ServiceNow/AgentLab
Framework for reproducible benchmarking of web agents
View on index · View in 3D Map
Related repos
- Benchmark evaluates LLMs as agents
- Framework for agents to use computers and code
- Control coding agents with an HTTP API
- Browser agent for planning and executing tasks via natural language
- AI agents for internet research and task execution
- monitor and debug AI agents, track LLM costs, integrate with frameworks
- LangChain-based toolkit for building and running AI agent services
- Library for benchmarking multi-agent reinforcement learning algorithms
- Markdown for developing and evaluating AI agents
- Framework for AI agents with verifiable compute
