Browser Agent Python Packages

smolvm-core

Open-source AI sandbox infrastructure for code execution, browser use, and AI agents.

13K 544 34

perceive

Reachability-filtered perception layer for AI browser agents.

4K 0 0

clawbench-eval

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

2K 314 19

browsertrace

Local replay debugger for Browser Use failures with screenshots, model I/O, failed-step timelines, and public-safe HTML exports.

2K 3 23

clawbenchmark

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

776 314 19

webqa-agent

Autonomous web browser agent that audits performance, functionality & UX for engineers and vibe-coding creators. 网站自主评估测试 Agent，支持 GUI/CLI 一键完成性能、功能使用与交互体验的测试评估

437 212 16

clawbench-harness

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

421 314 19

claw-harness

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

395 314 19

nail-clawbench

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

377 314 19

openclawbench

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

354 314 19

clawbench-cli

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

320 314 19

browserground

Local UI-grounding specialist for hybrid AI agents. Qwen3-VL-2B LoRA. Screenshot + text target → strict JSON bbox. Drop-in for Claude Code, Codex, browser-use. Cuts GPT-4V cost & latency.

246 1 0

claw-eval

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

137 314 19

claw-ai

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

129 314 19

task-harness

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

122 314 19

nail-bench

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

113 314 19

everyday-bench

ClawBench: Can AI Agents Complete Everyday Online Tasks? (alias of claw-bench)

110 314 19

claw-agent

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

109 314 19

blackreach

an autonomous browser agent that does your research while you sleep

109 1 0

mcq-bench

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

107 314 19

uzdabrawza

The Anal-Queen of AI Browser Automation 🏴‍☠️ A beautifully fucked-up Skynet-powered browser automation script that harnesses neural brainfuck and machine learning chaos to give zero shits about anything while somehow still working perfectly.

107 10 0

life-bench

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

104 314 19

harness-hub

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

92 314 19

nail-agent

Open-source benchmark for browser AI agents on 153 everyday online tasks across 144 live websites. 5-layer recording + DOM-match + LLM judge. Top score 33.3%.

92 314 19