Harnesses & SDKs

Python library that builds a tree index of long documents and has an LLM reason through it to retrieve answers, without a vector database or chunking.

AI application runtime framework for backends with structured outputs, observable actions, MCP capabilities and recoverable workflows.

Python SDK for deploying agents to Amazon Bedrock AgentCore, a managed runtime with memory, gateway, tools and observability.

Python SDK for building agents on Google Antigravity and Gemini, with the agent loop handled by the runtime.

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.

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.

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.

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.

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

Lightweight Python framework for composing AI agents and tools as small, typed pieces built on Instructor and Pydantic.

Python and TypeScript SDK that gives an AI agent a phone number, with pluggable LLM, speech and telephony providers.

Python framework for structured LLM outputs and agentic workflows built from tasks, agents and threads.

Open-source reinforcement learning framework that trains LLM agents on multi-step tasks using GRPO.

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