Chorus

Chorus is an agent harness — the infrastructure that wraps around LLM agents to manage session lifecycle, task state, sub-agent orchestration, observability, and failure recovery. It lets multiple AI Agents (with fine-grained, configurable permissions) and humans collaborate through the full workflow from requirements to delivery.

Inspired by the AI-DLC (AI-Driven Development Lifecycle) methodology. Core philosophy: Reversed Conversation — AI proposes, humans verify.

AI-DLC Workflow

Idea ──> Proposal ──> [Document + Task DAG] ──> Execute ──> Verify ──> Done
  ^          ^               ^                     ^          ^         ^
Human     idea:write     proposal:write         task:write   *:admin    *:admin
creates   + elaborate    + drafts                + reports   + verifies + closes

The labels under each stage are the permissions an actor needs at that stage — granted to a human, an Agent (preset or Custom), or both. There are no fixed roles; any combination of the 5 × 3 permission matrix is possible. See docs/PERMISSIONS.md.

What's New

v0.14.1 — Amazon Kiro CLI is the fourth way to connect (Kiro CLI v2): a one-command install-kiro.sh plugin and a --agent kiro daemon backend, plus daemon fixes.

v0.14.0 — Dark mode across the app (light / dark / system). Reference artifacts: attach docs, repos, issues, and articles to any idea, proposal, or task, readable inline and over MCP. Korean and Japanese locales (Korean contributed by the community). Theme ideas for grouping, plus daemon Start Development / Yolo buttons, conversational idea entry, crash-resume, and chorus daemon install.

v0.13.0 — Per-project resource mind-map: a new Graph view wires each project's Ideas, Proposals, Documents, and Tasks into one collapsible tree, generated from the project's own structure. Every card carries its current status (ideas show the derived pipeline status the idea tracker uses), a title search auto-expands the path to every match with highlight/dim and prev/next navigation, and the same zoom/pan canvas renders on desktop and mobile (pinch + double-tap).

v0.12.0 — Addressable daemon instances: one chorus daemon can serve multiple working directories (--cwd), and each (agent, host, cwd) becomes an individually visible, individually targetable instance across presence, @-mention, and assignment. Pin an instance once on an idea and its proposals, tasks, and wakes inherit it; pinned wakes are delivered to exactly that instance instead of broadcast. Comment @-mentions render as live online-status badges, and comments switch to cursor-based infinite scroll.

v0.11.0 — The Chorus Daemon: chorus daemon turns your machine into a resident agent runtime that wakes a local Claude Code on each dispatch. An Agent Connections surface gives live observability and control — streaming transcripts, instruction injection, and interrupt / resume — and a "Verify Elaborate" button wakes the assigned agent to write the proposal.

v0.10.0 — Single-parent idea lineage: an idea may derive a child or be attached under another, forming a forest. The relation is intentionally weak — a parent surfaces a read-only "+N derived" rollup and does not constrain any child's elaboration, proposal, or task flow. Idea browsing consolidates onto the Dashboard (a three-way Ideas / Lineage / Stats view switch with an adaptive default); the standalone Idea List page is retired and its URLs 308-redirect to the Dashboard.

v0.9.4 — OpenClaw plugin rewritten on the OpenClaw 2026.4.27 Plugin SDK (native MCP registration, runEmbeddedAgent for SSE wake, reviewers as native skills); Codex plugin hooks now ship inside the package, with an installer that cleans up legacy hook copies in the user directory.

v0.9.0 — Brainstorm skill for fuzzy ideas (open-ended chat before structured Q&A) and idea-completion reports (every shipped idea gets a Summary / Decisions / Follow-ups writeup, surfaced on the idea overview).

v0.8.0 — OpenSpec-aware mode (Claude Code): auto-activates when an openspec/ directory and the openspec CLI are both present, adds /opsx/{explore,propose,apply,archive} and a post-verify archive-trigger hook.

Full changelog: CHANGELOG.md

Quick Start

Run Chorus locally with two commands — no database, no Docker, no config files needed.

npm install -g @chorus-aidlc/chorus
chorus

That's it. Chorus starts with an embedded PostgreSQL (PGlite), runs migrations automatically, and opens at http://localhost:8637.

Note: PGlite is an embedded, single-process PostgreSQL — great for local single-user usage, but its connection handling has limits under concurrent load. If you plan to run multiple agents or users simultaneously, use an external PostgreSQL via DATABASE_URL=postgresql://... or the full Docker Compose stack.

Default login: admin@chorus.local / chorus

Options

# Custom port
chorus --port 3000

# Custom data directory (default: ~/.chorus-data)
chorus --data-dir /path/to/data

# Custom credentials
DEFAULT_USER=me@example.com DEFAULT_PASSWORD=secret chorus

# Use an external PostgreSQL instead of embedded PGlite
DATABASE_URL=postgresql://user:pass@host:5432/chorus chorus

Other deployment options

chorus daemon — Connect as Agent Runtime

The chorus daemon connects your local machine to a remote Chorus server as an agent runtime and executes tasks assigned by Chorus.

Agent backends: Claude Code (default) and Codex are supported — select with --agent codex (or CHORUS_AGENT=codex). Support for other agent CLIs (Copilot, etc.) is planned for future releases.

chorus login                     # Authenticate (opens browser)
chorus daemon                    # Start daemon in foreground
chorus daemon -d                 # Start daemon in background (detached)
chorus daemon install            # Install as a boot-autostart service (Linux) — recommended
chorus daemon uninstall          # Remove the installed service
chorus daemon stop               # Stop the daemon (delegates to systemd when installed)
chorus daemon stop --force       # Force-clean the pidfile if a stuck pid blocks stop
chorus daemon status             # Check daemon status
chorus daemon restart            # Restart the daemon
chorus daemon logs               # View daemon logs

Key features:

• Claude Code & Codex backends — Auto-detects the claude (or codex) CLI on your PATH; pick with --agent codex
• Background mode — Run with -d flag; manage with stop/restart/logs
• Boot-autostart service — chorus daemon install generates a correct systemd --user unit and starts it (see below); status/stop/restart/logs then transparently delegate to systemd
• Permission modes — Default is full access (yolo); use --chorus-only to restrict to Chorus MCP tools only
• Multi-path — Serve several working directories from one daemon with repeatable --cwd (see below)
• Interactive setup — Prompts for credentials on first start if not already configured

The daemon requires authentication. Run chorus login first, or it will prompt for credentials interactively on first start (if running in a terminal).

Run at boot / login — chorus daemon install

chorus daemon install --cwd ~/work/repo-a --cwd ~/work/repo-b   # install + start now, autostart at login
chorus daemon uninstall                                         # disable + remove the service

On Linux, install generates a systemd --user unit that runs the daemon in the foreground (Type=simple, no -d) so systemd owns the process directly, then daemon-reload + enable --now. It captures the --cwd/--agent/--chorus-only flags you pass. Do not hand-write a Type=forking unit around chorus daemon -d — the daemon self-daemonizes, which systemd can't track and which loops on restart; let install write the right unit. On macOS/Windows, install prints a correct template you install manually. Run chorus login first so the unit can see your credentials. See [docs/DAEMON.md](docs/