Harnesses & SDKs

Rust multi-agent framework with typed tool calling, sliding-window memory, pluggable LLM backends and OpenTelemetry tracing.

Event-sourced Python graph runtime where agent behaviors react to a shared graph, with an audit trail and fork-and-diff replay.

Open-source NVIDIA library that connects existing agents to tools and data, with profiling and LangSmith tracing; deprecated, EOL end of 2026.

Cross-platform C++ DAG framework with a Python version, for running task graphs with no third-party dependencies.

Reinforcement-learning trainer of about 3,500 lines that trains models behind agents run in their own harnesses, locally or as Kubernetes jobs.

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

Reliability layer for tool calling with self-hosted LLMs, offered as a proxy, a workflow runner and middleware.

Open-source Python evaluation framework with ready-made and custom graders for scoring AI agent quality and producing reward signals.

Python library of 35 agentic AI architectures with one run() interface, built on LangGraph and multiple LLM providers.

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

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

Rust framework with an agent harness, typed task graphs and streaming indexing and RAG pipelines for LLM applications.

XState library where agent logic is a state machine, so a model can only pick events the machine allows.

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

Python framework for durable AI agents built as dataflows that resume after crashes, retry safely and record each step.

Python framework for customer-facing conversational agents that narrows the prompt context each turn using rules, knowledge and tools you define.

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

Python library for steering language models by constraining output with regex and grammars and mixing control flow with generation.

Typed Python toolkit for composing classic and agentic retrieval-augmented generation pipelines with pluggable LLMs and stores.

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

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

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

Open-source Python framework for text and voice assistants; the open-source edition is in maintenance mode while Rasa moves to its CALM engine.

JavaScript framework for multi-agent teams whose tasks move across a Kanban-style board you can watch.