Paca: AI Agents Join Your Scrum Board as Teammates

What Is Paca?

Paca is a self-hosted project management platform where AI agents and humans collaborate as equal teammates inside a Scrum team, according to the project’s GitHub repository. It is described as an AI-native, free, open-source alternative to Jira, Trello, ClickUp, and Monday. The platform is built for Scrum teams where humans and AI agents work on the same board, the same sprints, and the same goals.

Unlike traditional project management tools that treat AI as a chatbot add-on, Paca gives AI agents a seat at the table. They join sprint planning, pick up tasks from the board, write BDD specs, and adapt alongside humans in real time. Everything about Paca — its workflow, data model, and UI — is configurable and extendable via plugins.

How AI Agents Work as Teammates

In Paca, AI agents are assigned to sprints and appear on the Scrumban board alongside human teammates. They pick up tasks from the backlog and update their status in real time. Agents collaborate on BDD specs, helping product owners and business analysts write Gherkin scenarios. They also contribute to System Design Documents, keeping the architecture visible to the whole team.

The project’s documentation emphasizes that this is not automation but genuine collaboration, rooted in the Cynefin/Stacey framework’s recognition that complex domains require teams, not pipelines. Agents probe, sense, and respond to emerging complexity, just like a human would.

Why Small Businesses Should Care

For small businesses, Paca removes the manual work of coordinating disparate tools and constant status updates, letting the team focus on execution. The platform is self-hosted, meaning you own the data and control the workflow. It is also free forever — the project promises no paid tiers, no paywalled features, and no open-core bait-and-switch.

Paca is fully customizable via configuration files and plugins. Workflows, statuses, field definitions, board layouts, sprint rules, and agent behavior are all driven by project-level configuration files. No code is needed to adapt Paca to your team’s process. Plugins are compiled to WebAssembly for the backend and standard module bundles for the frontend, running in a sandboxed environment with a capability-based permission model.

The P-A-C-A Cycle and What’s New

Paca structures team collaboration around four phases that mirror both Scrum and the scientific method: Plan, Act, Check, Adapt. In the Plan phase, product owners, business analysts, and AI agents collaboratively refine the backlog. In Act, the sprint is live and agents pull tasks from the board. In Check, QA agents run automated verification. In Adapt, the team — human and AI — retrospects together.

Version 0.20.0 introduced Git integration, allowing agents to work on pull requests. Agents can be mentioned on pull/merge requests or issues, and they reply, push commits, review, and fix CI. Every action is attributed to a bot identity and bounded by least-privilege credentials. The update also added connections and linked repositories, task references, and a plugin marketplace where community plugins can be browsed and installed directly from the Paca UI.

Getting Started and Community Promise

Paca is 100% open-source under the Apache 2.0 license. The project is built by its contributors and for its users, with direction shaped in the open through issues, discussions, and pull requests. The project’s website, paca-ai.org, provides a getting started guide, MCP server documentation, and architecture details.

For small businesses, this means no vendor lock-in, no per-seat costs, and full control over your data and workflow. Paca promises to remain free and non-profit, with every feature available to everyone at no cost.

Takeaways

• Paca is a free, open-source project management tool where AI agents work as equal teammates on the same Scrum board as humans.
• It is self-hosted, fully customizable via configuration and plugins, and promises to remain free forever with no paid tiers.
• Small businesses can reduce manual coordination and focus on execution by letting AI agents pick up tasks, write specs, and update statuses in real time.