Get This Tool
Paca
Pricing
- Model
- Free
Summary
Most project management tools treat AI as a sidebar — a chat widget that suggests things and then watches while you do the actual work. Paca puts agents on the board itself, assigned to sprints, pulling tasks, and posting status updates next to your human teammates.
Paca is a self-hosted, open-source Scrumban board where AI agents participate in the full sprint cycle alongside humans: planning BDD specs, picking up tasks, running QA verification, and feeding retrospective data into the next sprint. The P·A·C·A loop — Plan, Act, Check, Adapt — mirrors Scrum phases and gives agents structured context through living BDD scenarios and System Design Documents, so they aren't operating blind. An in-app chat converts plain-English instructions into real backlog items without tab-switching. Every change — from agents and humans alike — lands in a diff-based activity feed with one-click revert. The ceiling appears when your workflow departs from Scrum or Scrumban structure; teams running Kanban-only or highly custom processes will find the framework opinionated.
Bottom line: Paca earns its place on a Scrum team that wants agents doing real sprint work, not generating summaries — but teams whose process doesn't map to the P·A·C·A cycle will spend more time fighting the framework than shipping.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Agents appear as assigned teammates on the live Scrumban board and post real-time task updates, which means sprint visibility stays in one place instead of split between your board and a separate AI dashboard you have to manually reconcile.
- BDD scenarios and living System Design Documents anchor every agent's context to how the product actually works, so agents don't generate output that contradicts your existing architecture or acceptance criteria.
- One-click diff revert on every change — agent or human — means teams can let agents move at full speed without a separate approval bottleneck on every action, and roll back anything that lands wrong without hunting through logs.
- Self-hosted under Apache 2.0 with no per-seat cost, so data stays on your infrastructure and the tool stays off your SaaS budget regardless of team size.
- In-app project-level chat converts plain-English instructions directly into backlog items and docs without leaving the board, which means product managers without technical fluency can drive sprint planning alongside agents without a separate tool in the chain.
Cons
Sign in to edit- The P·A·C·A cycle is the structural backbone of the product, not an optional configuration — teams running Kanban-only flows, shape-up cycles, or heavily customized processes will find the sprint-phase assumptions surfacing constantly, and adapting the tool to a non-Scrum workflow means working against the grain of how agents are wired into the board.
- At v0.4.0, the plugin ecosystem and community extension library are early-stage; teams that need a mature integration surface — existing webhooks, third-party CI/CD hooks, or established plugin catalog — will hit gaps that require them to build rather than install, adding engineering overhead before they get to the actual agent work.
- Any team that needs auditable, manager-approved gates before agent changes affect the board — regulated industries, client-facing projects with contractual deliverable sign-off — will find the current revert-after-the-fact model insufficient; when the compliance requirement is approval before the change lands, not rollback after, teams in that situation will move to a tool with explicit pre-ship review steps built into the workflow.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- Linux (Docker), browser-based UI
- API Available
- Yes
- Self-Hosted
- Yes
- Last Updated
- 2026-06-14T22:17:18.500Z
Best For
Who it's for
- Scrum or Scrumban teams integrating AI agents as peers
- Organizations requiring self-hosted, customizable project management
- Teams using BDD and living documentation for agent context
- Developers connecting MCP-compatible agents or Claude Code
What it does well
- Collaborative sprint planning and execution with AI agents on the same board
- BDD scenario and System Design Document co-authoring by humans and agents
- Real-time task updates and verification by QA agents
- Plain-English project management via in-app chat
- Self-hosted project tracking with full data ownership and plugin extensibility
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare Paca
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Recommended skills for this tool
Auto-curated by the AIDiveForge recommendation matrix. These skills are predicted to enhance this tool based on category, capability, and domain signals.
-
Meeting Summary Template transform 32%
Turn a raw transcript into a decision-focused recap: outcomes, owners, deadlines, open threads.
Why: category partial · caps 0/0 · domain ops
-
Standup Note Synthesizer transform 32%
Merge individual standup bullets from multiple people into a single team digest with blockers surfaced to the top.
Why: category partial · caps 0/0 · domain ops
-
Runbook Skeleton post 32%
Produce a first-draft runbook from a postmortem — detection, diagnosis, mitigation, rollback — so the next incident has a template to follow.
Why: category partial · caps 0/0 · domain ops
-
OKR Draft Critiquer post 32%
Score draft OKRs against SMART criteria and the outcome-not-output rule, with suggested rewrites for each failing key result.
Why: category partial · caps 0/0 · domain ops
Frequently Asked Questions
- Is Paca free?
- Yes — Paca is fully free to use. There is no paid tier.
- Is Paca open source?
- Yes. Paca is open source.
- Does Paca have an API?
- Yes. Paca exposes a developer API. See the official documentation at https://paca-ai.org for details.
- Can I self-host Paca?
- Yes. Paca supports self-hosting on your own infrastructure.
- What platforms does Paca support?
- Paca is available on: Linux (Docker), browser-based UI.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Paca is a self-hosted project management board designed around one premise: AI agents should be assigned to sprints and pull tasks the same way human teammates do. The core workflow follows the P·A·C·A cycle — Plan (POs and agents co-author BDD scenarios and System Design Documents before code is written), Act (humans and agents pull from the same live board), Check (QA agents run automated verification while humans review agent output), and Adapt (sprint data feeds the next planning cycle). The vendor states the tool is free, self-hosted, and Apache 2.0 licensed, with no per-seat cost. An in-app AI chat at the project level lets anyone create or update epics, stories, tasks, and docs in plain English — no copy-paste between tabs.
The differentiating feature is how Paca grounds agents in context. Rather than giving agents a raw prompt and hoping for coherent output, the platform anchors every agent to living BDD scenarios and System Design Documents — specifications the team maintains as the product evolves. The vendor frames this in terms of the Cynefin framework: complex work demands teams that can probe, sense, and respond to emerging conditions mid-sprint, which rigid pipeline tools can’t accommodate. Agents aren’t running in a separate AI workspace; they appear on the Scrumban board, are assigned to tasks, and post real-time updates that every teammate — human or agent — sees immediately.
Paca fits Scrum or Scrumban teams that want agents treated as peers rather than automation sidecars, and organizations that need full data ownership through self-hosting. It fits less well for teams running process structures outside of Scrum — the P·A·C·A cycle is the framework, not a configurable option. At v0.4.0, the product is early-stage; teams with mature, complex workflows should expect gaps and the community-contribution trade-offs that come with an open-source project still finding its edges.
The docs describe MCP-compatible agent connections and explicit support for Claude Code, giving developers a defined integration surface. The plugin extensibility model allows teams to extend the platform, though the community ecosystem around those plugins is nascent. The activity feed logs every change with a before/after diff, and the revert function applies to human edits as well as agent actions — which matters operationally when agents move fast and mistakes need unwinding without ceremony.