// agents · onecli/onecli

onecli

onecli is an open-source ai agents project by onecli (onecli/onecli on GitHub). It has 3,565 GitHub stars and 250 forks, is released under the Apache-2.0 license, and was last updated on GitHub on 8 October 2026.

An open-source sandboxed agent harness for teams — a secured personal agent for every employee.

★ 3.6k stars⑂ 250 forksApache-2.0updated 2026-10

View on GitHub ↗Official site ↗

▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.

// project facts

Project facts

Repository: onecli/onecli
GitHub stars: 3,565
Forks: 250
License: Apache-2.0
Last updated on GitHub: 8 October 2026
Category: AI Agents
Listing: Full install guide
Official site: Official site

// how it works

How it works

Clarify your goal
Decide the first concrete outcome you want from it, so you can pick the right example, template or mode instead of exploring everything at once.
Get the project
Clone the repository (or install the published package) and skim its README quick start for the requirements for your platform.
Install and configure
Run the documented install step and set any required configuration — such as provider keys, data sources or local services — before the first run.
Run your first task
Execute the smallest documented example end to end, confirm the output is what you expected, then adapt it to your real data or workflow.

// features

Why people love it

An agent per person

Each workspace member gets a sandboxed agent reachable from the dashboard or Slack, provisioned from the company IdP.

Credentials agents never see

The gateway injects secrets per request, matched by host/path; Bitwarden/1Password on-demand injection is supported.

Deterministic approvals

Human-in-the-loop approval in chat for sensitive actions like sending email or deleting resources.

Memory and skills

Platform-kept memory you can read and edit, plus reusable skills available to every agent run.

Scheduling

Agents can plan future work and are woken by the platform at the right time.

Team policy in one place

One policy enforced for every agent, with shared global connections granted per agent.

// run it

Run it yourself

Clone the repository
Get the source so you can inspect, configure and run it locally.
```
git clone https://github.com/onecli/onecli.git
cd onecli
```

Self-host OneCLI

Clone the repo, install dependencies and run the setup.

git clone https://github.com/onecli/onecli.git && cd onecli
pnpm install
pnpm run setup

Or develop locally

Use mise for tooling, then run the dev stack.

git clone https://github.com/onecli/onecli.git && cd onecli
mise install
pnpm install
pnpm dev

// use cases

What you can build

Roll out personal agents to a whole company without sharing raw API keys
Give each employee a Slack-native assistant with enforced policy
Approve sensitive agent actions deterministically in chat
Share team LLM keys per-agent without handing them to agents

// faq

Questions, answered

Who maintains onecli?

It is maintained by onecli on GitHub (onecli/onecli), where the source, issues and releases live.

Is it free to use?

Yes — it is free and open source under Apache-2.0, which permits use, modification and commercial redistribution, with licence/notice retention.

Does it need a paid API key?

You configure the team's own LLM keys and service accounts as global connections; OneCLI also offers a cloud-hosted option at onecli.sh.

How does it compare to running individual unmanaged agent CLIs per employee?

Compared with running individual unmanaged agent CLIs per employee, onecli's distinguishing focus is: an open-source sandboxed agent harness for teams — a secured personal agent for every employee. Pick it when that focus matches your need; the alternative may suit you better if its broader or different scope is the priority.

How do I get started?

The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if onecli is not the right fit.

openclaw★ 391.6k
A personal AI that really does things — on any OS, with your data staying yours.
superpowers★ 294.9k
An agentic skills framework & software development methodology that works.
ECC★ 275.2k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
hermes-agent★ 252.0k
The agent that grows with you — a Python framework for adaptive AI agents.
deepseek-harness★ 245.5k
DeepSeek's plugin-based agent harness where everything is a plugin.

// more in agents

Get onecli

Free and open — grab the source, star the repo, and start creating.

View on GitHub ↗← More AI Agents tools

onecli

Project facts

How it works

Why people love it

An agent per person

Credentials agents never see

Deterministic approvals

Memory and skills

Scheduling

Team policy in one place

Run it yourself

What you can build

Questions, answered

Similar tools

moltis

agentkit

goclaw

deepseek-harness

nanoclaw

deepagents

Alternatives in AI Agents

More in AI Agents

Get onecli