Tools tagged: researchers

AutoGen

✓

Microsoft's multi-agent conversation framework for complex AI workflows

AutoGen is Microsoft's open-source framework for building multi-agent AI systems. Version 0.4 (early 2025) introduced a major architectural redesign with an event-driven foundation, segmenting the framework into distinct components: AutoGen-Core, AgentChat, AutoGen-Extensions, and a rebuilt low-code AutoGen Studio. It enables specialized agents to collaborate on complex tasks through async conversations with human-in-the-loop capabilities. Features superior scalability, observability, and cross-language support for Python and .NET.

LangChain

✓

Framework for building LLM applications with chains, agents, and RAG

LangChain is the leading open-source framework for building applications with large language models. It provides composable components for chains, agents, memory, and tool use, making it easy to build complex AI applications. With support for RAG (Retrieval Augmented Generation), multi-agent systems, and production-grade deployments via LangSmith, LangChain is the foundation for thousands of AI applications worldwide.

LangGraph

✓

Graph-based framework for building stateful, multi-step AI agents

LangGraph is a specialized framework from LangChain for building stateful, multi-step AI agents with complex workflows. Using graph-based architecture, LangGraph enables branching logic, conditional workflows, and persistent state management. Perfect for building sophisticated AI agents that need to handle complex decision trees and multi-step reasoning with full control over execution flow.

OpenAI Codex

✓

The AI model that powers GitHub Copilot - Evolving into an Agent

OpenAI Codex was the original AI model capable of translating natural language to code, powering tools like GitHub Copilot. While the original standalone API was deprecated in 2023, the 'Codex' brand was revived in late 2025 as an autonomous software engineering agent. OpenAI continues to release specialized coding models under the Codex lineage, such as GPT-5.1-Codex, ensuring it remains at the forefront of AI code generation.

StarCoder 2

✓

State-of-the-art open-access code LLM by BigCode

StarCoder 2 is a family of open-access Large Language Models for code, developed by BigCode (Hugging Face & ServiceNow). Released in February 2024, it comes in 3B, 7B, and 15B parameter sizes. Trained on The Stack v2 (4 trillion tokens), it offers state-of-the-art performance, transparency, and a 16K context window, making it a powerful tool for code completion and generation.