Paca-AI/paca: AI-native, free, open-source alternative to Jira, Trello, ClickUp & Monday. Built for Scrum teams where humans and AI agents collaborate as equals — on the same board, the same sprints, the same goals. Self-hosted. Fully customizable via config and plugins. · GitHub

AI-native. Free. Light weight. open source.
Fully customizable alternative to Jira, Trello, ClickUp, and Monday.

Getting Started · MCP Server · Cloud Code Skills · Architecture · Contributions · Roadmap

Paka is one Self-Hosted Project Management Platform Where AI agents and humans collaborate within a Scrum Team as equal teammates – not like chatbots.

Jira gives you the backlog. ClickUp gives you automation. Monday gives you a dashboard. Paka gives your AI agents a seat at the table. They get involved in sprint planning, taking tasks off the board, writing BDD specifications, and optimizing with humans in real time.

Everything about Paca – its workflow, its data model, its UI – is Configurable and extendable via plugins.

This is the central insight behind Paka AI agents should participate in the Scrum processNot just generate outputs in isolation.

In Paka, the AI ​​agent:

• Are assigned to sprint and appear on the Scrumban board with human teammates
• pick up the task Update your status from backlog and in real time
• Collaborate on BDD specifications – Helping Product Owners and BAs write Gherkin scenarios
• Contribute to system design documents – Keeping the architecture visible to the entire team
• Investigate, Understand and Respond To emerging complexity, just like a human being

This is not automation. it is real cooperation – Inherent in the Cynefin/Stacey framework’s belief that complex domains require teams, not pipelines.

Paka ships as a small, concentrated core. Everything else is optional.

Configuration-driven: Workflows, statuses, field definitions, board layouts, sprint rules, and agent behavior are all driven by project-level configuration files. Paka requires no code to adapt to your team’s process.

Plugin System: Extend or replace any part of Paka through plugins. plugins have been compiled WebAssembly (WASM) For the backend (write in Go, Rust, AssemblyScript – anything with a WASM target) and standard module bundles for the frontend. Plugins run in a sandboxed environment with a capability-based permissions model; They declare exactly which host functions they require, and nothing more.

plugins/
├── backend/        # WASM modules — add custom routes, logic, data models
└── frontend/       # UI modules — add custom pages, board views, widgets

Browse and install community plugins directly plugin market Inside Paca UI – no command line required. Go Settings → Plugins → MarketplaceFind a plugin, and click to install.

For local development or custom plugins, you can also install from the file system:

./scripts/install-local-plugin.sh ./my-plugin --api-key <your-api-key>

The Paka Structures team collaborates in four phases that reflect both Scrum and the scientific method:

Plan  →  Act  →  Check  →  Adapt
  ↑                             |
  └─────────────────────────────┘

• In-app AI chat – Chat with AI agents at the project level to plan work, create or update epics, stories, tasks and documentation – all in plain English without leaving Paka

• Activity Vary and Undo – Each field change in the Activity pane now shows the before/after difference; One click reverts the change to its previous value

• integrated scrumban board – Humans and AI agents share the same real-time board; No separate “AI workspace”
• In-app AI chat – Chat with AI agents at the project level to plan work, create or update epics, stories, tasks and documents in simple English
• Activity Vary and Undo – See a visual difference for each field change in the Activity pane and undo any changes with a single click
• bdd support – Co-authored by Gherkin scenario editors, POs, BAs, and AI agents
• System Design Document (SDD) – Living architecture documents that contextually ground AI agents
• mcp server – Connect the cloud, custom agents or any MCP-compliant tool directly to Paka’s data layer
• cloud code skills — /paca slash command for cloud code; Manage tasks, documents and sprints in simple English without leaving your editor
• real time updates – socket.io delivery; Everyone watches the change happen
• OpenHand-powered agent – AI agents run on the OpenHands SDK; Each agent executes inside its own isolated sandbox container so your host environment is never affected
• WASM Plugin Sandbox – Expand the Paka safely; Plugins cannot escape their declared permissions
• self hosted – Runs on a single Docker compose command; Your data never leaves your infrastructure
• light weight by default – Minimal core, no feature bloat; Add only what your team really needs

Runs on any Linux server with Docker. No repository clone required.

curl -fsSL https://github.com/Paca-AI/paca/releases/latest/download/install.sh | bash

The script takes you through the configuration interactively and starts the full stack. open http://your-server-ip When this is over.

# 1. Create a directory and download the compose file
mkdir paca && cd paca
curl -fsSL https://github.com/Paca-AI/paca/releases/latest/download/docker-compose.yml -o docker-compose.yml
mkdir -p nginx
curl -fsSL https://github.com/Paca-AI/paca/releases/latest/download/gateway.conf -o nginx/gateway.conf

# 2. Create your environment file
cat > .env <<'EOF'
JWT_SECRET=
ADMIN_PASSWORD=
POSTGRES_PASSWORD=
AGENT_API_KEY=
INTERNAL_API_KEY=
ENCRYPTION_KEY=
PUBLIC_URL=http://localhost
EOF

# 3. Start the stack
docker compose --env-file .env up -d

open http://localhost – Login with admin And the password you set.

Customizing the Stack: Cut back on services you don’t need.

# External PostgreSQL (supply DATABASE_URL in .env)
docker compose --env-file .env up -d --scale postgres=0

# AWS S3 instead of MinIO (set STORAGE_PROVIDER=s3 in .env)
docker compose --env-file .env up -d --scale minio=0

# Without the AI agent (reduces resource usage)
docker compose --env-file .env up -d --scale ai-agent=0

# Clone the repository
git clone https://github.com/Paca-AI/paca.git && cd paca

# Start infrastructure dependencies (PostgreSQL + Valkey)
docker compose -f deploy/docker-compose.dev.yml up -d postgres valkey

# Or start the full dev stack in containers
docker compose -f deploy/docker-compose.dev.yml up -d

See docs/guides/local-development.md for running services on a host for active development.

Paca ships an MCP (Model Context Protocol) server that gives any compatible AI agent direct, structured access to your workspace – projects, tasks, sprints, documents, members, and more. No scraping, no custom APIs to wire up.

The server is published as @paca-ai/paca-mcp On npm. you run it along npx; Your MCP client takes care of the rest.

1. Open (or create) a Cloud Desktop configuration file:

   • Mac OS: : ~/Library/Application Support/Claude/claude_desktop_config.json
   • windows: : %APPDATA%\Claude\claude_desktop_config.json

2. add paca Entry:

{
  "mcpServers": {
    "paca": {
      "command": "npx",
      "args": ["-y", "@paca-ai/paca-mcp"],
      "env": {
        "PACA_API_KEY": "your-api-key-here",
        "PACA_API_URL": "http://localhost:8080"
      }
    }
  }
}

3. Restart Cloud Desktop. The cloud now has access to all Paka tools and can respond to requests like:
   • “List all active sprints in Project X”
   • “Create a task to implement OAuth and assign it to Sprint 3”
   • “Add a comment on Task #42 with my progress update”

Any client that speaks MCP works. Typical configuration:

{
  "name": "paca",
  "command": "npx",
  "args": ["-y", "@paca-ai/paca-mcp"],
  "env": {
    "PACA_API_KEY": "your-api-key-here",
    "PACA_API_URL": "http://your-paca-instance:8080"
  }
}

The server displays tools in these categories:

For complete reference and advanced configuration (agent-mode, plugin tools, programmatic usage), see docs/guides/mcp-server-setup.md.

If you use Cloud Code, install the Paka skill set and manage your entire Paka workspace through natural-language slash commands – without leaving your editor and creating local files. Reads your Paka documentation to understand the project before executing each command.

skills are defined skills/ Directory using the agent skills format – one subdirectory per skill, with each SKILL.md Which includes YAML frontmatter and directives. Install script removes frontmatter and writes body ~/.claude/commands/ For use as cloud code slash command.

Run this once in your terminal to install all skills globally:

curl -fsSL https://raw.githubusercontent.com/Paca-AI/paca/master/scripts/install-claude-skill.sh | bash

Then connect the Paca MCP server to the cloud code:

claude mcp add paca \
  --env PACA_API_KEY=<your-api-key> \
  --env PACA_API_URL=<your-paca-url> \
  -- npx -y @paca-ai/paca-mcp

run /paca-setup Inside the Cloud Code session for a guided interactive walkthrough instead.

For full setup options and command reference, see docs/guides/cloude-code-skill.md.

apps/web          React + TanStack Start + shadcn/ui — user interface
apps/mcp          @paca-ai/paca-mcp — MCP server for AI agent integration
services/api      Go + Gin — core business logic and REST API
services/realtime Node.js + Socket.IO — real-time event fan-out
services/ai-agent Python + FastAPI + OpenHands SDK — AI agent orchestration
apps/e2e          Playwright — end-to-end test suite

skills/           Agent Skills — /paca slash commands for Claude Code

PostgreSQL        Persistent store
Valkey            Cache + async event streams between services

See docs/architecture/overview.md for details.

This name is a pun on the Japanese word “Baka” (ばか) – “mindless.”

In the early days, when our AI assistants had hallucinations we jokingly called them “fools.” And creating a serious project management platform as a free, open-source alternative to a multi-billion-dollar tool might also seem a little silly.

But Paka is built from a conviction: Human-AI collaboration in a true Scrum team should be accessible to every team, everywhere – not locked behind a vendor’s pricing model. We think it’s worth being a little silly. 🦙🌸

distributed under Apache License 2.0. See license for details.