Harnesses & SDKs

Open-source Python and TypeScript SDK for model-driven agents, with tools, MCP, multi-agent patterns and streaming.

Open-source SDK that connects AI agents to app front ends with chat UI, generative UI, shared state and human approvals; creator of the AG-UI protocol.

Open-source agent harness that runs the model loop for you, with MCP tools, skills, sandboxing, approvals and a chat UI.

TypeScript toolkit for agents with Zod-typed tools, graph and multi-agent workflows, and Node.js or browser runtimes.

Python and TypeScript framework for multi-agent systems, with MCP and A2A interop, YAML orchestration and OpenTelemetry tracing.

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

Open-source toolkit for building, evaluating and deploying agents in Python, TypeScript, Go, Java and Kotlin, tuned for Gemini but model-agnostic.

Open-source framework that routes each user query to one of several AI agents, with Python, TypeScript and Swift runtimes.

TypeScript framework for AI agents with tools, memory, RAG, MCP and sub-agents, paired with a Cloud or self-hosted console.

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

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.

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

Framework for AI agents and multi-agent networks where a router picks which agent runs, with tools and MCP support.