An open-source framework by Stream for building vision AI agents that work with any model or video provider, leveraging Stream's edge network for ultra-low latency video experiences.

Agent & ToolingPythonPyTorch

VIEW DETAILS →

Blades is a multimodal AI Agent framework for the Go language, supporting custom models, tools, memory, middleware, and more. It's designed for multi-turn conversations, chain-of-thought reasoning, and structured output applications.

Agent & ToolingGoAgent Framework

VIEW DETAILS →

A Python library for orchestrating zero-shot computer vision models, enabling custom end-to-end pipeline creation without needing to collect and annotate large training datasets.

Model & Inference FrameworkPythonMultimodal

VIEW DETAILS →

An open-source intelligent assistant framework for mobile devices that understands screen content through multimodal methods and performs automated operations to help users complete tasks.

Agent & ToolingPythonAgent Framework

VIEW DETAILS →

A tool that gracefully solves hCaptcha challenges using multimodal large language models, without relying on browser extensions or third-party captcha services.

Agent & ToolingPythonMultimodal

VIEW DETAILS →

Nekro Agent is an extensible multi-person interactive agent framework that combines code execution capabilities with high extensibility, featuring sandbox-driven architecture, visual interface, and multimodal interaction support across multiple platforms.

Agent & ToolingPythonDocker

VIEW DETAILS →

A groundbreaking visual AI development environment for building no-code data pipelines and multimodal agents with real-time capabilities, social connectors, and AI-powered tools.

Agent & ToolingDockerPostgreSQL

VIEW DETAILS →

A curated collection showcasing what's possible with ChatGPT Code Interpreter, featuring experiments that push boundaries and unlock creative potential through the combination of AI and code execution.

Docs, Tutorials & ResourcesPythonAI Agents

VIEW DETAILS →

Director is an AI video agents framework that can reason through complex video tasks like search, editing, compilation, generation etc & instantly stream results. It's built on VideoDB's 'video-as-data' infrastructure.

Agent & ToolingPythonNode.js

VIEW DETAILS →

AIlice is a fully autonomous, general-purpose AI agent based on open-source LLMs. Using its unique Interactive Agents Call Tree (IACT) architecture, it decomposes complex tasks into dynamically constructed agents with high fault tolerance, enabling seamless task execution and result integration.

Agent & ToolingPythonAgent Framework

VIEW DETAILS →