PyPI Stats

Search Packages

Find Python packages by name, description, GitHub topic, or filter by metrics
ServiceNow
agentlab

AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.

3K 574 112
OSU-NLP-Group
uground-demo-test

[ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents

1K 312 18
reacher-z
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%.

1K 147 9
reacher-z
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%.

1K 147 9
reacher-z
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%.

1K 147 9
reacher-z
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%.

1K 147 9
reacher-z
openclawbench

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%.

1K 147 9
reacher-z
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%.

753 147 9
reacher-z
claw-ai

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

248 147 9
reacher-z
task-harness

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

241 147 9
reacher-z
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%.

227 147 9
reacher-z
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%.

219 147 9
reacher-z
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%.

213 147 9
reacher-z
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%.

212 147 9
reacher-z
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%.

210 147 9
ServiceNow
doomarena-taubench

DoomArena is a Framework for Testing AI Agents Against Evolving Security Threats

209 58 6
ServiceNow
doomarena

DoomArena is a Framework for Testing AI Agents Against Evolving Security Threats

208 58 6
reacher-z
nail-eval

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

207 147 9
reacher-z
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%.

206 147 9
reacher-z
nail-group

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%.

205 147 9
reacher-z
r2-harness

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

204 147 9
reacher-z
nail-bench

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

204 147 9
reacher-z
r2agent

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

204 147 9
reacher-z
harnessos

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%.

203 147 9