Self-serve, on your own infra
You install and configure it yourself, on the GitHub, cloud, and infrastructure you already run. No managed black box, no data leaving your control.
// agentic & automation, on your infra
wrok.in is BytesBrains' home for installable AI agents. Configure them and install them on your own GitHub, cloud, and platforms — your infra, your data, your AI keys.
Self-serve · BYOK · You own infra & data
$ git commit -m "fix: auth race" @wrokin /pi review▍ ─ wrokin · code-review agent ✓ 14 files scanned ! 3 suggestions · 0 blocking model: your-provider/your-model
// 01 · what you get
You install and configure it yourself, on the GitHub, cloud, and infrastructure you already run. No managed black box, no data leaving your control.
Plug in your own LLM API keys and choose the model per role — Anthropic, OpenAI, Google, Mistral, DeepSeek, or OpenRouter. Switch anytime. We never sit between you and your provider.
Ships as products that drop into your stack: a GitHub App today, more integrations coming. Configure with a dashboard and a simple file in your repo.
Clear docs, sane defaults, transparent config. Built to set up in minutes and run on its own — not to keep you on a support thread.
// 02 · products
wrokin is the first. More agentic apps and integrations are landing on wrok.in over time.
wrokin
Install the GitHub App and wrokin deploys AI agents across your repositories. They work automatically when a PR or issue opens, or on demand when you call them. You bring the keys and pick the models; everything runs against your own provider account.
Under the hood, wrokin runs on the Pi agent — with BytesBrains' own workflows, context-gathering (Scout), and extra harnesses & guardrails layered on to make it more effective and safer.
@wrokin / /piversion: 1 agents: code-review: model: deepseek/deepseek-v4-pro issue-triage: model: anthropic/claude-opus-4-8 # your keys, your models, your repo
Chain agents into multi-step pipelines across your tools and repos.
Continuous dependency, secret, and config audits on your codebase.
Triage alerts, draft incident summaries, and suggest runbook steps.
Schedule and run extract-transform-load jobs on your own infrastructure.
Define your own roles and prompts; bring them to your stack.
// 03 · how it works
Add the product from GitHub to the repos or org you choose.
Add your own LLM API keys and assign a model per role.
Set defaults in the dashboard and commit a .wrokin/config.yml.
Agents trigger on PRs and issues, or on demand. Calls go through your provider — your data and spend stay yours.
// 04 · principles
Your code and LLM keys stay in your accounts. We're not in the data path.
Swap models or providers anytime. Uninstall cleanly. Nothing holds your stack hostage.
Flat monthly price, predictable. You pay your LLM provider directly — no markup, no metering games.
Designed to install, configure, and run without a sales call or a support queue.
// 05 · pricing
A flat monthly price for the product — you always pay your LLM provider directly for usage, with no markup or metering games.
FREE
$0
Open source & trying wrokin out
Your LLM keys. Your provider's bill.
InstallPRO
$19/mo
Solo developers
$190/yr (2 months free) · 14-day trial
Install on GitHubTEAM
$49/mo
Teams shipping together
$490/yr (2 months free) · 14-day trial
Install on GitHubBUSINESS
$199/mo
Orgs that live in pull requests
$1,990/yr (2 months free) · 14-day trial
Install on GitHubNeed SSO, custom roles, or a self-hosted runner? Enterprise — talk to us →
Install wrokin, bring your keys, and let the agents start working — on your infra, under your control.