open-codex-computer-use vs openbot
openbot is much bigger: 5.3k stars against 2.2k. Over the days we have tracked them open-codex-computer-use moved +87.2% and openbot +412.4%, so openbot is growing faster right now.
They split the axes: open-codex-computer-use leads on privacy and model freedom and setup ease, openbot on context depth and noise control.
Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.
Where they stand today
Open-source, self-hosted MCP implementation of Computer Use that provides a local alternative to Codex Computer Use and integrates with multiple agent clients.
- Stars
- 2.2k
- Tracked growth
- +87.2%
- Maturity
- ●●●●●
- Last commit
- 1h ago
- Language
- Swift
- License
- MIT
- Cost to run
- Free, local
Runs each agent in an isolated, browser-backed per-agent 'computer' with a central gateway that enforces CEL policies and records an auditable trail of every action.
- Stars
- 5.3k
- Tracked growth
- +412.4%
- Maturity
- ●●●●●
- Last commit
- 6h ago
- Language
- TypeScript
- License
- MIT
- Cost to run
- Requires CopilotKit license and your model API key.
Six axes, head to head
Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.
| Axis | open-codex-computer-use | openbot |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Local UI only | ●●●●● Workspace access |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● None mentioned | ●●●●● Policy and audit |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Config file support | ●●●●● YAML & UI configs |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Fully local | ●●●●● Cloud APIs w/ key |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Provider-agnostic | ●●●●● Multiple providers |
Setup ease What it takes to get a first useful run out of it. | ●●●●● One-command install | ●●●●● Config + API key |
Which one to pick
Pick open-codex-computer-use if…
Privacy-first — use a local, open-source Computer Use service that runs on macOS, Linux, and Windows and plugs into Codex/Claude/Gemini clients.
- Privacy: Fully local (5/5 against 3/5)
- Model freedom: Provider-agnostic (5/5 against 3/5)
- Setup ease: One-command install (5/5 against 3/5)
Pick openbot if…
Privacy-first — runs on your machine with per-bot containers, encrypted credentials, and a policy-enforced gateway for auditable, controllable agent actions.
- Context depth: Workspace access (3/5 against 1/5)
- Noise control: Policy and audit (3/5 against 1/5)
What people want from each one
iFurySt/open-codex-computer-use
CopilotKit/openbot
Questions people ask
Is open-codex-computer-use better than openbot?
They split the axes: open-codex-computer-use leads on privacy and model freedom and setup ease, openbot on context depth and noise control. open-codex-computer-use is worth picking when privacy-first — use a local, open-source Computer Use service that runs on macOS, Linux, and Windows and plugs into Codex/Claude/Gemini clients.
Which of open-codex-computer-use and openbot keeps my code private?
open-codex-computer-use: Fully local (5/5). openbot: Cloud APIs w/ key (3/5).
What does each one cost to run?
open-codex-computer-use: Free, local. openbot: Requires CopilotKit license and your model API key..
Full profiles: iFurySt/open-codex-computer-use and CopilotKit/openbot. Everything else in Computer use.