GoKawiilAn issue tracker and wiki your AI coding agent runs as a first-class client - agent-native like a git tracker, deployed and cross-project like Jira, on a single Cloudflare Worker.
Agents drive it Filing issues, moving tickets, planning sprints, searching the wiki - an agent does it all over MCP, instead of asking you to. The MCP server is the primary surface, not a bolt-on. Fills the gap Agent-native like a git-file tracker, but deployed and cross-project like Jira - and cheap to self-host. When you outgrow it, you swap the database, not the tool. Built for fleets An agent registry, file claims, and coordination messages let many agents work the same repo in parallel without colliding. Runs on the edge One Cloudflare Worker: Hono, D1 for data, KV for cache, R2 for attachments. No servers, no containers. Deploy to your own account in minutes.
Deploy to your own Cloudflare account from a config-only repo - wrangler auto-provisions D1, KV, and R2, applies migrations, and ships. One button, one command, or hand the repo to an agent and say “deploy projektor to my Cloudflare account.”
Self-hosting guide → · Why Projektor looks like this →
Projektor’s own roadmap is tracked inside Projektor; these docs are generated from the same repo.