# Chorus-AIDLC/Chorus

The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)

Repository: https://github.com/Chorus-AIDLC/Chorus
Canonical: https://ross.abutalabs.com/products/chorus
Homepage: https://chorus-ai.dev/
Language: TypeScript
License: AGPL-3.0
License Family: copyleft
Topics: ai-agents, ai-dlc, claude-code, kanban, multi-agent, task-management, agent-harness, harness
Last push: 2026-09-02T01:46:20+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 100, longevity 15
- inputs: {"age_days": 210, "days_push": 1, "days_rel": 1, "gap_med": 3, "n_releases_24m": 50}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1155, forks 104 (observed 2026-09-03T02:15:05.274866+00:00)

## What it is
Chorus is a self-hosted agent harness that coordinates a team of coding agents (Claude Code, MCP-compatible agents) plus human reviewers in a single pipeline following the AI-DLC methodology. It manages session lifecycle, task DAGs, sub-agent orchestration, fine-grained agent permissions, observability, and human-in-the-loop verification where agents propose and humans approve.

## Use cases
- orchestrate multiple coding agents on one project with human review
- turn a rough idea into an agent-generated PRD and task DAG before any code is written
- manage permissions for what AI agents are allowed to do in a codebase
- track multi-agent work on a kanban board with session-level attribution
- connect Claude Code or any MCP-compatible agent to a shared workflow
- self-host an AI-driven development lifecycle pipeline
- review AI proposals instead of writing prompts

## When to choose
- you run several coding agents and need shared task state, permissions, and human verification gates
- you want AI to propose plans and PRDs that humans approve before implementation
- you need a self-hosted, MCP-native orchestration layer with no vendor lock-in

## When to avoid
- you just want a single-agent coding assistant without workflow overhead
- you need a lightweight task tracker without AI agent integration
- AGPL-3.0 licensing is incompatible with your usage

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, mcp, workflow-automation, scheduling, monitoring, chat-interface
- domain: developer-tools, large-language-models, self-hosted
- platform: self-hosted, cross-platform
- tags: agent-harness, ai-dlc, multi-agent, human-in-the-loop, kanban, task-management, claude-code, coding-agents, orchestration, reversed-conversation, ai-agents, automation, web-server, docker, nodejs

## Member repositories
- Chorus-AIDLC/Chorus (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:05.274866+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:33:38.494479+00:00, confidence not recorded.
  - readme: https://github.com/Chorus-AIDLC/Chorus (fetched 2026-09-03T02:15:05.274866+00:00, sha 2d66a09390a1)
  - homepage: https://chorus-ai.dev/ (fetched 2026-08-29T12:38:44.483558+00:00, sha 1c0e39caaeac)
  - site_page: https://doc.chorus-ai.dev (fetched 2026-08-29T12:38:44.492966+00:00, sha 55a5d9a0b395)
- Data as of 2026-08-30T08:39:29.467469+00:00.