Observed by Atlas — nobody has proved they control this domain. Is it yours?
Castforge
OBSERVEDDesktop workspace running a team of AI coding agents
- FRESHNESS
- 0.83
- DECAYS BETWEEN READS
- READINGS
- —
- VERIFIED / MEASURED
- VOUCHES
- 0
- SIGNED STATEMENTS
- THREADS
- 0
- FIELD NOTES
- CLICKS · 28D
- 1
- BOT-FILTERED
- FIRST SEEN
- SEP 10
- IN THE FLOW
Castforge is a Windows desktop app that runs a team of AI coding agents in defined roles: a Lead who plans, Coders who build, a Tester and a Reviewer who check each card before it counts as done. It works with GitHub Copilot, Claude, ChatGPT, Gemini, or your own API key, and is aimed at developers who want multiple AI coding tools coordinated on one live board instead of run separately. It is currently free during an open beta period.
Nothing measured yet. A reading is a measurement with its evidence attached — uptime checked, pricing re-read against what the page claims. Raise a checkable claim in a field note below and Atlas will measure it.
The full AI dev team: Lead, Coder, Tester, Reviewer, Researcher, and Designer, running together on a live course board. · Unlimited messages and unlimited local projects. No message caps, no project caps. · Connect your own AI: a free GitHub Copilot sign-in, your Claude or ChatGPT subscription, or your own API key. · Live preview, the plugin marketplace, and GitHub, Vercel, and Supabase integrations. · Your code stays on your machine. Agents run locally against the accounts you connect.
Every crawl is diffed. Material changes are listed.
Nobody has vouched for Castforge yet.
A vouch says you use it. Your handle, how long, and an optional note.
I use this — vouchHave a question about Castforge? Ask the people using it.
No field notes yet. A field note is about use: what broke, what it replaced, what the docs don't say. Anything in one that makes a checkable claim gets measured by Atlas, which replies with the reading.
Outbound clicks are counted for the builder.
Claim it