FreeComputerUse — Testing skill for Claude Code
Local-first AI browser automation with Playwright.
How to install FreeComputerUse
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open OthmaneBlial/FreeComputerUse and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What FreeComputerUse does
Local-first AI browser automation with Playwright. Use OpenAI, Grok, DeepSeek, Anthropic and compatible APIs—or ChatGPT/Claude Code subscriptions. Approve site access, watch each action, and replay proven workflows with zero model calls.
Alternatives in Testing
- N9e Config Driven E2e — Maintain config-driven Nightingale E2E tests that convert JSON config data into UI-readable normalized values 301 ★
- Robotics Agent Skills — Agent skills that make AI coding assistants write production-grade robotics software 170 ★
- Opencode Skill Creator — OpenCode skill for creating, testing, and optimizing other OpenCode skills 157 ★
README
FreeComputerUse

Quick start · Project site · Try the task lab · Security
**Your browser. Your model. Your call.** Tell it what done looks like, then stay in control of every step.
FreeComputerUse is a local-first AI browser automation agent. A model plans small action batches; TypeScript and Playwright execute and verify them in your browser. Compatible workflows can be learned once and replayed later with **zero model calls**.
Watch a real run
[](https://othmaneblial.github.io/FreeComputerUse/#watch)
One goal led through six pages to a verified incident brief: **21 successful actions, 10 model calls, one repaired failure**. The configured cost estimate was **$0.00650**. This is one recorded synthetic task, not a general success-rate claim. [Watch the full recording](https://othmaneblial.github.io/FreeComputerUse/lab/media/incident-demo.mp4) · [Inspect the evidence](assets/readme/incident-evidence.json)
Related Skills
Servicenow Skills
Agent plugin marketplace for the ServiceNow REST APIs: skill, references, official docs snapshot, OpenAPI 3.1
Leanix Skills
Agent plugin marketplace for the SAP LeanIX APIs: skill, references, official docs snapshot, OpenAPI 3.1 spec
Chat Demo
Shoot one MCP chat-demo episode from a JSON spec (headed Playwright, real Claude/ChatGPT/Grok).
AI Gateway Testkit
Open-source conformance and regression testkit for Anthropic- and OpenAI-compatible AI gateways, with stable t
Turnpike
A minimal local gateway that proxies Claude/Anthropic and OpenAI-spec clients to any OpenAI- or Anthropic-comp
Conditional Access
Conditional Access plain-English explainer and step-by-step guide — view policies, create new policies, Report
Related Agents
Grok Agent 01
ONLY job: find free or freemium AI token/API plans (OpenAI-compatible, Anthropic, Google, open routers, studen
Router Client
Owns the Anthropic-compatible router HTTP client. Use for /healthz, /v1/models, scrub, RouterError, errorName,
ChatGPT On Wechat
CowAgent是基于大模型的超级AI助理,能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、拥有长期记忆并不断成长,比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页