camel-ai / crabLinks
🦀️ CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/
☆386Updated last week
Alternatives and similar repositories for crab
Users that are interested in crab are comparing it to the libraries listed below
Sorting:
- An open platform for enhancing the capability of LLMs in workflow orchestration.☆182Updated 8 months ago
- [ICLR 2025] A trinity of environments, tools, and benchmarks for general virtual agents☆220Updated 5 months ago
- This is a collection of resources for computer-use GUI agents, including videos, blogs, papers, and projects.☆464Updated 3 weeks ago
- An open-source framework for collaborative AI agents, enabling diverse, distributed agents to team up and tackle complex tasks through in…☆783Updated 2 months ago
- AI for all: Build the large graph of the language models☆277Updated last year
- Code for Husky, an open-source language agent that solves complex, multi-step reasoning tasks. Husky v1 addresses numerical, tabular and …☆346Updated last year
- [ICML2025] Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction☆371Updated 8 months ago
- Beating the GAIA benchmark with Transformers Agents. 🚀☆138Updated 9 months ago
- AWM: Agent Workflow Memory☆359Updated 10 months ago
- Building Open LLM Web Agents with Self-Evolving Online Curriculum RL☆479Updated 5 months ago
- 👩⚖️ Coding Agent-as-a-Judge☆672Updated 6 months ago
- ☆640Updated 3 weeks ago
- Multi-Faceted AI Agent and Workflow Autotuning. Automatically optimizes LangChain, LangGraph, DSPy programs for better quality, lower exe…☆266Updated 6 months ago
- The evaluation benchmark on MCP servers☆226Updated 3 months ago
- Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhi…☆658Updated 2 months ago
- A repo with an automated prompt engineering workflow from scratch. It leverages the OPRO technique.☆202Updated last year
- A LLM-based Agent that predict its tasks proactively.☆445Updated 3 months ago
- ☆853Updated 3 months ago
- AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and re…☆479Updated this week
- SkillWeaver is a framework to enable web agent self-improvement through environment exploration and skill synthesis.☆99Updated 7 months ago
- Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.☆792Updated 7 months ago
- Code for ScribeAgent paper☆64Updated 9 months ago
- ☆314Updated last year
- OS-ATLAS: A Foundation Action Model For Generalist GUI Agents☆401Updated 7 months ago
- Integrating Tool Use into LLM Reasoning☆695Updated 9 months ago
- OpenCUA: Open Foundations for Computer-Use Agents☆582Updated last week
- [EMNLP 2025] OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking☆469Updated 3 months ago
- Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving☆394Updated 3 months ago
- [ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents☆284Updated 4 months ago
- [NeurIPS 2025] Atom of Thoughts for Markov LLM Test-Time Scaling☆597Updated 2 weeks ago