Harnesses & SDKs

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

Python SDK for multi-agent workflows with handoffs, guardrails, sessions and built-in tracing, usable with OpenAI and other LLMs.

Open-source Python framework for multi-agent systems: agent societies, memory, RAG, code interpreters, synthetic data and large-scale simulation.

Open-source Python framework for AI agents that cooperate on tasks, with human-in-the-loop workflows and multi-agent patterns.

Sample projects for the Strands Agents SDK, showing how to build agents in Python and TypeScript; not intended for production use.

TypeScript SDK for persistent AI agents on Cloudflare Durable Objects, with state sync, scheduling and MCP support.

Kotlin and Java framework for AI agents with tools, graph workflows, MCP, streaming and multiplatform targets.

OpenAI-compatible agentic API server for inference, vector stores, files and skills, on any model or infrastructure.

Python SDK for tracing agents and scoring their traces with prompt-based judges, to find failures in production.

JVM framework for agentic flows that plan toward goals, mixing LLM calls with code and domain models, usable from Kotlin or Java.

Ruby AI framework with one API for chat, tools, agents, streaming, embeddings and Rails integration across many providers.

CLI-first Python agent framework and coding agent with MCP, A2A and Agent Skills support, live streaming and human input.

Python toolkit for signed identities, verifiable credentials and delegated authority for AI agents, with MCP and REST interfaces.

Embeddable version control system for files and SQL tables, with branch, diff, merge and rollback across both.

Quarkus extensions that connect LangChain4j to Quarkus apps, with declarative AI services and LLM, tool and embedding support.

TypeScript and JavaScript framework for multi-agent workflows with tools, handoffs, guardrails, sandboxes and voice agents.

TypeScript framework and product stack for autonomous agents, with a plugin system, persistent memory, a CLI, an app and cloud services.

Lightweight Python framework and starting template for agents that let the model choose its own approach to each task.

TypeScript agent framework on a Rust runtime, where runs are checkpointed, replayed with zero LLM calls and resumed after a crash.

Official Python implementation of the Universal Tool Calling Protocol, calling HTTP, CLI, MCP and text-file tools through plugins.

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

Python framework for generative AI agents, pipelines and parallel workflows, with RAG engines, tools, memory and swappable drivers.

All-in-one Python AI framework for embeddings-based semantic search, LLM pipelines, workflows and agents.

TypeScript SDK with reference implementations of Hashgraph Consensus Standards and a Registry Broker client.