Aida — a fully offline, cross-platform memory + integrity runtime for local LLMs on Ollama. Won't fabricate (20%→0% confabulation); memory you own, audit, and correct.

Prove `k(I)=t`. A general-purpose framework for proving any transformation produces its canonical truth object. The substrate is opaque to domain; any verifiable proposition gets a 64-byte content-…

An extension for Visual Studio Code that adds rich language support for CodeQL

GLM-5: From Vibe Coding to Agentic Engineering

Hierarchical Reasoning Model Official Release

Playwright Test Visual Studio Code integration

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

PersonaLive! : Expressive Portrait Image Animation for Live Streaming

TermNet is an AI-powered terminal assistant that bridges a Large Language Model (LLM) with your local environment. It can safely run shell commands, search the web, and load custom tools dynamicall…

The most cost-effective, highest performance AI voice agent possible today

Automated pipeline for downloading, staging, ingesting, and investigating leaked and declassified archives (DDoSecrets, National Security Archive, WikiLeaks) using recursive RAG with LM Studio.

The official Python SDK for Z.ai's large model open interface, making it easier for developers to call Z.ai's open APIs.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Cross-platform Flask web app to preview and remove EXIF, GPS, ICC, XMP, and other metadata from images without quality loss. Supports JPEG, PNG, GIF, WebP, HEIC/AVIF, and more, with drag-and-drop b…

Matcha – brew beautiful TUIs at Swift speed.

Kimi K2 is the large language model series developed by Moonshot AI team

This repository delivers end-to-end, code-first tutorials covering every layer of production-grade GenAI agents, guiding you from spark to scale with proven patterns and reusable blueprints for re…

🦜🔗 Build context-aware reasoning applications

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Code of LHM: Large Animatable Human Reconstruction Model for Single Image to 3D in Seconds

No fortress, purely open ground. OpenManus is Coming.

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

Graph Neural Network Library for PyTorch

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Mobius: Text to Seamless Looping Video Generation via Latent Shift

Open Thoughts: Fully Open Data Curation for Thinking Models

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer