Better context. Better code.
Define what you want. Let Claude Code, Codex, opencode, Gemini CLI, and GitHub Copilot CLI build it — safely.
Watchfire turns clear specs into scoped tasks, then hands each one to an agent in its own git worktree and sandbox. Better context in, better code out — with clean transcripts and full control at every step.
From pair programming to autonomous loops
Six modes that cover interactive chat, single tasks, and fully hands-off Wildfire runs.
Wildfire
Autonomous loop — execute ready tasks, refine drafts, generate new tasks, repeat.
Chat
Interactive session with the coding agent — ask questions, iterate, and pair-program.
Task
Execute a single task from the task list in its own worktree.
Start All
Run every ready task sequentially, one worktree per task.
Generate Definition
Auto-generate a project definition by scanning your codebase.
Generate Tasks
Break down the project definition into discrete, ready-to-run tasks.
Any agent. One orchestrator.
Watchfire is backend-agnostic. Plug in your favourite CLI coding agent — or mix and match across tasks.
Claude Code
Anthropic
Codex
OpenAI
opencode
Open source
Gemini CLI
Copilot CLI
GitHub
One window for the whole fleet
Watchfire turns agents you have to babysit into a fleet you can supervise. The dashboard, notifications, insights, and integrations work together to keep you in the loop without staying on the keyboard.
Dashboard
Aggregate status bar, filter chips, layout toggle, live PTY previews. See working / needs attention / idle / done at a glance, then drill in.
Learn moreNotifications
Typed notification bus with OS notifications, bundled sounds, dynamic tray menu, and a weekly digest. Headless? They land in a JSONL fallback log.
Learn moreInsights & metrics
Per-task token, cost, and duration capture. Per-project Insights, cross-project rollup, CSV / Markdown export, plus an inline diff viewer pre- or post-merge.
Learn moreIntegrations
Outbound webhooks, Slack, Discord, GitHub auto-PR. Inbound HTTP server with signature verification and idempotency, routing slash commands to a transport-agnostic command layer.
Learn moreBuilt for real agent workflows
Isolation, sandboxing, and orchestration — the plumbing that makes multi-agent safe.
Task Orchestration
Ship work without babysitting sessions. Write tasks in YAML and the daemon handles the rest — picking up ready work, stopping sessions on completion, and chaining to the next task. Every run lands in the same clean transcript, no matter which backend produced it.
Git Worktree Isolation
Every task runs in its own git worktree on a dedicated `watchfire/<n>` branch — never the working tree you're in. Tasks run one at a time per project (the agent finishes one before starting the next), but each one is isolated from your branch and from any work in flight. Finished tasks auto-merge back to your default branch.
Sandboxed Execution
Your credentials and dotfiles stay off-limits, even if an agent goes off-script. Every session runs inside a platform-native sandbox — Seatbelt on macOS, Landlock or Bubblewrap on Linux — blocking ~/.ssh, credential stores, and git hooks by default. Restart protection stops runaway loops before they burn budget.
Multi-Project Management
Drive every repo on your machine from one place. A single daemon runs multiple projects concurrently — each with its own task queue and one active agent at a time — so spreading work across repos is how you get real parallelism. The system tray keeps them all one click away.
What you get that the raw CLI doesn’t
Same agents you’d run yourself — wrapped in the safety rails you’d otherwise build by hand.
Edits land directly on your working tree; one bad refactor and you're fighting git stash.
Each task runs on its own git worktree and branch. Failed runs leave your main branch untouched.
The agent inherits your shell's PATH, SSH keys, and cloud creds. One prompt-injected command, one bad call.
Sandboxed by Seatbelt on macOS and Landlock on Linux; ~/.ssh, credential stores, and .git/hooks blocked by default.
One repo, one agent, one terminal. Three tasks waiting on the previous to merge.
One agent per project, but every project on your machine runs concurrently — open several repos and they all make progress at once.
Scrollback in your terminal is the only record. Hope you didn't clear it.
Clean transcripts captured per task; inline diff viewer on the worktree branch; insights track duration, tokens, and cost.
You manage what runs when, by hand.
Wildfire mode runs ready tasks, refines drafts, and generates new ones toward your project definition.
How it shows up in your day
Concrete moments where Watchfire earns its keep — not features, but the work itself.
Drain a queue across projects
Each project runs one agent at a time, but every project on your machine runs concurrently. Queue ready tasks in three repos and watch them drain in parallel — each on its own worktree, each auto-merging back when it's done.
Read moreRefactor without losing your place
Hand a long refactor to a task and keep moving on the next thing in chat. The session runs in the background; the transcript and the diff are waiting when you come back, ready to review.
Read moreOperate a fleet of repos
The Beacon dashboard rolls every project into one window — what's running, what needs attention, what's done. Slack, Discord, and OS notifications fan out the rest, so you don't have to keep the app open to know.
Read moreTriage a flood of tasks
Wildfire mode picks up ready work, refines the drafts, and writes new tasks toward your project definition until the goal is met. Walk away with a backlog; come back to a branch full of completed work.
Read moreGet started with Watchfire
Install in seconds. Define tasks. Let agents ship code for you.
Download for macOSAvailable for macOS, Linux, and Windows
# Install via Homebrew (macOS)brew tap watchfire-io/tapbrew install --cask watchfire-io/tap/watchfire# Set up your project and gowatchfire initwatchfire task add "Build the login page"watchfire start --allIncludes GUI, CLI, and daemon. Also available via Homebrew.
Every project, one window
Watchfire.app puts your repos, tasks, branches, and live agent terminals in a single multi-project client — built on the same daemon as the CLI.
Three regions, one window
The app is built around a fixed sidebar, an active main view, and a collapsible right panel — so live agent output never crowds out the work you're reviewing.
Sidebar
Every project, the dashboard, and Settings — always one click away.
Main content
Tasks, Definition, Secrets, Trash, and Settings — plus a built-in terminal docked at the footer.
Right panel
Live Chat, Branches, and Logs. Collapse it when you want focus, pop it back when you need eyes on the agent.
Three components, one system
A daemon orchestrates in the background while the CLI and GUI give you full control.
CLI / TUI
watchfireProject-scoped commands plus a rich interactive TUI with split-pane task navigation and live output.
GUI (Watchfire.app)
Watchfire.appElectron multi-project client with a native feel, sidebar navigation, and embedded live terminals.
Daemon (watchfired)
watchfiredBackground service handling orchestration, PTY management, git workflows, and the gRPC API.
Questions, answered
The honest version — what Watchfire does, what it doesn’t, and how it stays out of your way.
How is this different from running Claude Code, Codex, or another agent directly?
How does Watchfire compare to Aider, Cursor, or Devin?
Which agent backends are supported?
Is my code and are my credentials safe?
sandbox-exec) on macOS, Landlock (kernel 5.13+) with a Bubblewrap fallback on Linux — with ~/.ssh, credential stores, and .git/hooks blocked by default. Restart protection caps runaway loops before they burn budget. Full sandboxing details.What platforms does Watchfire run on?
Is it free? Open source?
Do I need to use the GUI, or can I run everything from the terminal?
watchfire) and the interactive TUI cover everything the GUI does — they all talk to the same daemon over gRPC. The Electron GUI is just another client; pick whichever fits your workflow, or use both side by side.Can Watchfire post to Slack or Discord, or open GitHub PRs automatically?
How do I see what an agent actually did?
watchfire/<n>) and post-merge (reconstructed from the merge commit), and a per-task Insights record captures duration, tokens, and cost. GUI walkthrough · Insights & metrics.Get started with Watchfire
Install in seconds. Define tasks. Let agents ship code for you.
Download for macOSAvailable for macOS, Linux, and Windows
# Install via Homebrew (macOS)brew tap watchfire-io/tapbrew install --cask watchfire-io/tap/watchfire# Set up your project and gowatchfire initwatchfire task add "Build the login page"watchfire start --allIncludes GUI, CLI, and daemon. Also available via Homebrew.