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.
0%+412%90 tracked days
iFurySt/open-codex-computer-useCopilotKit/openbot

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.

Axisopen-codex-computer-useopenbot
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)
Runs in cli, coding-agent-plugin. Works with other-fixed.

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)
Runs in web-app, cli, ci. Works with byok, openai, anthropic, gemini.

What people want from each one

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.