PyRank
  • Insights
  • PyPI
  • GitHub
  • Search
  • Compare
  • Advisories
  • Ecosystem
  • About

Web Agents Python Packages

Python packages with the GitHub topic web-agents. Sorted by relevance, with stars and monthly downloads.
ServiceNow
agentlab

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

2K 598 121
reacher-z
clawbench-eval

Open-source benchmark for browser AI agents on daily tasks.

2K 453 26
tinyfish-io
langchain-tinyfish

LangChain integration for TinyFish Web Agent - AI-powered web automation

560 13 6
jstibal
langchain-openterms

openterms sdk

534 0 0
OSU-NLP-Group
uground-demo-test

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

514 315 19
ServiceNow
doomarena-taubench

TauBench extensions for DoomArena

401 62 7
ServiceNow
doomarena

A framework to test the security and robustness of AI agents

391 62 7
reacher-z
clawbench-harness

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

312 453 26
reacher-z
nail-clawbench

Open-source benchmark for browser AI agents on daily tasks.

296 453 26
reacher-z
openclawbench

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

294 453 26
reacher-z
claw-harness

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

286 453 26
tinyfish-io
tinyfish-adk

TinyFish Web Agent tools for Google Agent Development Kit (ADK)

275 13 6
reacher-z
clawbench-cli

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

252 453 26
ServiceNow
doomarena-promptceptor

Promptceptor tool

215 62 7
reacher-z
claw-eval

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

157 453 26
reacher-z
realtask-bench

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

127 453 26
reacher-z
task-harness

Open-source benchmark for browser AI agents on daily tasks.

126 453 26
reacher-z
claw-ai

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

122 453 26
reacher-z
everyday-bench

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

119 453 26
reacher-z
nail-bench

Open-source benchmark for browser AI agents on daily tasks.

119 453 26
reacher-z
life-bench

Open-source benchmark for browser AI agents on daily tasks.

118 453 26
reacher-z
claw-agent

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

117 453 26
reacher-z
mcq-bench

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

115 453 26
reacher-z
nail-eval

Open-source benchmark for browser AI agents on daily tasks.

111 453 26
    • Data from PyPI, GitHub, ClickHouse, and BigQuery