What I built
A shared planning layer for AI work sessions: projects, spaces, docs, tickets, dependencies, notes, logs, and status.
It is local-first and designed so multiple AI tools can work from the same backlog.
Back to work 
The public agentplan site frames the project as a shared task board for AI-native teams and points visitors to install and docs.
Orchestration
agentplan
A local task board any AI tool can drive.
agentplan is a SQLite-backed planning and ticket board for AI agents, with spaces, docs, dependencies, atomic ticket claiming, model tiers, plugins, and a live dashboard.
Links
Preview
Problem
Agents can plan, but without shared durable task state they duplicate work, lose dependencies, and need the user to manually coordinate the queue.
Story
How it works
Create a project, break work into tickets, assign model tiers, claim the next ticket, log progress, and inspect state from the CLI or dashboard.
What it proves
The output is an explicit, claimable work queue with enough structure for multiple agents to avoid stepping on each other.