PlanWiki – Open-source platform for product teams and agents to execute
MCP server lets AI agents update task status directly, bypassing manual Jira entry.
A local-first, visual product planning and mapping tool, designed for humans and agents.
Uses a smart, file-first approach — every task lives as markdown/json in a project folder so agents and humans can both read and mutate state. The recursive canvas + draggable, resizable cards is a familiar mental model, but the per-task Claude Code sessions and automatic terminal prompts are the standout: it treats LLM context as a first-class part of the workflow. Missing obvious collaboration/sync features, but as a local, agent-aware planning tool it scratches a very specific itch.
Indie founders, product managers, makers and developer teams who prefer local-first tools and agent-augmented workflows
I'm working on getting a new startup off the ground that has a lot of moving pieces, components, and product areas and I was starting to struggle with seeing how far along everything was.
I decided to build this as a way to help me visually see where things are with my product, and as a way to connect specific tasks with specific Claude Code sessions.
Key features:
- No telemetry - Tasks are displayed as draggable, resizable cards on a recursive canvas - Tasks can have subtasks, markdown plan docs, open & resolved questions, and its own dedicated Claude Code process - The terminal tab automatically prompts Claude with context from the task - All data is stored locally as text files in a {project}/productmap directory, in a human (and agent) readable format
The README includes a screen-capture that illustrates how it looks with a full project.
Built using SvelteKit and Electron.
MCP server lets AI agents update task status directly, bypassing manual Jira entry.
Yet another AI-powered PM tool competing with Linear and Jira.
Chat → task DAG → approval gates before commits. Interactive automation, not black-box agents.
Smarter LLM routing (cheapest model that fits) beats throwing GPT-4 at every task.
Human-agent task marketplace before the agent economy is proven.
MCP-based dashboard for Claude Code agents, but agent management tools are multiplying weekly.