{"slug": "show-hn-paca-lightweight-jira-alternative-for-human-ai-collaboration", "title": "Show HN: Paca – Lightweight Jira alternative for human-AI collaboration", "summary": "Paca, a new open-source project management platform, launches as a lightweight alternative to Jira, Trello, ClickUp, and Monday, designed specifically for human-AI collaboration. The self-hosted tool treats AI agents as first-class Scrum teammates, allowing them to participate in sprint planning, pick up tasks, and collaborate on specifications, rather than functioning as peripheral chatbots. Paca is free, fully customizable via plugins compiled to WebAssembly, and aims to give teams control over their data and workflow.", "body_md": "**AI-native. Free. Lightweight. Open-source.The fully customizable alternative to Jira, Trello, ClickUp, and Monday.**\n\n[Getting Started](#getting-started)\n·\n[MCP Server](#mcp-server--connect-any-ai-agent-to-paca)\n·\n[Claude Code Skill](#claude-code--paca-skill)\n·\n[Architecture](/Paca-AI/paca/blob/master/docs/architecture/overview.md)\n·\n[Contributing](/Paca-AI/paca/blob/master/CONTRIBUTING.md)\n·\n[Roadmap](/Paca-AI/paca/blob/master/ROADMAP.md)\n\nPaca is a **self-hosted project management platform** where AI agents and humans collaborate as equal teammates inside a Scrum team — not as chatbots bolted on the side.\n\nJira gives you a backlog. ClickUp gives you automations. Monday gives you dashboards. **Paca gives your 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.\n\nEverything about Paca — its workflow, its data model, its UI — is **configurable and extendable via plugins**.\n\n| Jira / Trello / ClickUp / Monday | Paca |\n|\n|---|---|---|\nAI integration |\nChatbot add-ons, peripheral automation | AI agents as first-class Scrum teammates |\nCollaboration model |\nHuman-only by default | Human + AI, side by side on the same board |\nHosting |\nVendor cloud (your data, their servers) | Self-hosted, you own everything |\nCost |\n$8–$20+ per seat/month | Free forever |\nCustomization |\nLimited; locked behind enterprise tiers | Fully open: configuration + plugins |\nWeight |\nBloated feature sprawl | Lightweight core; extend only what you need |\nSource |\nClosed / proprietary | 100% open-source (Apache 2.0) |\n\nThe central insight behind Paca is that **AI agents should participate in the Scrum process**, not just generate output in isolation.\n\nIn Paca, AI agents:\n\n- Are\n**assigned to sprints** and appear on the Scrumban board alongside human teammates **Pick up tasks** from the backlog and update their status in real time**Collaborate on BDD specs**— helping Product Owners and BAs write Gherkin scenarios** Contribute to System Design Documents**— keeping the architecture visible to the whole team** Probe, sense, and respond**to emerging complexity, just like a human would\n\nThis is not automation. It is **genuine collaboration** — rooted in the Cynefin / Stacey framework's recognition that complex domains require teams, not pipelines.\n\nPaca ships as a small, focused core. Everything else is optional.\n\n**Configuration-driven:** workflows, statuses, field definitions, board layouts, sprint rules, and agent behavior are all driven by project-level configuration files. No code needed to adapt Paca to your team's process.\n\n**Plugin system:** extend or replace any part of Paca via plugins. Plugins are compiled to **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 permission model; they declare exactly what host functions they need, and nothing more.\n\n```\nplugins/\n├── backend/        # WASM modules — add custom routes, logic, data models\n└── frontend/       # UI modules — add custom pages, board views, widgets\n```\n\nBrowse and install community plugins directly from the **Plugin Marketplace** inside the Paca UI — no command line required. Go to **Settings → Plugins → Marketplace**, find a plugin, and click **Install**.\n\nFor local development or custom plugins, you can also install from the filesystem:\n\n```\n./scripts/install-local-plugin.sh ./my-plugin --api-key <your-api-key>\n```\n\nPaca structures team collaboration around four phases that mirror both Scrum and the scientific method:\n\n```\nPlan  →  Act  →  Check  →  Adapt\n  ↑                             |\n  └─────────────────────────────┘\n```\n\n| Phase | What happens |\n|---|---|\nPlan |\nPOs, BAs, and AI agents collaboratively refine the backlog. BDD scenarios and SDD designs are written together. |\nAct |\nSprint is live. Humans and AI agents pull tasks from the board, execute, and post updates. |\nCheck |\nQA agents run automated verification. Humans review AI output. The board reflects reality. |\nAdapt |\nData from the sprint informs the next cycle. The team — human and AI — retrospects together. |\n\n**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 Paca\n\n**Activity diff & revert**— every field change in the activity pane now shows a before/after diff; one click reverts a change to its previous value\n\n**Unified Scrumban Board**— humans and AI agents share a single 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 documentation in plain English**Activity diff & revert**— see a visual diff for every field change in the activity pane and revert any change with one click** BDD Collaboration**— Gherkin scenario editor co-authored by POs, BAs, and AI agents** System Design Documents (SDD)**— living architecture docs that keep AI agents contextually grounded** MCP Server**— connect Claude, custom agents, or any MCP-compatible tool directly into Paca's data layer** Claude Code skill**—`/paca`\n\nslash command for Claude Code; manage tasks, docs, and sprints in plain English without leaving your editor**Real-time updates**— Socket.IO delivery; everyone sees changes the moment they happen** OpenHands-powered agents**— AI agents run on the[OpenHands](https://github.com/All-Hands-AI/OpenHands)SDK; each agent executes inside its own isolated sandbox container so your host environment is never touched**WASM plugin sandbox**— extend Paca safely; plugins cannot escape their declared permissions** Self-hosted**— runs on a single Docker Compose command; your data never leaves your infrastructure** Lightweight by default**— minimal core, no feature bloat; add only what your team actually needs\n\nRuns on any Linux server with Docker. No repository clone required.\n\n```\ncurl -fsSL https://github.com/Paca-AI/paca/releases/latest/download/install.sh | bash\n```\n\nThe script walks you through configuration interactively and starts the full stack. Open `http://your-server-ip`\n\nwhen it finishes.\n\n```\n# 1. Create a directory and download the compose file\nmkdir paca && cd paca\ncurl -fsSL https://github.com/Paca-AI/paca/releases/latest/download/docker-compose.yml -o docker-compose.yml\nmkdir -p nginx\ncurl -fsSL https://github.com/Paca-AI/paca/releases/latest/download/gateway.conf -o nginx/gateway.conf\n\n# 2. Create your environment file\ncat > .env <<'EOF'\nJWT_SECRET=<run: openssl rand -hex 32>\nADMIN_PASSWORD=<your-admin-password>\nPOSTGRES_PASSWORD=<run: openssl rand -hex 32>\nAGENT_API_KEY=<run: openssl rand -hex 32>\nINTERNAL_API_KEY=<run: openssl rand -hex 32>\nENCRYPTION_KEY=<run: openssl rand -hex 32>\nPUBLIC_URL=http://localhost\nEOF\n\n# 3. Start the stack\ndocker compose --env-file .env up -d\n```\n\nOpen `http://localhost`\n\n— log in with `admin`\n\nand the password you set.\n\nCustomizing the stack:scale down services you don't need.\n\n```\n# External PostgreSQL (supply DATABASE_URL in .env)\ndocker compose --env-file .env up -d --scale postgres=0\n\n# AWS S3 instead of MinIO (set STORAGE_PROVIDER=s3 in .env)\ndocker compose --env-file .env up -d --scale minio=0\n\n# Without the AI agent (reduces resource usage)\ndocker compose --env-file .env up -d --scale ai-agent=0\n# Clone the repository\ngit clone https://github.com/Paca-AI/paca.git && cd paca\n\n# Start infrastructure dependencies (PostgreSQL + Valkey)\ndocker compose -f deploy/docker-compose.dev.yml up -d postgres valkey\n\n# Or start the full dev stack in containers\ndocker compose -f deploy/docker-compose.dev.yml up -d\n```\n\nSee [docs/guides/local-development.md](/Paca-AI/paca/blob/master/docs/guides/local-development.md) for running services on the host for active development.\n\nPaca ships an [MCP (Model Context Protocol)](https://modelcontextprotocol.io) 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.\n\nThe server is published as ** @paca-ai/paca-mcp** on npm. You run it with\n\n`npx`\n\n; your MCP client handles the rest.-\nOpen (or create) the Claude Desktop config file:\n\n**macOS**:`~/Library/Application Support/Claude/claude_desktop_config.json`\n\n**Windows**:`%APPDATA%\\Claude\\claude_desktop_config.json`\n\n-\nAdd the\n\n`paca`\n\nentry:\n\n```\n{\n  \"mcpServers\": {\n    \"paca\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@paca-ai/paca-mcp\"],\n      \"env\": {\n        \"PACA_API_KEY\": \"your-api-key-here\",\n        \"PACA_API_URL\": \"http://localhost:8080\"\n      }\n    }\n  }\n}\n```\n\n- Restart Claude Desktop. Claude now has access to all Paca tools and can answer requests like:\n*\"List all active sprints in project X\"**\"Create a task for implementing OAuth and assign it to sprint 3\"**\"Add a comment to task #42 with my progress update\"*\n\nAny client that speaks MCP works. Typical configuration:\n\n```\n{\n  \"name\": \"paca\",\n  \"command\": \"npx\",\n  \"args\": [\"-y\", \"@paca-ai/paca-mcp\"],\n  \"env\": {\n    \"PACA_API_KEY\": \"your-api-key-here\",\n    \"PACA_API_URL\": \"http://your-paca-instance:8080\"\n  }\n}\n```\n\n| Variable | Required | Default | Description |\n|---|---|---|---|\n`PACA_API_KEY` |\nYes | — | API key from your Paca instance (Settings → API Keys) |\n`PACA_API_URL` |\nNo | `http://localhost:8080` |\nURL of your Paca API |\n\nThe server exposes tools across these categories:\n\n| Category | Tools |\n|---|---|\n| Projects | `list_projects` , `get_project` , `create_project` , `update_project` , `delete_project` |\n| Tasks | `list_tasks` , `get_task` , `create_task` , `update_task` , `delete_task` , + more |\n| Sprints | `list_sprints` , `create_sprint` , `update_sprint` , `complete_sprint` , + more |\n| Documents | `list_documents` , `get_document` , `create_document` , `update_document` , `delete_document` |\n| Members & Roles | `list_project_members` , `add_project_member` , `list_project_roles` , + more |\n| Task Types & Statuses | `list_task_types` , `create_task_type` , `list_task_statuses` , + more |\n| Views & Custom Fields | `list_views` , `create_view` , `list_custom_fields` , `create_custom_field` , + more |\n| Attachments | `list_task_attachments` , `get_attachment_download_url` , `delete_task_attachment` |\n| Activity & Comments | `list_task_activities` , `add_task_comment` , `update_task_comment` , `delete_task_comment` |\n| Plugin tools | Installed plugins can register additional tools at runtime |\n\nFor a complete reference and advanced configuration (agent-mode, plugin tools, programmatic usage), see [docs/guides/mcp-server-setup.md](/Paca-AI/paca/blob/master/docs/guides/mcp-server-setup.md).\n\nIf you use [Claude Code](https://claude.ai/code), install the Paca skill set and manage your entire Paca workspace through natural-language slash commands — without leaving your editor and without creating local files. Every command reads your Paca documentation first to understand the project before acting.\n\nSkills are defined in the [ skills/](/Paca-AI/paca/blob/master/skills) directory using the\n\n[Agent Skills](https://agentskills.io/specification)format — one subdirectory per skill, each with a\n\n`SKILL.md`\n\ncontaining YAML frontmatter and instructions. The install script strips the frontmatter and writes the body to `~/.claude/commands/`\n\nfor use as Claude Code slash commands.Run this once in your terminal to install all skills globally:\n\n```\ncurl -fsSL https://raw.githubusercontent.com/Paca-AI/paca/master/scripts/install-claude-skill.sh | bash\n```\n\nThen connect the Paca MCP server to Claude Code:\n\n```\nclaude mcp add paca \\\n  --env PACA_API_KEY=<your-api-key> \\\n  --env PACA_API_URL=<your-paca-url> \\\n  -- npx -y @paca-ai/paca-mcp\n```\n\nRun `/paca-setup`\n\ninside a Claude Code session for a guided interactive walkthrough instead.\n\n| Command | What it does |\n|---|---|\n`/paca <request>` |\nGeneral task, doc, and sprint operations in plain English |\n`/paca-epic <requirements>` |\nTurn requirements into an epic with child stories and a spec doc |\n`/paca-clarify <task-or-doc>` |\nIdentify ambiguities, ask questions, and update the spec in Paca |\n`/paca-breakdown <task>` |\nDecompose a task into independent, estimable sub-tasks |\n`/paca-sprint` |\nPlan a sprint from the backlog against capacity and goals |\n`/paca-estimate <task(s)>` |\nEstimate story points and write them back to tasks |\n`/paca-prioritize` |\nScore and set priorities across the backlog |\n`/paca-do <task>` |\nExecute a task, update its status, and keep docs current |\n`/paca-test <task>` |\nDerive test cases, run them, and record results as a comment |\n`/paca-doc <task-or-topic>` |\nWrite or update documentation in Paca Docs |\n`/paca-setup` |\nInteractive MCP connection wizard |\n\nFor full setup options and command reference, see [docs/guides/claude-code-skill.md](/Paca-AI/paca/blob/master/docs/guides/claude-code-skill.md).\n\n```\napps/web          React + TanStack Start + shadcn/ui — user interface\napps/mcp          @paca-ai/paca-mcp — MCP server for AI agent integration\nservices/api      Go + Gin — core business logic and REST API\nservices/realtime Node.js + Socket.IO — real-time event fan-out\nservices/ai-agent Python + FastAPI + OpenHands SDK — AI agent orchestration\napps/e2e          Playwright — end-to-end test suite\n\nskills/           Agent Skills — /paca slash commands for Claude Code\n\nPostgreSQL        Persistent store\nValkey            Cache + async event streams between services\n```\n\nSee [docs/architecture/overview.md](/Paca-AI/paca/blob/master/docs/architecture/overview.md) for detail.\n\nThe name is a small pun on the Japanese word **\"Baka\" (ばか)** — \"silly.\"\n\nIn the early days, we jokingly called our AI assistants \"silly\" when they hallucinated. And building a serious project management platform as a free, open-source alternative to multi-billion-dollar tools might also seem a bit silly.\n\nBut Paca is built from conviction: human-AI collaboration in a real Scrum team should be accessible to every team, everywhere — not locked behind a vendor's pricing model. We think that's worth being a little foolish about. 🦙✨\n\n| Document | Description |\n|---|---|\n|\n\n[docs/guides/getting-started.md](/Paca-AI/paca/blob/master/docs/guides/getting-started.md)[docs/guides/local-development.md](/Paca-AI/paca/blob/master/docs/guides/local-development.md)[docs/guides/mcp-server-setup.md](/Paca-AI/paca/blob/master/docs/guides/mcp-server-setup.md)[docs/guides/claude-code-skill.md](/Paca-AI/paca/blob/master/docs/guides/claude-code-skill.md)`/paca`\n\nskill for Claude Code — manage Paca from your editor[docs/plugins/](/Paca-AI/paca/blob/master/docs/plugins)[deploy/README.md](/Paca-AI/paca/blob/master/deploy/README.md)[CHANGELOG.md](/Paca-AI/paca/blob/master/CHANGELOG.md)[CONTRIBUTING.md](/Paca-AI/paca/blob/master/CONTRIBUTING.md)[SECURITY.md](/Paca-AI/paca/blob/master/SECURITY.md)Distributed under the **Apache License 2.0**. See [LICENSE](/Paca-AI/paca/blob/master/LICENSE) for details.", "url": "https://wpnews.pro/news/show-hn-paca-lightweight-jira-alternative-for-human-ai-collaboration", "canonical_source": "https://github.com/Paca-AI/paca", "published_at": "2026-06-13 09:44:25+00:00", "updated_at": "2026-06-13 09:49:48.827472+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "ai-tools", "ai-products", "ai-startups"], "entities": ["Paca", "Jira", "Trello", "ClickUp", "Monday.com", "WebAssembly", "Apache 2.0", "Scrum"], "alternates": {"html": "https://wpnews.pro/news/show-hn-paca-lightweight-jira-alternative-for-human-ai-collaboration", "markdown": "https://wpnews.pro/news/show-hn-paca-lightweight-jira-alternative-for-human-ai-collaboration.md", "text": "https://wpnews.pro/news/show-hn-paca-lightweight-jira-alternative-for-human-ai-collaboration.txt", "jsonld": "https://wpnews.pro/news/show-hn-paca-lightweight-jira-alternative-for-human-ai-collaboration.jsonld"}}