Repository Showcase
A curated collection of interesting GitHub repositories
THUDM/AgentBench
Benchmark evaluates LLMs as agents
Related repos
- Framework for reproducible benchmarking of web agents
- monitor and debug AI agents, track LLM costs, integrate with frameworks
- Unified environment for developing and testing LLM agents with feedback
- Multi-agent framework for building collaborative LLM applications
- Framework for evaluating LLM agents in Factorio
- Upgrade LLM APIs to agent APIs with real-time output, knowledge base access, web search, and advanced MCP and research features
- Curated list of LLM apps built with RAG and AI agents using models from OpenAI, Anthropic, and others
- Pairing LLM agent for machine learning engineering
- Open source AI agents for learning and building with Live Agent Studio
- platform for building and deploying LLM-powered AI agents with plugins and tools
