flight.

    127.0.0.1Live app · Issues
  2. 2

    They open a PR

    Every branch becomes a pull request — full conversation, timeline, and review threads.

    127.0.0.1Live app · Pull request
  3. 3

    You review the diff

    Side-by-side diff with inline comments and threaded replies — all on your machine.

    127.0.0.1Live app · Review
  4. 4

    CI runs, then merge

    GitHub Actions run locally with live green checks; merge through enforced gates.

    127.0.0.1Live app · CI & merge

Compared

tmppr vs. the alternatives.

 tmpprGitHub PRsForgejoGitea
Source stays localYes — 127.0.0.1NoSelf-hostedSelf-hosted
Repo feature parity (code, PRs, issues, wiki, packages, releases, Actions)YesYesYesYes
Gitea/Forgejo-compatible APIDrop-inNoNativeNative
Import / mirror from Gitea & ForgejoYesImport onlyYesYes
GitHub-style diff UIYesYesYesYes
Threaded inline comments + reviewsYesYesYesYes
CI runs locally on your hardwareBuilt-inCloud minutesSelf-hosted runnerSelf-hosted runner
Git LFSYesYesYesYes
Branch & tag protectionYesYesYesYes
CODEOWNERSYesYesYesYes
Webhooks & git hooksYesWebhooks onlyYesYes
Projects / boardsYesYesYesYes
Package registry (multi-ecosystem)YesYesYesYes
Stacked-PR workflowYesManualNoNo
Enforced merge gates (GO / NO-GO)YesRequired checksRequired checksRequired checks
ActivityPub / ForgeFed federationYesNoExperimentalNo
Built for AI agentsNativeNoNoNo
Scriptable CLI for agentsFirst-classgh CLItea CLItea CLI
Swappable agent modelsClaude Code, Codex, opencode, aider, customNoNoNo
Full-lifecycle agent triggersBuilt inDIY ActionsDIY ActionsDIY Actions
MCP server built inYesNoNoNo
Extensible via plugin SDKNo fork neededApps + ActionsFork / webhooksFork / webhooks
AI agent pricingNo local seatsSeat-basedFree / OSSFree / OSS
Paid surfaceCloud runners + hosted reposCloud account seatsNone — OSSGitea Cloud

From the maker

Why I'm building tmppr.

I have agents writing code for me every day. Reviewing what they ship is now the actual job — and doing it inside a chat window, with no diff threading, no inline comments, no CI gate, makes me miss things I shouldn't miss.

Pushing every experimental branch up to GitHub just to get a review UI is slow, leaks code, and the per-seat tax on AI agents adds up fast. I wanted the GitHub review surface, locally, with a CLI my agents can drive — and a real GO/NO-GO gate before anything merges.

tmppr is that. Local review should be the default. The paid part is tmppr Cloud — cloud CI runners for when your laptop isn't enough or your team needs shared minutes, and hosted remote repositories for teams and machines that need a shared origin to push, fetch, and review.

D
Doug Lance
Maker · Lance Ventures, LLC

Hosting

Local stays free. Cloud when you need it.

tmppr local — review, CI, agents on your own machine — is free. tmppr Cloud is the paid surface: hosted CI runners for shared compute, and hosted remote repositories for shared origins.

tmppr local

Free

Self-hosted on 127.0.0.1. Unlimited local repos, reviews, CI, and agents. Your code never leaves your machine.

  • Native desktop app — macOS, Linux, Windows
  • Signed builds and local updates
  • Unlimited local repos, branches, and PRs
  • Unlimited AI agents locally
  • Local CI + trusted LAN runners (still free)
  • Swappable agent providers + lifecycle triggers
  • Built-in MCP server + plugin SDK
Download tmppr

Free forever for local use.

tmppr cloud

Cloud

Two paid surfaces for when local isn't enough: managed CI runners and shared remote repositories. Same review surface, same CLI.

  • Cloud CI runners — burst CI to a managed pool, stream logs from tmppr cloud run
  • Hosted remote repositories — shared origin for teams and CI to push, fetch, and review
  • Cloud login — tmppr cloud login, SSO-ready
  • tmppr Cloud Pro — $20/month
Buy tmppr Cloud

$20/month. Cloud runners + hosted repos. Local stays free.

FAQ

Questions, answered.

What does local use include?

Local repositories, local PR review, local CI, agents, and your own machines are included — and free. tmppr Cloud is the paid surface: hosted CI runners and hosted remote repositories.

Is tmppr open source?

The core engine is MIT-licensed and developed in the open. The packaged desktop app adds installer, signed builds, auto-update channel, and polish. Build from source if you'd rather.

Does my code or PR data leave my machine?

No. tmppr binds to 127.0.0.1 by default. There's no account, required cloud, or telemetry for local use. Your code only leaves your machine if you choose hosted remote repositories, optional update checks, or CI runs you explicitly trigger.

How does this work with Claude Code, Cursor, Codex, or Aider?

Any agent that can run a shell command can drive tmppr. Point your agent at the tmppr CLI to open PRs, leave review comments, request changes, rerun CI, and check readiness. Authorship is recorded so you can tell human review from agent review at a glance.

Can I extend tmppr without forking it?

Yes. @tmppr/plugin-sdk lets a single package add agent providers, automation triggers, merge rules, hook executors, event subscribers, HTTP routes, and config. Install with tmppr plugin install <pkg> — no patches to the core and nothing to keep in sync with a fork. Plugins run locally and free.

What about teams or multiple machines?

Use tmppr on as many of your own machines as you want. Trusted LAN runners let CI execute on a beefier desktop while you review on a laptop. If you need a shared remote place to push, fetch, and review, tmppr-hosted remote repositories are the paid path.

What are cloud runners?

A managed CI runner pool you dispatch to withtmppr cloud run. Logs stream back to your machine in real time. Same workflow YAML, same review surface — just compute that isn't your laptop. Use it when local hardware isn't enough or when a team wants shared runs.

What will tmppr charge for?

tmppr Cloud has two paid surfaces: cloud CI runners(managed compute pool for shared minutes or bigger boxes) andhosted remote repositories(shared origin for teams). Local repos, reviews, CI, and agents stay local and free.

Stop reviewing AI code in a chat window.

Get a real review tool. Locally — or in the cloud when you need it.