Workflow orchestration for AI coding agents — from ticket to merged PR, and beyond.
Optio orchestrates AI coding agents across three modes:
- Tasks — turn tickets into merged pull requests. Submit a task (manually, from a GitHub Issue, Linear, Jira, or Notion), and Optio provisions an isolated environment, runs an AI agent, opens a PR, monitors CI, triggers code review, auto-fixes failures, and merges when everything passes.
- Agent Workflows — run reusable, parameterized agent jobs on a schedule, via webhook, or on demand. Generate reports, triage alerts, audit dependencies — anything that doesn't need a repo checkout.
- Connections — give your agents access to external services. Connect Notion, Slack, Linear, GitHub, PostgreSQL, Sentry, or any MCP-compatible server, and Optio injects them into agent pods at runtime.
The feedback loop is what makes tasks different. When CI fails, the agent is automatically resumed with the failure context. When a reviewer requests changes, the agent picks up the review comments and pushes a fix. When everything passes, the PR is squash-merged and the issue is closed. You describe the work; Optio drives it to completion.
Dashboard — real-time overview of running agents, pod status, costs, and recent activity
Task detail — live-streamed agent output with pipeline progress, PR tracking, and cost breakdown
You create a task Optio runs the agent Optio closes the loop
───────────────── ────────────────────── ──────────────────────
GitHub Issue Provision repo pod CI fails?
Manual task ──→ Create git worktree ──→ → Resume agent with failure context
Linear / Jira / Notion Run Claude / Codex / Copilot Review requests changes?
Open a PR → Resume agent with feedback
CI passes + approved?
→ Squash-merge + close issue
- Intake — tasks come from the web UI, GitHub Issues (one-click assign), Linear, Jira, or Notion
- Provisioning — Optio finds or creates a Kubernetes pod for the repo, creates a git worktree for isolation
- Execution — the AI agent (Claude Code, OpenAI Codex, or GitHub Copilot) runs with your configured prompt, model, and settings
- PR lifecycle — Optio polls the PR every 30s for CI status, review state, and merge readiness
- Feedback loop — CI failures, merge conflicts, and review feedback automatically resume the agent with context
- Completion — PR is squash-merged, linked issues are closed, costs are recorded
You define a workflow Optio triggers it Optio runs & tracks
──────────────────── ───────────────── ───────────────────
Prompt template Manual (UI / API) Provision isolated pod
{{PARAM}} variables ──→ Cron schedule ──→ Execute agent with params
Agent + model config Webhook from external Stream logs in real time
Budget & retry limits service Track cost & token usage
Auto-retry on failure
Workflows are standalone agent executions — no git repo required. Define a prompt template with {{PARAM}} placeholders, configure triggers (manual, cron schedule, or webhook), and let Optio handle execution, retries, and cost tracking.
Connections give your agents access to external tools and data at runtime. Configure a provider once, assign it to repos or agents, and Optio injects MCP servers into agent pods automatically.
Built-in providers: Notion, GitHub, Slack, Linear, PostgreSQL, Sentry, Filesystem, plus custom MCP servers and HTTP APIs.
- Autonomous feedback loop — auto-resumes the agent on CI failures, merge conflicts, and review feedback; auto-merges when everything passes
- Agent Workflows — reusable, parameterized agent jobs triggered manually, on a cron schedule, or via webhook, with real-time log streaming, cost tracking, and auto-retry
- Connections — plug external services (Notion, Slack, Linear, GitHub, PostgreSQL, Sentry, custom MCP servers) into agent pods with fine-grained access control per repo and agent type
- Pod-per-repo architecture — one long-lived Kubernetes pod per repo with git worktree isolation, multi-pod scaling, and idle cleanup
- Code review agent — automatically launches a review agent as a subtask, with a separate prompt and model
- Multi-agent support — run Claude Code, OpenAI Codex, GitHub Copilot, Google Gemini, or OpenCode with per-repo model and prompt configuration
- GitHub Issues, Linear, Jira, and Notion intake — assign issues to Optio from the UI or via ticket sync
- Real-time dashboard — live log streaming, pipeline progress, cost analytics, and cluster health
┌──────────────┐ ┌────────────────────┐ ┌───────────────────────────┐
│ Web UI │────→│ API Server │────→│ Kubernetes │
│ Next.js │ │ Fastify │ │ │
│ :3100 │ │ │ │ ┌── Repo Pod A ───────┐ │
│ │←ws──│ Workers: │ │ │ clone + sleep │ │
│ Dashboard │ │ ├─ Task Queue │ │ │ ├─ worktree 1 ⚡ │ │
│ Tasks │ │ ├─ PR Watcher │ │ │ ├─ worktree 2 ⚡ │ │
│ Repos │ │ ├─ Workflow Queue │ │ │ └─ worktree N ⚡ │ │
│ Workflows │ │ ├─ Health Mon │ │ └─────────────────────┘ │
│ Connections │ │ └─ Ticket Sync │ │ ┌── Workflow Pod ──────┐ │
│ Cluster │ │ │ │ │ isolated agent ⚡ │ │
│ Costs │ │ Services: │ │ └─────────────────────┘ │
│ │ │ ├─ Repo Pool │ │ │
│ │ │ ├─ Workflow Pool │ │ MCP servers injected via │
│ │ │ ├─ Connections │ │ Connections at runtime │
│ │ │ ├─ Review Agent │ │ │
│ │ │ └─ Auth/Secrets │ │ │
└──────────────┘ └─────────┬──────────┘ └───────────────────────────┘
│ ⚡ = Claude / Codex / Copilot / Gemini
┌──────┴──────┐
│ Postgres │ Tasks, workflows, connections, logs, secrets
│ Redis │ Job queue, pub/sub, live streaming
└─────────────┘
┌──────────────────────────────────────────────────┐
│ INTAKE │
│ │
│ GitHub Issue ───→ ┌──────────┐ │
│ Manual Task ───→ │ QUEUED │ │
│ Ticket Sync ───→ └────┬─────┘ │
└───────────────────────────┼──────────────────────┘
│
┌───────────────────────────┼──────────────────────┐
│ EXECUTION ▼ │
│ │
│ ┌──────────────┐ ┌─────────────────┐ │
│ │ PROVISIONING │───→│ RUNNING │ │
│ │ get/create │ │ agent writes │ │
│ │ repo pod │ │ code in │ │
│ └──────────────┘ │ worktree │ │
│ └───────┬─────────┘ │
└───────────────────────────────┼──────────────────┘
│
┌─────────────┐ │ ┌──────────────────┐
│ FAILED │←──┴──→│ PR OPENED │
│ │ │ │
│ (auto-retry │ │ PR watcher │
│ if stale) │ │ polls every 30s │
└─────────────┘ └─────────┬────────┘
│
┌─────────────────────────────────────────────┼─────────┐
│ FEEDBACK LOOP │ │
│ │ │
│ CI fails? ────────→ Resume agent ←─────┤ │
│ to fix build │ │
│ │ │
│ Merge conflicts? ──→ Resume agent ←─────┤ │
│ to rebase │ │
│ │ │
│ Review requests ───→ Resume agent ←─────┤ │
│ changes? with feedback │ │
│ │ │
│ CI passes + ───────→ Auto-merge ──────┤ │
│ review done? & close issue │ │
│ ▼ │
│ ┌──────────────┐ │
│ │ COMPLETED │ │
│ │ PR merged │ │
│ │ Issue closed │ │
│ └──────────────┘ │
└───────────────────────────────────────────────────────┘
- Kubernetes v1.33+ — required for post-quantum TLS on the control plane. v1.33 is the first release built on Go 1.24, which enables hybrid X25519MLKEM768 key exchange automatically. Earlier versions run but do not negotiate post-quantum TLS between Optio and the Kubernetes API server.
- Docker Desktop with Kubernetes enabled (Settings → Kubernetes → Enable)
- Node.js 22+ and pnpm 10+
- Helm (
brew install helm)
git clone https://github.com/jonwiggins/optio.git && cd optio
./scripts/setup-local.shThat's it. The setup script installs dependencies, builds all Docker images (API, web, and agent presets), deploys the full stack to your local Kubernetes cluster via Helm, and installs metrics-server.
Web UI ...... http://localhost:30310
API ......... http://localhost:30400
Open the web UI and the setup wizard will walk you through configuring GitHub access, agent credentials (API key or Max/Pro subscription), and adding your first repository.
./scripts/update-local.shPulls latest code, rebuilds images, applies Helm changes, and rolling-restarts the deployments.
helm uninstall optio -n optioapps/
api/ Fastify API server, BullMQ workers, WebSocket endpoints,
workflow engine, connection service, review service, OAuth
web/ Next.js dashboard with real-time streaming, cost analytics,
workflow management, connection catalog
site/ Documentation site (GitHub Pages)
cli/ Terminal client for Optio
packages/
shared/ Types, task state machine, prompt templates, error classifier
container-runtime/ Kubernetes pod lifecycle, exec, log streaming
agent-adapters/ Claude Code + Codex + Copilot + Gemini + OpenCode adapters
ticket-providers/ GitHub Issues, Linear, Jira, Notion
images/ Container Dockerfiles: base, node, python, go, rust, full
helm/optio/ Helm chart for production Kubernetes deployment
scripts/ Setup, init, and entrypoint scripts
Optio can use a GitHub App instead of a Personal Access Token for GitHub operations. This provides user-scoped access (respecting CODEOWNERS, branch protection, and repository permissions), automatic token refresh, and clear attribution on PRs and commits.
Register a new GitHub App at https://github.com/organizations/{org}/settings/apps/new with these settings:
Repository permissions:
| Permission | Access | Used for |
|---|---|---|
| Contents | Read & Write | git clone, push, branch management |
| Pull requests | Read & Write | create PRs, post comments, merge |
| Issues | Read & Write | issue sync, label management |
| Checks | Read | CI status polling in PR watcher |
| Metadata | Read | repo listing, auto-detection |
Account permissions:
| Permission | Access | Used for |
|---|---|---|
| Email addresses | Read | user email for login (recommended) |
Organisation permissions:
| Permission | Access | Used for |
|---|---|---|
| Members | Read | repo listing (optional) |
Other settings:
- Callback URL:
{PUBLIC_URL}/api/auth/github/callback - Request user authorization (OAuth) during installation: Yes
- Expire user authorization tokens: Yes (recommended, 8-hour lifetime with refresh)
- Webhook: Can be left disabled (Optio uses polling)
After creating the app and installing it on your organisation, configure Optio via Helm values:
github:
app:
id: "123456" # App ID (from app settings page)
clientId: "Iv1.abc123" # Client ID (for user OAuth login)
clientSecret: "..." # Client secret
installationId: "789" # Installation ID (from org install URL)
privateKey: | # PEM private key (for server-side tokens)
-----BEGIN RSA PRIVATE KEY-----
...
-----END RSA PRIVATE KEY-----When configured, users who log in via GitHub get a user access token that is used for all their git and API operations. Background workers (PR watcher, ticket sync) use the app's installation token. If the GitHub App is not configured, Optio falls back to the GITHUB_TOKEN PAT.
If you manage secrets externally (e.g., with external-secrets-operator, sealed-secrets, or vault-injector), you can reference an existing Kubernetes Secret instead of providing the values inline:
github:
app:
existingSecret: "my-github-app-secret"The secret must contain these keys: GITHUB_APP_ID, GITHUB_APP_CLIENT_ID, GITHUB_APP_CLIENT_SECRET, GITHUB_APP_INSTALLATION_ID, GITHUB_APP_PRIVATE_KEY.
Optio ships with a Helm chart for production Kubernetes clusters. Three installation methods are available:
helm repo add optio https://jonwiggins.github.io/optio
helm repo update
helm install optio optio/optio -n optio --create-namespace \
--set encryption.key=$(openssl rand -hex 32) \
--set postgresql.enabled=false \
--set externalDatabase.url="postgres://..." \
--set redis.enabled=false \
--set externalRedis.url="redis://..." \
--set ingress.enabled=true \
--set ingress.hosts[0].host=optio.example.comhelm install optio oci://ghcr.io/jonwiggins/optio -n optio --create-namespace \
--set encryption.key=$(openssl rand -hex 32) \
--set postgresql.enabled=false \
--set externalDatabase.url="postgres://..." \
--set redis.enabled=false \
--set externalRedis.url="redis://..." \
--set ingress.enabled=true \
--set ingress.hosts[0].host=optio.example.comgit clone https://github.com/jonwiggins/optio.git && cd optio
helm install optio helm/optio -n optio --create-namespace \
--set encryption.key=$(openssl rand -hex 32) \
--set postgresql.enabled=false \
--set externalDatabase.url="postgres://..." \
--set redis.enabled=false \
--set externalRedis.url="redis://..." \
--set ingress.enabled=true \
--set ingress.hosts[0].host=optio.example.comSee the Helm chart values for full configuration options including OAuth providers, resource limits, and agent image settings.
| Layer | Technology |
|---|---|
| Monorepo | Turborepo + pnpm |
| API | Fastify 5, Drizzle ORM, BullMQ |
| Web | Next.js 15, Tailwind CSS 4, Zustand |
| Database | PostgreSQL 16 |
| Queue | Redis 7 + BullMQ |
| Runtime | Kubernetes (Docker Desktop for local dev) |
| Deploy | Helm chart |
| Auth | Multi-provider OAuth (GitHub, Google, GitLab) |
| CI | GitHub Actions (format, typecheck, test, build-web, build-image) |
| Agents | Claude Code, OpenAI Codex, GitHub Copilot, Google Gemini, OpenCode |
See CONTRIBUTING.md for development setup, workflow, and conventions.