Build, test, ship: Forge gives your coding assistant the method and the infrastructure. From idea to a production API on Cloudflare in minutes.
NewAgents that answer in seconds. And now, missions: hand over a job, come back, it's delivered.
Codex
Cursor
OpenCode
and any agent that can run a CLI
your ai coder
Codex, Cursor, OpenCode, OpenClaw, Hermes or your favourite assistant work just as well: the Forge skill and CLI give them the complete method.
Your assistant:
Output schema, custom tools, prompts, the best-suited model for each phase. Your assistant puts together a real precision instrument, not just a prompt.
It runs your test cases on the real infrastructure, reads the traces, fixes and retries until every case passes.
Once the bench is green, it publishes. Your agent is live on Cloudflare's global network, behind one URL and one API key.
Build your agents on the Claude Code plan
you already pay for.
The long crafting loops run on your subscription, not on platform credits.
Start for freemacOS · Linux · no credit card
our stance
Each of these deserves its own article, they are coming to the blog. Meanwhile, the documentation goes into detail.
the process
Scroll: the agent builds itself on the left, at the pace of your reading.
01
One command: magic-link sign-in, an agents/ folder created, kit and skills installed. Your AI agent now knows the whole cycle.
02
Your assistant (Claude Code here, but the skill is the same for Codex, Cursor or OpenCode) applies the built-in methodology: output schema first, declared tools, a golden set of test cases. In the end you review files.
you → claude code
“Create an agent that answers questions about our opening hours, with strict JSON output.”claude code
I created agents/opening-hours/ : agent.ts, prompt.md, output.schema.json and 5 golden cases. Pushing now and running the bench.03
The golden set runs on the real infrastructure, every run traced (tools, tokens, cost, latency). No production release without proof.
04
Each agent becomes an isolated worker with its own secrets, streamed from Cloudflare's global network. One URL, one API key, and it is live.
05
Every push freezes a complete version, with the prompt, the code and the config. Every run knows which one produced it. Compare, pin, restore in one command.
Execution traces, golden sets, versions, secrets: full details in the documentation.
new — missions
Your agents answer in seconds. Mission agents take their time: you hand them a job, they settle in, do it, check their own work — and hand you finished files.
“Analyse these forty customer reviews and bring me a summary.” One sentence is enough. The mission leaves with a budget you set and a time limit — never the other way round.
In an isolated workshop, under contract: spending stops dead at the cap, your documents are read at your place and never taken away, and an outage doesn't make it lose its thread — it picks up where it left off.
A report, a summary, a document: finished files, produced by an agent that checked its own work and tried again until it met your order.
A mission is forged like everything else: describe the job to your assistant, it prepares the agent — all that's left is to hand over the work.
trust
An agent platform touches your prompts, your data and your API keys. It has to earn its place.
Start on our discovery credit, then plug in your Vercel AI Gateway or OpenRouter key. It is only visible to the egress worker that calls your provider, the interface shows only its last four characters, and your provider bills you directly.
The binary that reads your files and carries your secrets will be released as open source: anyone can audit what leaves their machine. The control plane, deliberately thin, stays managed by us.
Your tool keys are set as Cloudflare secrets of the agent's worker (forge secret set), write-only: neither our database, nor the logs, nor the API can read them back. Sign-in by magic link with an anti-phishing code.
pricing
to evaluate properly, no credit card
5 active agents · 5,000 calls/month
1 seat · 7-day traces
Web search and integrations included
or €24.90/month with no commitment
20 active agents · 100,000 calls/month
3 seats · 30-day traces
Email support within 48 h
billed €1,490/year · or €149/month with no commitment
Unlimited agents · 1,000,000 calls/month
Unlimited seats · 12-month traces
Priority support within 1 business day
Language models are billed separately, with no markup from us: your own key, or prepaid credit deducted at the price we pay for each execution.
See full pricing →15 minutes flat
