“Python”

Python library and API that uses LLMs to extract structured data from websites and local documents.

Python framework for live data processing and RAG pipelines that run on a Rust engine.

Durable orchestration for data, ML and agent workflows, written as Python functions.

Runs open models locally or in the cloud, with a REST API and Python and JavaScript libraries.

Open-source browser agent in Python, plus a hosted cloud with stealth browsers and an agent API

Open-source AI gateway with a Python SDK that calls 100+ LLM providers through the OpenAI format.

Lightweight self-hosted personal agent framework in Python with a WebUI, chat-app channels, memory and MCP

Open-source visual builder for AI agents and workflows, with Python-customizable components and deployment as an API or MCP server

Unified inference platform for deploying and scaling AI models on any cloud, with an open-source Python serving framework.

Open-source Python framework from Microsoft for finding risks in generative AI systems through red teaming.

Memory system for agents that captures, structures and retrieves memories, with a Docker backend and Python client.

Open-source Python library for adding programmable guardrails to LLM-based conversational applications

Python tool that scans MCP servers and their tools for security findings using YARA, LLM and AI Defense analysis.

Open-source multi-agent coding system from the HKU Data Intelligence Lab, written in Python

Open-source library that optimizes LLM and visual generation inference with specialized kernels and a Python framework.

Source-available, self-hosted platform for AI agent flows, with a visual editor, Python nodes and persistent agent memory.

Open-source Python framework for building temporal knowledge graphs that AI agents can query.

Open-source terminal AI agent that runs shell, Python and web tools on any model, including local ones.

Lightweight terminal coding assistant with a tool loop and TUI, offered as TypeScript, Python and Rust versions

Python terminal coding agent with DeepSeek by default, MCP tools, sub-agents, approval prompts and reusable learned skills

Python rebuild of Claude Code with multi-agent teams, output-compression filters, a nano mode and a web UI

Python framework with input and output guards that detect LLM risks, plus structured output generation

Python framework for LLM-powered agents, built on the Dapr distributed systems runtime.

Code sandboxes built from Docker-image snapshots for running agent and model-generated code, with Python and TypeScript SDKs.