Hub
    Docs
Try for Free
xiangyi-li
/
OS-World
mirrored 14 minutes ago
0
Benchmark CardFiles and versionsLeaderboard
  • Hub
  • Contact
DiscordGitHubXLinkedIn
  1. mm_agents
  • README.md
    1.99 kB
    ​
  • __init__.py
    -
    ​
  • accessibility_tree_wrap
    -
    ​
  • agent.py
    47.3 kB
    ​
  • aguvis_agent.py
    23 kB
    ​
  • anthropic
    -
    ​
  • coact
    -
    ​
  • gta1_agent.py
    68.3 kB
    ​
  • gui_som
    -
    ​
  • jedi_3b_agent.py
    17.9 kB
    ​
  • jedi_7b_agent.py
    17 kB
    ​
  • llm_server
    -
    ​
  • o3_agent.py
    9.14 kB
    ​
  • openai_cua_agent.py
    32.2 kB
    ​
  • opencua_agent.py
    39.7 kB
    ​
  • prompts.py
    75.4 kB
    ​
  • qwen25vl_agent.py
    24 kB
    ​
  • uitars15_v1.py
    38.5 kB
    ​
  • uitars15_v2.py
    37.1 kB
    ​
  • uitars_agent.py
    29.8 kB
    ​
  • utils
    -
    ​
Add Llama3-70B Support (from Groq)
a year ago
Modify the namespace of a11y tree (#62)
a year ago
FIx corner cases (val connection in chrome when using playwright, and action parsing for agent, and accessibility tree xml handling)
2 years ago
feat: add run_multienv_o3.py script for multi-environment evaluation - Introduced a new script `run_multienv_o3.py` to facilitate end-to-end evaluation across multiple environments. - Implemented command-line argument parsing for various configurations including environment settings, logging levels, and AWS parameters. - Integrated signal handling for graceful shutdown of environments and processes. - Enhanced logging capabilities for better traceability during execution. - Maintained existing logic from previous scripts while introducing new functionalities for improved evaluation processes.
5 days ago
feat: enhance run_coact.py with logging and configuration options - Added logging configuration to capture runtime logs in both file and console with adjustable log levels. - Introduced new command-line arguments for provider name, region, and client password to improve flexibility and security. - Updated process_task function to accommodate new parameters, ensuring compatibility with existing logic. - Modified prompt templates in coding_agent.py and cua_agent.py to use the client password placeholder for enhanced security.
2 days ago
add cogagent server
a year ago
feat: update jedi agent with support for o3 as planner
3 days ago
feat: update jedi agent with support for o3 as planner
3 days ago
Wxy/opencua (#290) * OpenCUA Agent code base * update url * debug, modify url input * debug opencua * show result * debug agent history overlap * modify opencua agent; add comment lines * update parallel; clean code; use sleep 3s * ui-tars-0717 * update detail * add system password to system prompt * add running command
2 days ago
feat: add client password argument to multiple agents and scripts - Introduced `--client_password` argument in `run_multienv_aguvis.py`, `run_multienv_claude.py`, and `run_multienv_gta1.py` for enhanced security and flexibility. - Updated agent classes (`PromptAgent`, `AguvisAgent`, `GTA1Agent`) to accept and utilize `client_password` for improved configuration. - Modified evaluation guidelines to reflect the new client password requirement. - Ensured existing logic remains intact while enhancing functionality for better user experience.
5 days ago
feat: add client password argument to multiple agents and scripts - Introduced `--client_password` argument in `run_multienv_aguvis.py`, `run_multienv_claude.py`, and `run_multienv_gta1.py` for enhanced security and flexibility. - Updated agent classes (`PromptAgent`, `AguvisAgent`, `GTA1Agent`) to accept and utilize `client_password` for improved configuration. - Modified evaluation guidelines to reflect the new client password requirement. - Ensured existing logic remains intact while enhancing functionality for better user experience.
5 days ago
feat: add client password argument to multiple agents and scripts - Introduced `--client_password` argument in `run_multienv_aguvis.py`, `run_multienv_claude.py`, and `run_multienv_gta1.py` for enhanced security and flexibility. - Updated agent classes (`PromptAgent`, `AguvisAgent`, `GTA1Agent`) to accept and utilize `client_password` for improved configuration. - Modified evaluation guidelines to reflect the new client password requirement. - Ensured existing logic remains intact while enhancing functionality for better user experience.
5 days ago
feat: add client password argument to multiple agents and scripts - Introduced `--client_password` argument in `run_multienv_aguvis.py`, `run_multienv_claude.py`, and `run_multienv_gta1.py` for enhanced security and flexibility. - Updated agent classes (`PromptAgent`, `AguvisAgent`, `GTA1Agent`) to accept and utilize `client_password` for improved configuration. - Modified evaluation guidelines to reflect the new client password requirement. - Ensured existing logic remains intact while enhancing functionality for better user experience.
5 days ago
feat: add client password argument to multiple agents and scripts - Introduced `--client_password` argument in `run_multienv_aguvis.py`, `run_multienv_claude.py`, and `run_multienv_gta1.py` for enhanced security and flexibility. - Updated agent classes (`PromptAgent`, `AguvisAgent`, `GTA1Agent`) to accept and utilize `client_password` for improved configuration. - Modified evaluation guidelines to reflect the new client password requirement. - Ensured existing logic remains intact while enhancing functionality for better user experience.
5 days ago
clean claude run code (#293) * add uitars agent code * improve claude * improve claude * improve claude * improve claude * improve claude * add nogdrive json * merge claude code * clean code claude run * clean code claude run * clean code claude run
2 days ago
Uitars/dev (#291) * use aws pub ip * os task fix: set the default dim screen time to be 300s * add all the uitars agents: 1. run_multienv_uitars.py: Qwen2VL-based UITARS models 2. run_multienv_uitars15_v1.py: UITARS1.5-7B 3. run_multienv_uitars15_v2.py: SeedVL1.5 thining/non-thinking --------- Co-authored-by: Jiaqi <dengjiaqi@moonshot.cn>
2 days ago
Uitars/dev (#291) * use aws pub ip * os task fix: set the default dim screen time to be 300s * add all the uitars agents: 1. run_multienv_uitars.py: Qwen2VL-based UITARS models 2. run_multienv_uitars15_v1.py: UITARS1.5-7B 3. run_multienv_uitars15_v2.py: SeedVL1.5 thining/non-thinking --------- Co-authored-by: Jiaqi <dengjiaqi@moonshot.cn>
2 days ago
Uitars/dev (#291) * use aws pub ip * os task fix: set the default dim screen time to be 300s * add all the uitars agents: 1. run_multienv_uitars.py: Qwen2VL-based UITARS models 2. run_multienv_uitars15_v1.py: UITARS1.5-7B 3. run_multienv_uitars15_v2.py: SeedVL1.5 thining/non-thinking --------- Co-authored-by: Jiaqi <dengjiaqi@moonshot.cn>
2 days ago
Add DuckTrack as initial annotation tool; Initial multimodal test
2 years ago
feat: refactor run_multienv_qwen25vl.py and qwen25vl_agent.py for improved logging and task management - Introduced signal handling for graceful shutdown of environments and processes. - Enhanced logging configuration to support dynamic log levels and structured output. - Updated argument parsing to include new parameters for model selection and task execution. - Refactored task distribution logic to streamline environment task management. - Improved error handling during task execution and environment cleanup. - Adjusted Qwen25VLAgent initialization to support new model and thought prefix options. - Reduced max tries for LLM calls to optimize performance.
10 days ago
support_qwen25vl (#276) Co-authored-by: root <ludunjie1219@github.com>
10 days ago
yuanmengqifeat: enhance run_coact.py with logging and configuration options - Added logging configuration to capture runtime logs in both file and console with adjustable log levels. - Introduced new command-line arguments for provider name, region, and client password to improve flexibility and security. - Updated process_task function to accommodate new parameters, ensuring compatibility with existing logic. - Modified prompt templates in coding_agent.py and cua_agent.py to use the client password placeholder for enhanced security. 84f407a