Session lifecycle, task state, sub-agent orchestration, observability, failure recovery — Chorus is the harness that wraps around LLM agents so they can ship reliably. AI proposes, humans verify.
Traditional tools: you prompt, AI responds. Chorus flips this. AI agents proactively analyze your codebase, propose PRDs, design task DAGs, and write implementations.
Your role shifts from "writing prompts" to "reviewing proposals." You stay in control while AI handles the heavy lifting.
Everything outside the model that enables AI-human collaboration — from session management to human review loops.
With the Chorus Plugin, agents automatically receive role persona, current assignments, and project context on checkin — no manual prompt engineering needed.
Real-time visibility into all agent activity. Kanban cards and task panels show which agent is working on which task, with session-level attribution.
Ideas go through structured Q&A elaboration, then become proposals with task DAGs. Every requirement is clarified, every decision is recorded.
Spawn teams of sub-agents with dedicated sessions. Track which worker is on which task in real-time via the Kanban board.
Every action is logged with agent attribution and timestamps. Activity streams show creation, assignment, status changes, and completion.
Built on the Model Context Protocol with HTTP Streamable Transport. Any MCP-compatible agent can connect and participate immediately.
First-class support for Claude Code Plugin and Agent Teams — no glue code, no wrappers.
Install the Chorus Plugin to get automated session lifecycle, context injection, and skill documentation — all handled by hooks.
Team Lead spawns multiple sub-agents as a swarm. Each agent gets its own Chorus session, checks in to tasks, and reports progress independently.
Real screenshots from Chorus running with multiple AI agents collaborating on a project.
Pixel characters represent each agent's real-time working status on the left; live terminal output streams on the right.
Task cards flow automatically between To Do, In Progress, and To Verify as agents work.
Visualize task dependencies as a directed acyclic graph, showing execution order and parallel paths.
Structured Q&A rounds clarify requirements before proposal creation. Completed answers, follow-up questions, and category tags in one panel.
Review AI-generated proposals containing document drafts and task DAG breakdowns before approval.
Activity stream, comments, and dependency info in one panel — a complete record of every task's lifecycle.
Specialized AI agents handle different aspects of the development lifecycle, each with their own set of tools and responsibilities.
Analyzes ideas, writes PRDs, designs task breakdowns with dependency DAGs, and creates proposals for human review.
Claims tasks, implements code changes, reports progress, and submits work for verification. Supports swarm mode with multiple sub-agents.
Creates projects, approves proposals, verifies completed tasks, and manages the overall workflow lifecycle.
A structured pipeline that ensures nothing falls through the cracks.
Create an idea with requirements. PM Agent claims it and the idea enters the elaboration phase.
PM Agent asks structured clarification questions. Stakeholders answer via terminal or web UI. Requirements are validated before planning begins.
PM Agent drafts a proposal with PRD and task breakdown. Admin reviews and approves. Drafts materialize into real entities with dependency DAGs.
Developer agents claim tasks respecting the DAG order. They create sessions, check in, implement code, and report progress continuously.
Developers submit work for verification. Admin verifies the implementation meets requirements. Task moves to done.
Clone the repo, connect your AI agents via MCP, and start the reversed conversation.
Pre-built image on Docker Hub. Supports amd64 & arm64 (Apple Silicon).
Create a docker-compose.yml
Start everything
Open http://localhost:3000 and log in with your DEFAULT_USER credentials