Search awesome repositories

An extensible, state-of-the-art framework for columnar compression, and the fastest FOSS columnar file format. Formerly at @spiraldb, now an Incubation Stage project at LFAI&Data, part of the Linux Foundation.

Foundation Architecture for (M)LLMs

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid.

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure

[EMNLP-2024] Build multimodal language agents for fast prototype and production

Comprehensive resources on Generative AI, including a detailed roadmap, projects, use cases, interview preparation, and coding preparation.

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.

A playground of highly experimental prompts, Jinja2 templates & scripts for machine intelligence models from OpenAI, Anthropic, DeepSeek, Meta, Mistral, Google, xAI & others. Author: Alex Bilzerian (2022-present).

Fast Multimodal LLM on Mobile Devices

Self-hosted Personal AI + agent runtime in .NET (NativeAOT-friendly)

MCP server for OpenRouter — chat with 300+ LLMs (Claude, Gemini, GPT), analyze images / audio / video, generate images / speech / music / video (Veo 3.1, Sora, Seedance, Wan) from Claude Desktop, Cursor, Kiro, VS Code.