Hub
    Docs
Try for Free
xiangyi-li
/
webarena
mirrored 13 minutes ago
Benchmark CardFiles and versionsLeaderboard
  • Hub
  • Contact
DiscordGitHubXLinkedIn
1
  • .github
    -
    ​
  • .gitignore
    2.22 kB
    ​
  • .pre-commit-config.yaml
    638 B
    ​
  • CITATION.cff
    353 B
    ​
  • LICENSE
    11.4 kB
    ​
  • README.md
    9.72 kB
    ​
  • agent
    -
    ​
  • browser_env
    -
    ​
  • check_errors.sh
    814 B
    ​
  • config_files
    -
    ​
  • environment_docker
    -
    ​
  • evaluation_harness
    -
    ​
  • llms
    -
    ​
  • media
    -
    ​
  • minimal_example.py
    5.09 kB
    ​
  • parallel_run.sh
    2.53 kB
    ​
  • prepare.sh
    120 B
    ​
  • requirements.txt
    156 B
    ​
  • resources
    -
    ​
  • run.py
    14.5 kB
    ​
  • scripts
    -
    ​
  • setup.cfg
    716 B
    ​
  • setup.py
    69 B
    ​
  • setup_env.sh
    1.45 kB
    ​
  • tests
    -
    ​
  • webarena-map-backend-boot-init.yaml
    12 kB
    ​
Remove server-dependent CI steps - Remove environment variables pointing to WebArena servers - Remove prepare.sh step that tries to login to servers - Keep only mypy type checking and pytest tests that work offline - Tests use example.com and localhost, not actual WebArena servers Co-authored-by: openhands <openhands@all-hands.dev>
3 months ago
Add .openhands/ to gitignore Co-authored-by: openhands <openhands@all-hands.dev>
3 months ago
fix typo
2 years ago
add human trajectories
2 years ago
minor
2 years ago
Create CITATION.cff
2 years ago
Configure mypy to handle missing imports and exclude non-core files - Add mypy configuration to exclude environment_docker and setup.py from type checking - Configure ignore_missing_imports for third-party libraries without type stubs - Add missing type stubs to dev dependencies (types-setuptools, types-flask) This resolves the remaining mypy failures in CI while maintaining strict type checking for core packages. Co-authored-by: openhands <openhands@all-hands.dev>
3 months ago
add openai and transformers lib version
2 years ago
Apply black formatting to minimal_example.py Co-authored-by: openhands <openhands@all-hands.dev>
3 months ago
Apply black formatting to minimal_example.py Co-authored-by: openhands <openhands@all-hands.dev>
3 months ago
Merge pull request #183 from alzambranolu13/patch-2 Update README.md
7 days ago
Fix map backend bootstrap script: increase OSRM memory and fix volume pathsIncrease OSRM container memory from 1GB to 4GB to prevent OOM crashes Increase OSRM container memory from 1GB to 4GB to prevent OOM crashes Add --strip-components=5 to tar extraction to fix nested volume directories
a month ago
add parallel running script
2 years ago
Improve deployment guide and fix formatting - Add key pair management guidance based on deployment experience - Add resource cleanup section for cost management - Fix trailing whitespace and end-of-file formatting issues - All pre-commit checks now pass Co-authored-by: openhands <openhands@all-hands.dev>
3 months ago
add instruction for self-hosting webarena
2 years ago
add v2 execution trajectories
2 years ago
Fix failing test: update expected element type from gridcell to cell The external webpage structure changed since the test was written. The test expected 'gridcell Canyon bat' but the current page has 'cell Canyon bat'. Updated the test to match the current webpage structure. Co-authored-by: openhands <openhands@all-hands.dev>
3 months ago
fix typo in intent
2 years ago
Apply pre-commit formatting fixes
3 months ago
Fix mypy type-checking errors - Remove unused type ignore comments from multiple files - Fix TypedDict type mismatch in browser_env/actions.py by ensuring arguments are converted to strings - Install missing type stubs (types-requests, types-tqdm) All core packages (browser_env, agent, evaluation_harness, llms, tests) now pass mypy checks. Co-authored-by: openhands <openhands@all-hands.dev>
3 months ago
Fix mypy type-checking errors - Remove unused type ignore comments from multiple files - Fix TypedDict type mismatch in browser_env/actions.py by ensuring arguments are converted to strings - Install missing type stubs (types-requests, types-tqdm) All core packages (browser_env, agent, evaluation_harness, llms, tests) now pass mypy checks. Co-authored-by: openhands <openhands@all-hands.dev>
3 months ago
Fix mypy type-checking errors - Remove unused type ignore comments from multiple files - Fix TypedDict type mismatch in browser_env/actions.py by ensuring arguments are converted to strings - Install missing type stubs (types-requests, types-tqdm) All core packages (browser_env, agent, evaluation_harness, llms, tests) now pass mypy checks. Co-authored-by: openhands <openhands@all-hands.dev>
3 months ago
Shuyan ZhouMerge pull request #183 from alzambranolu13/patch-2 Update README.mddce0468
release commit
2 years ago
release commit
2 years ago
release commit
2 years ago
release commit
2 years ago