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.

What it solves

Paca is a self-hosted project management platform designed to treat AI agents as first-class teammates rather than peripheral chatbots. It replaces traditional tools like Jira or Trello by allowing AI agents to participate directly in the Scrum process—picking up tasks from a board, collaborating on BDD specs, and updating statuses in real time.

How it works

Paca uses a lightweight core that is highly configurable via project-level configuration files and extendable through a WASM-based plugin system. It integrates with the OpenHands SDK to run AI agents in isolated sandbox containers. To enable external AI interaction, it provides an MCP (Model Context Protocol) server and a set of "skills" (slash commands) for tools like Claude Code and Cursor, allowing agents to read and write to the Paca data layer directly.

Who it’s for

It is built for software development teams who want to move away from proprietary cloud-based project management and integrate AI agents directly into their agile workflows and Scrum teams.

Highlights

  • AI-Native Scrum: AI agents are assigned to sprints and appear on the Scrumban board alongside humans.
  • WASM Plugin System: Backend plugins are compiled to WebAssembly for safe, sandboxed extension of logic and data models.
  • Visual Automation Engine: An n8n-style graph builder for creating complex Trigger $\rightarrow$ Condition $\rightarrow$ Action workflows.
  • MCP Server: Direct, structured access for any MCP-compatible AI agent to manage projects, tasks, and sprints.
  • Self-Hosted: Deployable via Docker Compose or Kubernetes (Helm chart) for full data ownership.

Related

  • Dispatch
    Paca: An Open-Source, AI-Native Alternative to Jira

    Paca is a self-hosted, open-source project management platform designed for Scrum teams where AI agents and humans collaborate as equal teammates on a shared Scrumban board.

  • Project
    Agenta-AI/agenta

    An open-source workspace for building and running AI agents that can automate work through interactive chat or scheduled background tasks.

  • Project
    shibing624/agentica

    Agentica is an open‑source, Apache‑2.0‑licensed Python framework that lets you run LLM‑based agents locally. A single chat session becomes an autonomous agent that can call built‑in tools (search, file I/O, code execution, OCR, image generation), remember past work, and spawn sub‑agents or delegate whole tasks. It works via a CLI, a local web UI, a desktop app, and IM gateways (WeChat, Feishu, Telegram). Supports many model providers (OpenAI, DeepSeek, Claude, Ollama, etc.), offers async‑first APIs, safety guardrails, multimodal input, persistent memory, a markdown‑based skill system, and RAG integration. Install with `pip install -U agentica` (add `[gateway]` for the web UI) and configure an API key. Ideal for developers, researchers, and power users who want a self‑hosted “LLM OS” with collaborative multi‑agent capabilities.

  • Project
    proma-ai/Proma

    A local-first AI desktop workbench that integrates multi-model chat, autonomous agents with browser automation, and project-specific skills and MCP support.

  • Project
    trycua/cua

    An infrastructure suite for computer-use AI agents, providing background drivers, cross-OS sandboxes, and benchmarks for training and evaluation.