Run repeatable AI workflows
on your machine.
Contenox turns prompts into versioned chains: explicit steps, model routing, tool permissions, retries, human approval, and local execution. Keep the workflow in a file you can edit, review, and run with the model or provider that fits the job.
Installs contenox. Run contenox init to scaffold a workspace.
What you can author
Repeatable work, with policy in the file.
- →Release evidence pack: feed in git history, PRs, ticket notes, and CI output; the chain drafts the changelog, risk notes, and deployment checklist, then stops before publishing.
- →API-to-workflow wrapper: register a narrow OpenAPI subset, inject hidden tenant or environment arguments, and require approval for mutating calls.
- →Repo maintenance chain: inspect an issue, plan the patch, touch only approved files, run tests, and prepare a review packet instead of silently changing the project.
- →Browser QA evidence: Playwright captures the live app state, the chain writes documentation or screenshots, and the policy decides what needs human approval.
Run it where work happens
The same chain can run in your editor, terminal, or automation.
Contenox speaks the Agent Client Protocol over stdio. Use Zed, JetBrains, or AionUi when an editor UI helps; keep the workflow itself in the chain file, with tool calls and HITL approvals routed through the client.
// ~/.config/zed/settings.json
{
"agent_servers": {
"Contenox": {
"type": "custom",
"command": "contenox",
"args": ["acp"]
}
}
}Bring one recurring workflow. We'll package it as a reviewable Contenox chain.
Private pilots include workflow packaging, internal API integration, and early Contenox Teams work for shared knowledge and operated deployments.
Request a workflow review