When to use this category
- Build assistants that call tools and APIs.
- Create repeatable research, coding, or operations workflows.
- Coordinate planner, worker, reviewer, and verifier roles.
- Evaluate how different frameworks handle memory and state.
Agent frameworks, system prompts, subagent configurations, tool calling, MCP servers, and plugin ecosystems.
Agent frameworks help developers coordinate model calls, tools, memory, planning, and execution loops. The best fit depends on whether you are prototyping, orchestrating multiple agents, or shipping a controlled workflow inside a product.
6 repositories sorted by GitHub stars. Use the interactive explorer for live filters.
A programming framework for agentic AI
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
LangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agents and RAG easy. It integrates seamlessly with enterprise Java frameworks like Quarkus and Spring Boot.
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework