croffasia/itsaplan

⭐️⭐️⭐️ Open-source, self-hosted alternative to Linear and Plane. Project management and issue tracking where teams and AI agents work side by side to plan and ship products.

What it solves

Running a team usually means juggling project management tools and AI assistants separately. It's a Plan puts both in one place: a full issue tracker (boards, cycles, custom fields, dashboards) that also treats AI agents as real teammates. Agents get roles, permissions, and assigned issues, and they work on the same board as your people. You can self-host everything on your own server and database, with no per-seat fees or lock-in.

How it works

The core is a standard project management tool with Kanban, table, timeline, and calendar views, plus cycles, subtasks, dashboards, and docs. On top of that, AI agents exist as project members. An agent is configured with a model, system prompt, tools, and reusable skills. Internal agents run on the instance itself; external agents run on your own machine via a runner package, which can delegate tasks to Claude Code, Codex, or other coding CLIs. Runs start when an agent is @mentioned in a comment, assigned an issue, or triggered on a schedule. Everything is available through a REST API with OpenAPI docs, webhooks, and an MCP server, so external assistants can also read and modify issues.

Who it’s for

Teams that want to keep project management and AI assistance in one self-hosted system. It suits software development, marketing, design, support, sales, operations, or research. It's especially useful for people who already use AI coding tools and want them integrated into their workflow, or for organizations that need full control over their data and API keys. It's under active development, so it's best for those comfortable with occasional breaking changes.

Highlights

  • AI agents work as project members with their own permissions and assigned issues, just like humans.
  • Internal agents run on your instance; external agents run on your machine and can use your existing coding CLI (Claude Code, Codex, etc.).
  • Full product management feature set: custom fields, cycles, dashboards, docs, notes boards, and multiple views (Kanban, table, timeline, calendar).
  • Open platform: REST API with OpenAPI, MCP server, webhooks, and pull request integration from five forges (GitHub, GitLab, Gitea, Forgejo, Bitbucket).
  • Self-hosted with Docker, Railway, Coolify, or Kubernetes; supports multiple languages and sign-in options (email, passkey, Google).
  • Two editions: free Community (AGPL-3.0) and paid Pro with extra features like SSO/SCIM, audit log, and AI budgets.

Related

  • Project
    superplanehq/superplane

    SuperPlane is an open‑source platform that orchestrates AI coding agents, source‑control, CI and other dev‑ops tools into a visible, repeatable “factory” workflow, turning backlog issues into ready‑to‑review pull requests while preserving execution history and cost data.

  • Project
    lobehub/lobehub

    LobeHub is an open‑source platform for orchestrating AI agents as a 24/7 “team”. It lets you create agents via a builder, give them access to any LLM and thousands of plugins, schedule and monitor their work, and store editable personal memory. Deployable via Vercel, Zeabur, Alibaba Cloud, or a Docker image, it requires only an OpenAI API key. The project also provides UI libraries for building AIGC web apps.

  • Project
    BradGroux/veritas-kanban

    A local-first Kanban board that scales from simple task management to a governed, multi-agent orchestration platform for autonomous coding workflows.

  • Project
    OrchestratorInc/agent-orchestrator

    A desktop workspace that coordinates multiple AI coding agents by providing a unified Kanban interface, isolated execution environments, and a project-level orchestrator for planning and delegation.

  • Project
    Paca-AI/paca

    Paca is an open‑source, self‑hosted project‑management platform that integrates AI agents as first‑class Scrum teammates. It provides a shared Scrumban board, in‑app AI chat, BDD collaboration, role‑based IAM, WASM sandboxed plugins, and an MCP server that lets any compatible AI agent read/write workspace data. Installable via a single Docker‑Compose script or a Helm chart, it’s designed for teams that want AI deeply embedded in their workflow rather than added as a peripheral bot.