EeriestraBrowser & computer use

browser-use-olympics

Browser Use Olympics by Almond: one prompt, five events, one clock. Plus fast loop, a ~200-line browser computer-use agent (Chrome DevTools + TypeSafe Jev).

Explore repository

How it uses Jev

1. Browser Use Olympics — a benchmark for browser-using agents, built and hosted on Almond, the home for websites made with AI. One prompt, five events, one server-side clock, a Hall of Fame. Live at https://sites.almond.build/browser-use-olympics/ (Hall of Fame: https://sites.almond.build/browser-use-olympics/hall). Source: olympics/ . 2. Almond-fastloop — a 200-line, dependency-free browser computer-use loop: Chro…

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to browser-use-olympics

Browse all
jev-browser project preview

jev-browser

Browser & computer use
Browser use using Typesafe's Jev model
JMade byjkudish257
jev-reach project preview

jev-reach

Browser & computer use
chrome-devtools-mcp plus one tool: Jev walks the browser to the right spot, then your agent makes a single devtools call there.
RMade byrashedInt320
jev-browser-skill (ChenYCL) project preview

jev-browser-skill (ChenYCL)

Browser & computer use
Browser use & computer use for coding agents, powered by TypeSafe Jev: calibrated judgments from a System One model, control loop in code. ego lite / Chrome / Safari · CLI + MCP
CMade byChenYCL2
jgrep project preview

jgrep

Agent tooling
grep, but the pattern is a description. Filters lines by meaning with TypeSafe's Jev decision model: ~200 ms and a thousandth of a cent per line.
KMade bykeltokhy78
jev-architect project preview

jev-architect

Benchmarks & research
Find, design, and evaluate TypeSafe Jev decision loops.
KMade bykaranb1926

Vercel AI SDK provider

Integrations
@ai-sdk/typesafe-ai plus experimental_evaluate; use jev-latest as an evaluation model.
CMade byCommunity contributor
siege project preview

siege

Games & simulations
SIEGE: 200 people vs one agent. A typed action gate (TypeSafe System One) that learns from every breach, evaluated by W&B Weave, hardened by a defender loop. Built at CoreWeave Hacks: Agent Loops 2026.
VMade byvnmoorthy0
llm-to-jev project preview

llm-to-jev

Applications
Convert LLM prompts to Jev prompts
AMade byalexwestco5
system-one-router project preview

system-one-router

Benchmarks & research
A fast System One decision model (Jev or local Laya) picks which LLM answers each prompt: OpenAI-compatible Go gateway + decision benchmark
MMade bymmornati1