“deployment”

Python framework for generative AI agents, pipelines and parallel workflows, with RAG engines, tools, memory and swappable drivers.

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

Open-source LLM function calling framework for AI agents, with serverless LLM tools and geo-distributed infrastructure.

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

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

Python runtime for agent apps with tool sandboxing and streaming agent APIs; archived, with features moved to AgentScope 2.0.

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

Python framework for data labeling agents that learn skills from a ground-truth dataset through iterative feedback.