Opengeni is a production-ready agentic service: it runs AI agents that do real work, keeps a session going for hours or days, records every step in a replayable event log, stops for a human when an action needs approval, and puts each session either in a managed sandbox or directly on a machine you own.
Opengeni is not the agent; it is everything the agent needs around it. Give agents work from the web app and follow along, or call the same session API from your own product and let Opengeni hold the state, history, approvals, and outputs. It grew out of two years of running agents against production cloud infrastructure at Cloudgeni.
Get started
The fastest way is the managed service. Sign up at app.opengeni.ai, name your organization, connect a model (a ChatGPT/Codex or SuperGrok subscription, a provider key, or prepaid credits), and start your first session. Nothing to deploy. The quickstart walks through it.
Prefer to run it yourself? Everything is open source. Jump to Run it locally for a one-command dev stack, or to Self-host for production.
Features
- Durable, replayable sessions. Every event lands in Postgres. Live streams backfill from it, so a browser reload, a new client, or an audit replays the same history.
- Sessions that finish the job. Give a session a goal with success criteria. The agent keeps working until it completes the goal with evidence, pauses with a rationale, or a human interrupts.
- Humans in the loop. Tool approvals gate risky actions. Agents can ask structured questions and resume the exact tool call after the answer, even across restarts.
- Run anywhere. A managed sandbox (Docker, Modal, or a cloud provider) or a Connected Machine: your laptop, build server, or GPU box, enrolled once and driven directly. Machines only dial out and receive no Opengeni credentials.
- Agent Knowledge. Files, retained sources, and useful findings in one searchable library, with personal and workspace ownership and optional review before anything is published.
- Integrate into your product. Embed the full conversation with the
SessionConversation React component behind a packaged, tenant- and user-scoped proxy on your server. Your organization API key stays there.
- Managed or self-hosted. Use app.opengeni.ai with nothing to run, or deploy the same API, web app, workers, Helm chart, and reference Terraform for Azure, AWS, and GCP yourself. All of it is Apache-2.0.
Run it locally
Repository changes land through the merge batcher: queued
PRs are tested together on the combined tree and each lands as one squash commit.
Main runs the full suite on a cadence and is the release gate.
For development, or to evaluate Opengeni before self-hosting. You need Bun at the exact version in .bun-version, Git, curl, Docker, rustup, a C compiler (Xcode Command Line Tools on macOS or build-essential on Debian/Ubuntu), and an OpenAI or Azure OpenAI key.
git clone https://github.com/Cloudgeni-ai/opengeni.git
cd opengeni
cp .env.example .env # add your model credentials
bun run dev
Open http://127.0.0.1:3000, describe a task, and watch the session run.
bun run dev installs dependencies, starts Postgres, NATS, Temporal, and object storage, runs migrations, and starts the API, workers, and web app. By default the agent runs commands directly on your machine (the local sandbox), not in an isolated container, so the API and web app listen only on 127.0.0.1. Set OPENGENI_SANDBOX_BACKEND=docker to run the agent in the local sandbox image instead. See Local development for manual startup, configuration, network exposure, and the native (no Docker) path.
Desktop app
Opengeni for macOS, Windows and Linux: your sessions, chat and inbox in a native window, with notifications and one click to let agents use the computer you're on.
# macOS
brew install --cask cloudgeni-ai/tap/opengeni
# macOS or Linux (deb, rpm or AppImage, picked for your system)
curl -fsSL https://<your-opengeni-server>/desktop/install.sh | sh
On Windows, download Opengeni-<version>-windows.exe from the newest desktop-v release. The web app's account menu has the same downloads under Desktop app. Every way of installing updates itself afterwards.
Use it from your code and product
Let your coding agent do it. Install the Opengeni plugin, then ask your agent to add Opengeni to your product:
# Claude Code
claude plugin marketplace add Cloudgeni-ai/opengeni
claude plugin install opengeni@opengeni --scope user
# Codex (CLI, IDE, and the Codex app)
codex plugin marketplace add Cloudgeni-ai/opengeni
codex plugin add opengeni@opengeni
In Cursor, use Customize → From GitHub Repository with this repository. The plugin adds the Opengeni skills and connects your agent to your organization over MCP (sign in once in the browser). See the plugin guide.
Or wire it yourself — one server route and one component:
// app/api/opengeni/[...path]/route.ts (server only; the key stays here)
import { Opengeni } from "@opengeni/sdk/chat";
import { createSessionProxyRoute } from "@opengeni/sdk/next";
const og = new Opengeni({ apiKey: process.env.OPENGENI_API_KEY! });
export const { GET, POST, PUT, PATCH, DELETE } = createSessionProxyRoute(og, {
resolve: async (request) => {
const me = await authenticate(request); // your product's own auth
if (!me) return new Response("Unauthorized", { status: 401 });
return { user: me.id, tenant: me.teamId }; // workspaces and members are created on first use
},
createSession: (input) => input,
});
// Browser
import { OpenGeniChat } from "@opengeni/react";
import "@opengeni/react/compiled.css";
<OpenGeniChat baseUrl="/api/opengeni" />;
Follow Embed manually for the details, then the TypeScript SDK and React components. Northstar support is a runnable SaaS embed with a product MCP server.
How it works
"Agent" is one word for at least ten different jobs. A model is a function from tokens to tokens: it forgets everything between calls, has no idea what it is allowed to do, and has no obligation to keep working until the job is done. Everything above it exists to turn that into work that finishes, can be trusted with real systems, and can be explained afterwards.
Opengeni is built as those layers.
┌───────────────┐ ┌───────────────────────────────────────────────────────┐
│ │ │ 10 SURFACES console · embedded UI · Slack · │
│ 8 GOVERNANCE │ │ voice · SDK · API │
│ │ ├───────────────────────────────────────────────────────┤
│ identity │ │ 9 KNOWLEDGE scoped retrieval · reviewed │
│ tenancy │ │ learning · never mixed with chat │
│ permissions │ ├───────────────────────────────────────────────────────┤
│ secrets │ │ 7 DURABLE STATE sessions · turns · goals · │
│ approvals │ │ & ORCHESTRATION recovery · human-in-the-loop │
│ audit │ ├───────────────────────────────────────────────────────┤
│ │ │ 6 COMPUTE sandboxes · browsers · │
│ + │ │ your own machines │
│ │ ├───────────────────────────────────────────────────────┤
│ OBSERVABILITY │ │ 5 TOOLS one gateway · MCP · connections · │
│ & COST │ │ credentials outside the prompt │
│ │ ├───────────────────────────────────────────────────────┤
│ every call │ │ 4 AGENT LOOP cache-stable prompt · gradual │
│ records what │ │ tool disclosure · exact history │
│ it cost and │ ├───────────────────────────────────────────────────────┤
│ who pays │ │ 3 MODEL ROUTING allowed models · fallback · │
│ │ │ capacity waits · billing │
│ │ ├───────────────────────────────────────────────────────┤
│ │ │ 1-2 INFERENCE any provider · any wire format · │
│ │ │ swappable mid-conversation │
└───────────────┘ └───────────────────────────────────────────────────────┘
Rent the edges, own the middle. Models, provider APIs, and the raw compute box change too fast to own, so every one of them is a swappable boundary. Durable state, governance, and knowledge are where your workflows, permissions, audit record, and institutional memory actually live, so they sit in a Postgres database you operate, export, and can leave with.
Documentation
The public product docs live at docs.opengeni.ai, and the thinking behind the layers above is on the Opengeni blog. The Cloudgeni Infrastructure Agents Guide covers patterns for infrastructure-focused agents.
Built with
Bun · Hono · React and Vite · Temporal · Postgres with pgvector · NATS · OpenAI Agents SDK · a Rust agent and relay for Connected Machines
Security
Do not expose a production deployment without a deliberate access mode, tested database role posture, rate limits, and a reviewed sandbox credential policy. See the security boundary and report vulnerabilities through SECURITY.md.
Contributing
Contributions are welcome. Read CONTRIBUTING.md for setup, checks, and the pull request workflow, and AGENTS.md if you work on Opengeni itself.
bun run typecheck
bun test
License
Apache-2.0. Optional curated Skills under packages/runtime/src/curated_skill_library carry their own provenance and license metadata; HashiCorp-derived Terraform guidance is MPL-2.0 and is never mounted by default.
