Pricing · Invite only
You bring GitHub, servers and LLM keys. We supply the rest: AI devs, review, CI. Your plan follows where your repositories live: Solo is $100 a month flat for one AI dev on a personal GitHub account, Enterprise is $1,000 / ai-dev / mo for repositories under a GitHub organisation, and open-source projects under your own name run free.
$100 / mo, flat, one AI dev
For a solo developer building products with the AI subscriptions they already pay for. One AI dev, on your own boxes, on repositories under your personal GitHub account.
One flat price, one AI dev, personal GitHub accounts only. An organisation buys Enterprise.
Request access$1,000 / ai-dev / mo
Full fleet: AI devs, review and self-hosted CI. Zero quotas. The tier for repositories owned by a GitHub organisation.
Organisations, zero quotas, 3 concurrent CI slots per AI dev
Request access$0 / mo (with limits)
Issue and PR handling and releases on the public repositories under your own GitHub name. developerz.ai orchestrates triage and releases; you bring the LLM key. Writing code takes AI devs on your own boxes, which come with Solo or Enterprise.
20 agent-hours a month (5 in your first), private repos need a paid seat
Request accessWe never resell tokens. BYOK is the only mode: your own key from Anthropic, OpenAI, Gemini, DeepSeek, Kimi, GLM, MiniMax and more, or any OpenAI-compatible endpoint, billed directly to you.
01Included
What the price covers, and the one thing it never does.
Human seats are free: invite your whole team. You only pay for AI dev spots, and every spot is a concurrency slot: parallel agents carry no surcharge.
Every AI dev spot includes 3 enrollable servers (3 spots → 9 servers). At most your spot count runs AI devs at once; the other boxes run your CI/CD, tests, and code review. No separate Blacksmith or CodeRabbit subscription needed.
Every AI dev seat includes 3 concurrent CI/CD slots: GitHub Actions jobs running in parallel on your own enrolled boxes. We only orchestrate them: the jobs run on your hardware and we keep their raw logs for 72 hours only.
BYOK: inference runs on the AI subscriptions you already pay for. We never resell tokens.
Lean by design: raw CI/CD and review logs are kept for 72 hours on our side, then deleted. Want them longer? Point your boxes at your own Postgres (we recommend pgbouncer or pgcat in front) and keep logs as long as you like. The audit trail of bot actions is separate: 90 days in our database, then archived before it is pruned.
02Assurances
Coding agents run on your own VMs: bring your own cloud or on-prem boxes (BYOVM). Full control over performance, latency, and where your code actually runs.
Your keys, your code, your infrastructure. BYOK inference and never-resold tokens. Your code is checked out and built on your boxes, not ours, and every action is audited.
Read the privacy policyProof
One feature, built two ways, with the method registered in public before either arm runs. The receipts publish on their own page and stay there.
03Questions
Yours. BYOK is the only mode: your own key from Anthropic, OpenAI, Gemini, DeepSeek, Kimi, GLM, MiniMax and more, or any OpenAI-compatible endpoint. We never resell tokens.
On Solo and Enterprise, yes, and it maintains it: your AI devs write the code on your own enrolled boxes, with your own keys, and developerz.ai orchestrates the work, reviews every pull request and gates the merge. An issue you hand to Copilot is written where GitHub runs Copilot. On OSS Free no AI dev writes code: it triages issues and cuts releases on your public repositories, on your key.
Yes. Every tool call and decision is logged. If it isn't logged, it didn't happen.
It never converses with another bot: no bot-on-bot loops. It waits for a CodeRabbit review to settle before acting, and it reviews, fixes and merges Dependabot and Renovate PRs through the merge gate when your policy covers them.
We expect software to be written faster than any team can review it. Bring your repos, your boxes and your keys. We bring the org that keeps up.
