“Python”

Experimental Python library that teaches agent handoffs on the Chat Completions API; OpenAI now points users to its Agents SDK.

Kubernetes-native framework and runtime for building and running AI agents as Kubernetes custom resources.

Open-source reinforcement learning framework that trains LLM agents on multi-step tasks using GRPO.

Open-source platform for voice agents that place and answer phone calls through Twilio or Plivo with pluggable speech and LLM providers.

Open-source online code execution system that runs submitted code in a sandbox behind an HTTP JSON API.

Open-source NVIDIA library that connects existing agents to tools and data, with profiling and LangSmith tracing; deprecated, EOL end of 2026.

Lightweight Python framework for LLM agents built as PyTorch-style layers, with agent memory kept as session state.

Opinionated agent harness on LangGraph with sub-agents, filesystem access, context management, persistent memory and approval of tool calls.

AI application runtime framework for backends with structured outputs, observable actions, MCP capabilities and recoverable workflows.

Browser infrastructure for AI agents: local and cloud Playwright-based browser sessions, scraping and deployable browser functions.

Open-source framework for real-time multimodal conversational AI, with RTC and WebSocket voice assistant examples.

Policy enforcement, identity, sandboxing and reliability tooling for autonomous AI agents, installable with one pip command.

Open-source framework that builds, evaluates and self-improves multi-agent LLM workflows from a goal.

Library for LLM post-training (SFT, DPO, GRPO and agentic RL) and classic RL, with evolutionary hyperparameter optimization.

Reinforcement learning framework for training reasoning LLM agents over multi-turn episodes with the StarPO algorithm.

Open-source infrastructure for continually self-improving agents that serves requests, learns from feedback and versions updates.

Reinforcement-learning trainer of about 3,500 lines that trains models behind agents run in their own harnesses, locally or as Kubernetes jobs.

Reliability layer for tool calling with self-hosted LLMs, offered as a proxy, a workflow runner and middleware.

Multi-interface agent framework with tools, memory and MCP, serving agents through Telegram, Discord, Twitter, Farcaster and a REST API.

Framework for developing, evaluating and benchmarking web agents on BrowserGym benchmarks, with parallel runs through Ray.

Java library with one API over LLM providers and vector stores, plus tools, RAG and integrations for Quarkus and Spring Boot.

Node.js distribution of the LiveKit Agents framework for realtime voice agents in LiveKit rooms.

Framework for building, running and evaluating autonomous agents, with a planner-based multi-agent mode, skills and agent RL training.

Java library for stateful, multi-agent LLM applications built as cyclical graphs, designed to work with langchain4j and Spring AI.