Cloudgeni-ai/opengeni

Durable sessions · human approvals · governed memory · your choice of compute
Start free at app.opengeni.ai →
Quickstart ·
Docs ·
Self-host ·
Issues
---
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
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.
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.