garry-schuette/browser-use-with-jev
User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Integrations & Adapters
Browser Use with Jev
An early-alpha integration that lets TypeSafe Jev choose from concrete browser actions while a host - the Codex sidebar or Browser Use's Python engine - handles generation, recovery, and final verification, without patching the installed Browser Use package.
- Stars
- 3
- Language
- Python
- License
- MIT
- Reading time
- 3 min
- Published by
- Community
- Author
- garry-schuette
- Last verified
- Oct 2026
Used inJev for Software & DevTools
Highlights
- Two modes: a Codex desktop sidebar using Codex Computer Use, and a standalone bridge over upstream Python Browser Use.
- The sidebar helper adapts the community jev-browser-use implementation and is bundled, so you do not need that skill installed.
- The Python SDK and standalone mode retain the installed Browser Use engine without patching it.
- Status: early alpha. Offline integration tests pass; the bridge and sidebar backend were exercised on a local browser form.
- Independent project, not an official Browser Use or TypeSafe product; moving most routine decisions to Jev is the goal, not a measured claim.
Watch out
Grounded in the repository README and GitHub metadata reviewed on 2026-10-15; the README states broad site coverage and comparative performance benchmarks are still pending, its install section was truncated - drawing on GitHub metadata (stars 3, MIT, Python) - and the Codex desktop setup - and the README's CI badge references a different owner-repo path than the manifest URL.
Questions about this entry
Short answers drawn from the linked project or page.
It lets TypeSafe Jev choose from concrete browser actions while a host handles generation, recovery, and final verification. In Codex desktop it defaults to the visible in-app browser; the Python SDK and standalone mode keep the installed Browser Use engine without patching it.
Codex sidebar, the desktop default, runs actions through Codex Computer Use with a bundled JavaScript helper driven by the current conversation. Standalone Browser Use runs the upstream Python engine in a separate browser, with the current-conversation bridge or a configured API model as host.
No. The README says the active Codex conversation can serve as the host model and no additional OpenAI or other text-model API key is required for that mode. Jev still needs its configured provider credential, and neither mode exposes your Codex login as an API.
Early alpha. Offline integration tests pass, and the current-conversation bridge and sidebar backend have been exercised on a local browser form, but broad site coverage and comparative performance benchmarks are still pending. The README says moving most routine decisions to Jev is the goal, not a measured claim about this release.
The README says this independent implementation was motivated by exploring Browser Use's Jev Ultrafast, whose dynamic indexed action space inspired the split here: Jev chooses among concrete actions while a general-purpose model handles generation and judgment. Published speed claims for other projects are not benchmarks for this one.
The Browser Use Python package is the actual execution dependency for standalone mode; the sidebar helper adapts the wy-coliney/jev-browser-use community skill under its MIT license. The README notes neither related project is an installed runtime dependency for the sidebar path.
It is a community project published under the garry-schuette GitHub account, and the README calls it independent, not an official Browser Use or TypeSafe product. Installation starts with a local Codex desktop project with shell access; the README also offers to let your Codex install and configure the skill for you from the repo URL.
More Jev resources like this
Two opt-in Hermes Agent plugins that add TypeSafe Jev decision layers: a pre-tool gate for terminal, write_file, and patch calls, and a skill router that names the one skill worth loading before the model call. Stdlib only and fail-open.
Jev Integrations & Adapters#community#catalog-import#logicrw
Community
dogmatiic/hermes-jevPython
dogmatiic/hermes-jevPythonEffortlane is a local router for Codex on macOS that picks model and reasoning effort with Jev before each user turn, keeps native ChatGPT authentication, and records routing evidence locally. Shadow mode logs recommendations without changing execution.
Jev Integrations & Adapters#community#catalog-import#logicrw
A single-file Python proxy that asks Jev which of four model tiers each new Codex turn needs — luna, terra, sol or astra — rewrites the model field, and retries flaky upstream errors.
Jev Integrations & Adapters#community#catalog-import#logicrw
Codex Agent Skill that hands continuous browser work to Jev: one sentence starts a task, Jev picks the actions and targets, and Codex replies once the run completes. Reuses your own Chrome and reads the DOM instead of screenshots.
Jev Agents & MCP#community#catalog-import#logicrw
Community
wanghai673/jev-browser-skillPython
wanghai673/jev-browser-skillPythonA Cline plugin that gives the agent an isolated Playwright Chromium through a jev_run tool: Jev chooses a concrete operation and target per step via AI SDK 7's experimental_evaluate through the Vercel AI Gateway, and when it picks TYPE_TEXT, gemini-2.5-flash-lite writes the field value.
Jev Integrations & Adapters#community#catalog-import#logicrw
An OpenCode plugin that keeps the session on a cheap sticky parent model so the cache stays warm, and asks Jev whether a turn is hard before escalating through jev_escalate to temporary stronger subagents.
Jev Integrations & Adapters#community#catalog-import#cobanov
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.