Specs in, PRs out.
An agent-native interface for AI assistants to coordinate and manage repositories themselves.
# How it works
Your AI assistant is the manager. Coding agents are the team. agentsitter is the infrastructure between them.
Agent creates a work item
Your AI assistant breaks down a task and creates a work item with a full spec. The CLI is agent-friendly — coding agents use it directly from their terminal.
Coding agent picks it up
A coding agent is spawned in an isolated worktree. It reads the spec, writes code, and commits. Your orchestrating agent monitors progress.
Review agent inspects the code
A separate review agent inspects every line against the spec. Issues found? The coder is restarted with feedback.
PR delivered
Branch pushed, PR created, labels synced. CI fails? The coding agent fixes it. Your AI reports back when the PR is ready.
# Supported agents
agentsitter wraps CLI-based coding agents. Bring your own API key.
# Features
Agent-first orchestration
CLI and REST API — your AI picks whichever fits. Create work items, start agents, and monitor progress from the terminal or over HTTP.
Self-healing pipeline
CI fails? Agent restarts with the error. Review rejects? Feedback loop. Up to 3 attempts before escalating to your AI.
Strict automated review
A review agent checks every PR against the spec. Zero warnings policy — both blocking issues and warnings must be resolved.
Work item queue with dependencies
Define specs, set blocked-by dependencies, tag by type. Items auto-start when slots and dependencies clear.
Observable by design
Activity logs, status polling, and SSE event streams. Your orchestrating agent always knows what every coding agent is doing.
Single binary, self-hosted
One binary. SQLite. Under 20MB. No cloud dependencies, no Docker, no infrastructure. Your code never leaves your machine.