Harnesses & SDKs

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

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.

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.

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

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

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.

C# framework on .NET for building multi-agent AI bots with plugins, RAG, MCP integration and a built-in admin UI.

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

Python framework for orchestrating multiple LLM agents in sequential, concurrent, hierarchical and graph-based workflows.

Modular Python agent framework with a tool-calling loop, context management, retrieval, persistent memory and MCP tools.

Go framework for multi-agent systems with graph workflows, tools, session memory, MCP, A2A, AG-UI and OpenTelemetry.

PHP framework for agentic applications with workflows, human-in-the-loop, MCP connectors, RAG and multi-provider LLM support.

Model-agnostic SDK for building agents and multi-agent systems in Python, .NET and Java; Microsoft names Agent Framework as its successor.

Python framework for real-time voice and vision agents that process video with pluggable models and processors over WebRTC.

Python framework for agents that discover MCP tools by themselves, with optional memory, guardrails, cache and tracing.

Code-first Java toolkit for building and testing AI agents, with multi-agent hierarchies, a dev UI and Maven packages.

Python interface for running and evaluating agents from several frameworks, with OpenTelemetry traces; now in soft deprecation.

TypeScript library that lets agents call MCP and UTCP tools by running model-written code in a sandbox.

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