Harnesses & SDKs

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

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

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

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

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

SDK for browser agents with act, observe and extract calls, used from TypeScript and Python to automate sites and pull out structured data.

Go framework for LLM applications with chat-model agents, multi-agent coordination, graph workflows and human-in-the-loop resume.

Go implementation of LangChain for writing LLM-based programs from composable building blocks.

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

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

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

Open framework for building and hosting production-grade AI agents and multi-agent workflows in .NET and Python.

Go framework for AI agents with memory, tool execution, MCP, agent skills, multi-agent patterns and evaluation.

Go framework for multimodal AI agents with models, tools, memory, middleware, chains and structured output.