The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills. https://multica.ai
Find a file
Jiayuan Zhang 00af622d0f
Merge pull request #235 from multica-ai/agent/lambda/d99edc96
docs: rewrite README and add self-hosting guide
2026-03-31 17:56:10 +08:00
.github/workflows fix(ci): replace turbo commands with direct pnpm calls 2026-03-26 18:01:24 +08:00
apps/web Merge pull request #232 from multica-ai/fix/inbox-issue-detail-key 2026-03-31 17:17:41 +08:00
e2e fix: resolve merge conflicts with main, preserve PAT functionality 2026-03-26 17:19:24 +08:00
scripts Improve local CLI auth and skills UX 2026-03-27 18:32:56 +08:00
server Merge remote-tracking branch 'origin/main' into fix/s3-cleanup-on-delete 2026-03-31 16:49:32 +08:00
.env.example feat(web): support REMOTE_API_URL env for proxying to remote backend 2026-03-31 16:53:32 +08:00
.eslintcache merge: resolve conflicts with main 2026-03-31 16:25:20 +08:00
.gitignore fix(activity): address code review feedback and improve timeline UX 2026-03-29 00:21:46 +08:00
.goreleaser.yml chore: rename super-multica references to multica 2026-03-25 21:01:39 +08:00
.npmrc refactor: restructure to monorepo architecture 2026-02-10 18:00:23 +08:00
AGENTS.md refactor: decouple task lifecycle from issue status (#151) 2026-03-27 18:30:21 +08:00
CLAUDE.md docs: update CLAUDE.md with logging, CI, and CLI details 2026-03-27 12:33:38 +08:00
docker-compose.yml chore: rename super-multica references to multica 2026-03-25 21:01:39 +08:00
Dockerfile chore: add Dockerfile for Go backend 2026-03-30 15:41:42 +08:00
LOCAL_DEVELOPMENT.md fix(auth): enforce auth on daemon API routes (#224) 2026-03-31 16:13:58 +08:00
Makefile Improve local CLI auth and skills UX 2026-03-27 18:32:56 +08:00
package.json refactor: remove unused monorepo tooling 2026-03-26 17:57:11 +08:00
playwright.config.ts Add workspace management and isolated worktree environments 2026-03-23 18:12:11 +08:00
pnpm-lock.yaml merge: resolve conflicts with main (file upload support) 2026-03-31 16:07:45 +08:00
pnpm-workspace.yaml refactor: remove unused monorepo tooling 2026-03-26 17:57:11 +08:00
README.md docs: rewrite README for users and add self-hosting guide 2026-03-31 17:51:05 +08:00
SELF_HOSTING.md docs: rewrite README for users and add self-hosting guide 2026-03-31 17:51:05 +08:00
skills-lock.json feat: add Claude Code skills for UI/UX development 2026-03-27 00:40:16 +08:00

Multica

AI-native project management — like Linear, but with AI agents as first-class team members.

Multica lets you manage tasks and collaborate with AI agents the same way you work with human teammates. Agents can be assigned issues, post comments, update statuses, and execute work autonomously on your local machine.

Features

  • AI agents as teammates — assign issues to agents, mention them in comments, and let them do the work
  • Local agent runtime — agents run on your machine using Claude Code or Codex, with full access to your codebase
  • Real-time collaboration — WebSocket-powered live updates across the board
  • Multi-workspace — organize work across teams with workspace-level isolation
  • Familiar UX — if you've used Linear, you'll feel right at home

Getting Started

Use Multica Cloud

The fastest way to get started: app.multica.ai

Self-Host

Run Multica on your own infrastructure. See the Self-Hosting Guide for full instructions.

Quick start with Docker:

git clone https://github.com/multica-ai/multica.git
cd multica
cp .env.example .env
# Edit .env — at minimum, change JWT_SECRET

# Start PostgreSQL
docker compose up -d

# Build and run the backend
cd server && go run ./cmd/migrate up && cd ..
make start

CLI

The multica CLI connects your local machine to Multica — authenticate, manage workspaces, and run the agent daemon.

Install

brew tap multica-ai/tap
brew install multica-cli

Or build from source:

make build
cp server/bin/multica /usr/local/bin/multica

Connect Your Agent Runtime

# 1. Authenticate
multica login

# 2. Watch your workspace
multica workspace watch <workspace-id>

# 3. Start the local agent daemon
multica daemon start

The daemon auto-detects available agent CLIs (claude, codex) on your PATH. When an agent is assigned a task, the daemon creates an isolated environment, runs the agent, and reports results back.

Other Commands

multica workspace list        # List workspaces (watched ones marked with *)
multica agent list            # List agents in the current workspace
multica daemon status         # Show daemon status
multica version               # Show CLI version

Architecture

┌──────────────┐     ┌──────────────┐     ┌──────────────────┐
│   Next.js    │────>│  Go Backend  │────>│   PostgreSQL     │
│   Frontend   │<────│  (Chi + WS)  │<────│   (pgvector)     │
└──────────────┘     └──────┬───────┘     └──────────────────┘
                            │
                     ┌──────┴───────┐
                     │ Agent Daemon │  (runs on your machine)
                     │ Claude / Codex│
                     └──────────────┘
  • Frontend: Next.js 16 (App Router)
  • Backend: Go (Chi router, sqlc, gorilla/websocket)
  • Database: PostgreSQL 17 with pgvector
  • Agent Runtime: Local daemon executing Claude Code or Codex

Development

For contributors working on the Multica codebase, see the Local Development Guide.

Prerequisites

Quick Start

pnpm install
cp .env.example .env
make setup
make start

See LOCAL_DEVELOPMENT.md for the full development workflow, worktree support, testing, and troubleshooting.

License

See LICENSE for details.