Millisecond decisions, any domain: a 0.8B open "System 1" model that picks between your options with calibrated probabilities. One base, swappable LoRA adapters, on your own hardware.
Repository Index
94,845 visible repositories in the index
73–96 of 130 · Most stars
Training Sparse Autoencoders on Language Models
Fine-tune Gemma 4 and 3n with audio, images and text on Apple Silicon, using PyTorch and Metal Performance Shaders.
Not just another ChatGPT user-interface!
- chatgpt
- chatgpt-api
- electron
- javascript
📎 Clippy, now with some AI
FireRed-Image-Edit is a powerful image editing foundation model achieving open-source state-of-the-art performance with precise instruction following, high-fidelity generation, superior identity consistency, and seamless multi-element fusion.
The fastest AI Chatbot for any LLM
A Docker-powered service for PDF document layout analysis. This service provides a powerful and flexible PDF analysis service. The service allows for the segmentation and classification of different parts of PDF pages, identifying the elements such as texts, titles, pictures, tables and so on.
An open-source, local-first writing workspace where you can write with Claude Code and Codex, drawing on your own sources and past work.
- ai-agents
- document-search
- electron
- local-first
A simple mesh network communications app powered by the Reticulum Network Stack.
- lora
- lxmf
- offgrid
- reticulum
An elegent pytorch implement of transformers
OpenTelemetry Instrumentation for Agent Observability
GPU-accelerated force graph layout and rendering
- graph
- network
- force
- simulation
The simplest way to run Alpaca (and other LLaMA-based local LLMs) on your own computer
Trace-native CI/CD for AI agents — production failures become regression tests that block the PR. Auto-detect, cluster, freeze into hermetic cases, replay in CI for $0.
- ai-agents
- ci-cd
- evals
- llm-evaluation
LLM model quantization (compression) toolkit with HW acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU, Tenstorrent, Huawei Ascent NPU, and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.
- gptq
- optimum
- peft
- quantization
TeleChat: 🤖️ an AI chat Telegram bot can Web Search Powered by GPT-5, DALL·E , Groq, Gemini 2.5 Pro/Flash and the official Claude4.1 API using Python on Zeabur, fly.io and Replit.
MyoSuite is a collection of environments/tasks to be solved by musculoskeletal models simulated with the MuJoCo physics engine and wrapped in the OpenAI gym API.
- machine-learning
- motor-control
- mujoco
- musculoskeletal
An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, Lark or DingTalk.
AttackGen is a cybersecurity incident response testing tool that leverages the power of large language models and the comprehensive MITRE ATT&CK framework. The tool generates tailored incident response scenarios based on user-selected threat actor groups and your organisation's details.
- ai-security
- cybersecurity
- generative-ai
- incident-response
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
- ai-infra
- attention
- inference-acceleration
- llm
Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.
- agent-harness
- ai-agent
- multi-provider
- rust
A curated list of awesome AI assistants. Example Telegram bot with all these assistants can be tested on the link below.
- awesome-ai
- awesome-gpt
- awesome-gpts
- awesome-list
NotaGen: Advancing Musicality in Symbolic Music Generation with Large Language Model Training Paradigms