onecli

Open-source sandboxed agent harness for teams. Giving every employee a secured personal agent.

What is onecli?

Open-source sandboxed agent harness for teams. Giving every employee a secured personal agent.

Overview of onecli

What it is

OneCLI is an open-source platform for running AI agents as a team. It provides a sandboxed agent harness that gives every employee a secured personal agent. The platform is built in Rust and designed to manage secrets, permissions, and multi-agent deployments for teams. It includes a web dashboard, API server, Rust gateway, runner, sandbox supervisor, SSH terminator, channel adapter, and secret store.

Key features

  • Your identity provider, integrated: provision agents on behalf of each employee's identity, straight from the company IdP.
  • An agent per person: everyone in the workspace gets their own sandboxed agent, reachable from the dashboard or Slack.
  • One policy, enforced everywhere: manage the team policy in one place, that any agent in the workspaces would be enforced by.
  • Deterministic human-in-the-loop approvals: in the chat itself, for things you need 100% control over, like sending the email, deleting the Linear ticket, emptying an S3 bucket.
  • Shared connections: connected once at the team level, like LLM keys or service accounts, granted per agent without ever being handed to one.
  • Credentials it never sees: each agent gets only the access you granted, and the gateway enforces it on every request. Or connect Bitwarden or 1Password for on-demand injection, with nothing stored on the server.
  • Its own Slack app: connect it once and it answers in channels and DMs under its own name and avatar, with files and images. Delete the agent and its Slack app goes with it.

Use cases

OneCLI is built for teams that need to run autonomous AI agents for each employee. It is suitable for organizations that want to give every team member a personal, sandboxed agent with controlled access to credentials and services. Use cases include managing secrets and permissions for agents, enabling multi-agent collaboration, and enforcing team-wide policies on agent behavior. The platform supports deterministic human-in-the-loop approvals for sensitive actions like sending emails or deleting tickets.

Getting started

For self-hosted deployment, run the following commands:bashgit clone https://github.com/onecli/onecli.git && cd oneclipnpm installpnpm run setupOpen http://localhost:10254. On Kubernetes, install the Helm chart: helm install onecli oci://ghcr.io/onecli/charts/onecli. For local development, use pnpm dev after cloning and installing dependencies. See the repository README for full details.

License and pricing

The project is licensed under Apache-2.0, with one exception: the ee/ directories hold enterprise features under the OneCLI Enterprise License, which is free for development, testing and evaluation, and requires a subscription for production use. Everything else is Apache-2.0 and can be self-hosted in production with no commercial license.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/oneclionecli.svg)](https://yunodb.com/tools/oneclionecli?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/oneclionecli?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/oneclionecli.svg" alt="Featured on YunoDB" height="20"></a>