Harnesses & SDKs

Open-source framework that builds, evaluates and self-improves multi-agent LLM workflows from a goal.

Python framework that models an application as a state machine, with a trace UI and persisted state.

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

Python framework for LLM apps built from collaborating agents that hold conversation state, tools and vector-store memory.

Python and TypeScript SDK and REST Agent Server for building agents that work with code in local or containerized workspaces.

Python framework for LLM agents that run as durable Dapr workflows, with retries, Kubernetes deployment and human-in-the-loop hooks.

Archived Microsoft Python framework for multi-agent apps; Microsoft directs new users to Microsoft Agent Framework.

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

Python library for autonomous agents that run scheduled tasks and exchange messages on the Fetch.ai network.

Python framework for multi-agent applications where agents with defined roles talk through explicit flows, built on the OpenAI Agents SDK.

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

Python runtime and framework for long-running agents, with durable sessions, approvals, spend caps and multi-agent collaboration.

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

Library for LLM post-training (SFT, DPO, GRPO and agentic RL) and classic RL, with evolutionary hyperparameter optimization.

Python SDK for building agents on Volcengine AgentKit, with a bundled Web UI, Studio deployment and short- and long-term memory.

Lightweight Python agent framework for long-running tasks, with skills, sub-agents, A2A and ACP servers, and CLI, TUI and web front ends.

Python multi-agent framework with PEER and DOE collaboration patterns and configurable LLM vendors such as Qwen, DeepSeek and OpenAI.

Minimal Python graph framework of about 100 lines for LLM agents, workflows, RAG and map-reduce pipelines.

Python agent framework for OpenAI-compatible agents with tools, memory, MCP connections, multi-agent collaboration and workflows.

Python platform that gives agents a cryptographic identity, A2A communication and x402 payment requirements behind one bindufy() call.

PyTorch-style Python framework for multi-agent, multi-session workflows, with a durable production runtime in v2.0.0.

Low-code Python framework for YAML-defined agents and multi-agent Cogs, with personas, prompt templates and memory nodes.

Python framework for autonomous agents that work in a sandboxed workspace, and task agents with tools and MCP support.

Python framework for MCP-based agents with composable workflow patterns, MCP server creation and Temporal-backed durable execution.