Put AI Agents on Your Scrum Board: Self-Host Paca for Free
Paca is an open-source Jira/Trello alternative built for teams where humans and AI agents plan, pick up work, write specs, and ship from the same Scrum board.
Paca is an open-source Jira/Trello alternative built for teams where humans and AI agents plan, pick up work, write specs, and ship from the same Scrum board.
1 warning(s) found across 3 checked link(s).
1 warning(s) found across 3 checked link(s).
Decision aid, not a safety guarantee.
What you get from it
Tool / App in Tools & Apps with the public original source Paca GitHub repository (github.com). The full contents continue directly below.
Useful for Tools & Apps, Tool / App, and adjacent workflows.
Open Paca GitHub repository first and validate new tools or prompts in a test setup.
Even when visible for free, quality and fit still depend on the original source and your setup.
1 warning(s) found across 3 checked link(s).
Read details
Paca is a self-hosted project management platform for teams that want AI agents to work inside the normal delivery loop instead of sitting beside it as chat widgets. It gives agents and humans the same board, sprint context, task flow, docs, and real-time updates.
Why this is worth saving
- AI agents can be assigned to sprints and appear on the Scrumban board with human teammates.
- The project includes MCP support, so compatible AI tools can access projects, tasks, sprints, documents, members, comments, attachments, and plugin tools through a structured interface.
- Teams can customize workflows, statuses, fields, board layouts, sprint rules, and agent behavior through configuration.
- Plugins extend the system with WASM backend modules and frontend modules, with capability-style permissions.
- It is Apache-2.0, self-hosted, and currently packaged with install assets through GitHub Releases.
Fast workflow
- Star or watch the repo so you can track the fast release pace.
- Spin it up in a disposable test environment first, not production.
- Connect one MCP-compatible assistant to a test project.
- Create a small sprint with low-risk tasks and ask the agent to update status through Paca instead of chat.
- Review the activity diff and task history before letting agents touch larger workstreams.
What to test first
| Area | What to check | Why it matters |
|---|---|---|
| MCP server | Project/task/sprint tool access | Determines whether your agent stack can use Paca as a real operating layer |
| Scrumban board | Human and agent task movement | Shows whether the workflow feels natural for mixed teams |
| Plugin model | WASM/backend and frontend extension paths | Useful if your team needs custom process logic |
| Deployment | Docker Compose and release assets | Confirms whether self-hosting fits your infrastructure |
| Security posture | API keys, sandboxed agents, permissions | Required before bringing real company data into the system |
Caveat
This is a young, fast-moving project. Treat it as promising infrastructure to evaluate, not a drop-in replacement for an enterprise Jira setup yet. Run a sandbox pilot, read the deployment files, and verify the MCP/API permission model against your own security requirements.
Source check
- GitHub repo confirms Apache-2.0 licensing, self-hosted positioning, MCP support, OpenHands-powered agents, WASM plugins, and current project stats.
- The official website confirms the product positioning: humans and AI agents working on one Scrum team.
- The latest GitHub release confirms active release packaging, including Docker Compose, gateway config, and install script assets.
Discussion
Share practical experience, questions, or warnings with the community.
Sign in to join the discussion and vote on comments.
Sign in