model-hub

transformers

Python

95

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

personal-model

Python

87

Build your HUMAN.md.

world-model-optimizer

Python

82

An open source model gateway that provides one control plane across closed, open-source, local, and custom models.

improve

85

Use your most capable model to audit your codebase and write plans for cheaper models to execute.

Codex-Orchestration

Python

72

Bring any model to Codex, assign them any role, use them in /goal or any workflow.

tau-0-vla

Python

82

This repo is the official implementation of "τ0-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation".

ComfyUI

Python

95

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

muscriptor

Python

85

A multi-instrument music transcription model developed by Kyutai and Mirelo.

TurboVLA

Python

77

TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

Boogu-Image

Python

72

Boogu-Image-0.1 is an Apache-2.0 open-source image generation and editing model family that delivers near-closed-source performance with an order of magnitude less data.

agent-as-a-router

TypeScript

67

The official implementations of Agent-as-a-Router: Agentic Model Routing for Coding Tasks.

ComfyUI-Spectrum-MiniMax-H3

Python

82

Spectrum-based acceleration for ComfyUI’s native MiniMax H3 audio-video model. Forecasts post-transformer features with Chebyshev ridge regression to skip selected transformer evaluations, with adaptive scheduling, sampler-aware safeguards, CPU/VRAM history storage, and native fallbacks.

open-sheet

TypeScript

77

The spreadsheet framework built for agents — write the model as React, export a live .xlsx. The third medium, after open-slide and open-doc.

hflow

Python

80

SDK for robotics teams to verify the quality of their data used for AI model training.

dify

TypeScript

100

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

LocalAI

Go

100

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

img2threejs

Python

95

Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.

maka

TypeScript

90

Apache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and termination events are recorded as an append-only log.

open-science

TypeScript

90

Open Science is an open-source, local-first, model-agnostic AI research workbench for reproducible scientific research on macOS, Windows, and Linux.

Soup

Python

90

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

klaatcode

TypeScript

85

Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, cutting costs 10x. Supports Claude, GPT, Gemini, DeepSeek & more.

brain2qwerty

Python

80

Non-invasive decoding of typed sentences from MEG and EEG brain recordings using a convolutional encoder, transformer, and character-level language model.

apex-inference-chip

Python

68

An inference chip design that runs a real LLM (Qwen2.5-0.5B) on FPGA — one transformer decoder layer in RTL, every silicon value bit-exact against a golden model. 0.56 tok/s measured, a 140× climb, full evidence trail.

Audar-ASR-V1

Python

68

Arabic-first generative speech recognition — Audar-ASR-V1 (Flash + Turbo). #1 on the Open Universal Arabic ASR Leaderboard. Model cards, benchmarks & inference.

sloptrim

Python

77

A local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model.

unlazy

JavaScript

95

Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.

lift

Python

72

Extract structured data from documents quickly and accurately.

Audio8_TTS

Python

82

SOTA-Class TTS at Compact Scale

kimi-k3-mlx

Python

62

MLX port of moonshotai/Kimi-K3 (2.78T multimodal MoE): streaming converter, REAP expert pruning, and per-language expert-overlap analysis

Token-Saver

Python

72

A local Claude Desktop extension to query large PDFs with 92–98% fewer tokens. Performs local hybrid search, cites exact page numbers, and keeps your documents private on your machine

doc7

Go

82

Turn documents into AI-ready Markdown with visual understanding

generative-ai-for-beginners

Jupyter Notebook

100

21 Lessons, Get Started Building with Generative AI

deepseek-reasonix

Go

95

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

fx

Zig

90

Unix like coding agent

OpenChatCut

TypeScript

90

Open-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.

looper

Python

77

Design visual, review-gated agent loops for Claude Code before you run them.

shard

Python

72

Pipeline-parallel LLM inference across GPUs on separate machines.

labs-OO-Agents

Python

90

NVIDIA Object Oriented Agents: the Pythonic way to build AI Agents.

SCAIL-2

Python

82

Official Implementation of SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning

MAGI-2-preview

Python

82

MAGI-2-preview: Scaling Video Generation Models Efficiently

kimodo.cpp

C++

72

Animate skeletons with natural language; NVIDIA's Kimodo ported to C++/GGML

factory

Shell

68

A reference software factory for Claude Code and Codex

gemma-chat

TypeScript

67

Local AI chat + coding agent for Apple Silicon, powered by Gemma 4 via MLX / Supports Ollama

fablize

Python

75

A Claude Code plugin that makes Opus behave like Fable — completion, evidence, and verification enforced as procedure. Ships only what a Fable-vs-Opus comparison proved transferable.

deltafin

Rust

72

Run full Kimi K3 on a single device. And an OpenAI-compatible API server for local chat and coding agents.

cursed_browser

Swift

45

True AI-Native Browser — a VLM reads the HTML and hallucinates the page.

Unlimited-OCR

Python

85

Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.

trueforge

TypeScript

90

The open-source agent harness - the runtime layer that turns an LLM into a working agent.