Harnesses & SDKs

Open-source online code execution system that runs submitted code in a sandbox behind an HTTP JSON API.

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

Reinforcement learning framework for training reasoning LLM agents over multi-turn episodes with the StarPO algorithm.

Open-source infrastructure for continually self-improving agents that serves requests, learns from feedback and versions updates.

YAML-driven Python robot simulator for navigation, control and learning research, with collision detection and a Matplotlib renderer.

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

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.

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.

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 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.

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.

Python framework for LLM applications built on Qwen models, with function calling, MCP, a code interpreter and RAG options.