Skip to content

IterionThe control plane for AI agents.

Apps have Linux. The cloud has Kubernetes. AI agents have Iterion. Define agent workflows as readable .bot files and operate every run — locally, in CI, or across a multi-tenant cloud.

Iterion logo

✨ See it

A .bot is a readable graph. Here's a plan → implement → review loop that keeps fixing until a judge approves — declarative, versioned, re-runnable:

iter
schema verdict:
  approved: bool
  notes: string

agent plan:
  system: "Turn the request into a concrete plan: files, steps, constraints."

agent implement:
  backend: "claude_code"
  system: "Implement the plan, then run the tests."

judge review:
  output: verdict
  system: "Approve only if the change is complete and the tests pass."

workflow ship_it:
  entry: plan
  plan -> implement -> review
  review -> implement as fix(3) when not approved
  review -> done when approved

… which compiles to this graph and runs it — in parallel where it can, with budgets, sandboxing, and checkpoints:

Design it on the canvas or edit the source — both stay in sync in the visual studio:

The Iterion studio — visual workflow editor with live diagnostics and a per-node inspector

⚙️ How a run works

Launch from anywhere; the same compiled graph runs the same way — scheduled in parallel, bounded by budgets, isolated in a sandbox, and checkpointed so it can resume:

💡 What teams build with it

Iterion ships a maintained fleet of 25+ production bots — real, grounded examples of what an operated agent workflow looks like. A few of the jobs they do:

Use caseBots that run it
🚀Ship software from a prompt — greenfield apps and end-to-end featuresAppy · Featurly · Fini · Bmady
🔁Continuously review & improve a codebase — whole-repo and per-branch campaigns, mono-default PR review with optional cross-family confirmation, test coverageWilly · Billy · Revi · Testy
🛡️Automated security & supply chain — SAST, dependency/SCA, diff-scoped CVE & malware shields on every PRSeki · Depsy · Vulny · Shieldy
⬆️Upgrade dependencies safely — multi-stack agentic upgrades with a review gateRenovacy · Vetty
📚Keep docs & knowledge aligned — docs alignment, wiki generation, ADR cartographyDoki · Wikky · Adry
Accessibility audits — RGAA 4.1.2 over deterministic gatesAcci
🗂️Triage & route work — classify board cards, auto-open PRs, answer PR questionsTriagy · Revi
📡Watch & react — feed/veille monitoring and digestsVigie
🧭A strategic partner — a conversational co-CTO and roadmap, an architectural visionaryNexie · Evoly

Browse the full catalogue →

🧰 A catalogue you run — or make your own

Run any bot as-is, fork and adapt one to your repo, or author your own from scratch — in the visual studio builder, with iterion bots create, or by hand in the readable .bot DSL. Package it as a .botz bundle and share it through the marketplace. The same workflow runs unchanged from your laptop to CI to the cloud.

🏗️ Built for real engineering

  • 🔗 Forge-native — GitHub, GitLab & Forgejo: open and review PRs, answer PR/MR comments, trigger on webhooks, triage issues, and post results back. → Forge integrations
  • 🔐 Secrets, done right — a sealed local & cloud secret store, bring-your-own provider keys, per-run sealed bundles, egress-scoped file secrets — never printed, materialised only at execution sinks. → Secrets
  • 🧱 Safe by default — per-run Docker/K8s sandboxes, a tool-permission gate against prompt injection, shared budget caps, and worktree isolation with an explicit merge policy. → Sandbox
  • Event-driven — an issue-tracker dispatcher, cron schedules, and a trigger spine over webhooks, board events, and run-completion chains.
  • 👁️ Operable — steer live runs, attach supervisors that watch and correct an agent, async human gates, checkpoint/resume, and Prometheus/OTLP/Grafana observability.
  • ☁️ Team scale — orgs & teams, quotas, audit, SSO, PATs, and a remote CLI — the same engine from laptop to multi-tenant cloud.

New here? Start with Why Iterion? for the vision, jump straight to Install, or explore the bot fleet.