Harnesses & SDKs

Minimal TypeScript agent harness with an agent runtime, multi-provider LLM API, terminal UI and coding agent CLI that users extend themselves.

Open-source Python toolkit for RAG and agents over your own data, with event-driven workflows and 300+ integration packages.

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

Multi-language SDKs for embedding the GitHub Copilot agent runtime, with planning, tool calls and file edits, in your apps.

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.

Rust library for LLM applications with agents, tool calling, streaming and 20+ model providers, plus a terminal coding agent.

Open-source Firebase framework for AI features and agent workflows in JavaScript, Go, Python and Dart, with model plugins.

Open-source agent harness for stateful agents whose memory persists and improves with use, with a terminal UI, app server and TypeScript SDK.

Code-first Go toolkit for building agents with a tool ecosystem, composable multi-agent systems and Cloud Run deployment.

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

Java framework for distributed, long-running agents with typed event streams, permission gating, middleware and subagents.

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

DSPy-style toolkit for typed LLM signatures, agents and flows, TypeScript-first with Python, Java, C++, Go and Rust libraries.

Java runtime for AI agents that streams tokens and tool events over WebSocket, SSE or gRPC, with human approvals.

TypeScript SDK for streaming chat, tool-calling agents and structured output across model providers and UI frameworks.

Python framework of interoperable components and integrations for building agents and LLM apps, with LangGraph and Deep Agents layered above it.

Python framework for multi-agent teams and workflows, with a CLI and Docker, MCP and A2A deployment options.

Low-level Python orchestration framework for long-running stateful agents, with durable execution, human review points and short- and long-term memory.

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.

Python framework for writing language-model programs as code and optimizing their prompts and weights instead of hand-tuning prompts.

TypeScript framework for AI agents and apps with graph-based workflows, memory, suspend-and-resume approvals, MCP servers and model routing.

Typed Python SDK for building agents with swappable model providers, plus optional capabilities for memory, sub-agents, planning and durable execution.

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