Lora: open-source projects on GitHub
67 repositories on Lora, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
LlamaFactory: Unified LLM Tuning
LlamaFactory offers a unified library for efficient fine‑tuning of 100+ LLMs and VLMs, with support for LoRA, QLoRA and distributed multi‑GPU training.
★ 71,186 · PythonAIRLLM: 70B Model on 4GB GPU
Running huge LLMs on weak hardware. AirLLM enables inference of 70B models on a single 4GB GPU.
★ 42,461 · Jupyter NotebookPEFT: Efficient AI Training
The PEFT library provides state-of-the-art parameter-efficient fine-tuning methods for models, reducing resources and training time.
★ 21,199 · Pythonms-swift: LLM training
A framework for fine-tuning 600+ language and 300+ multimodal models. Supports PEFT, full fine-tuning, CPT/SFT/DPO/GRPO.
★ 14,178 · PythonSoup: Train LLM Easily
Soup fine-tunes an LLM from a single YAML using a streaming layer — enabling an 8B model to run on a laptop with 4 GB VRAM.
★ 10,552 · PythonOUMI EASY LLM TUNING
OUMI lets you quickly fine‑tune (SFT/RL), evaluate, and deploy Qwen, Gemma, and any open agentic LLM/VLM without extra complexity.
★ 9,433 · PythonMetaClaw: learning agent
MetaClaw is a simple way to talk to an AI agent that learns on the fly during conversation and continuously improves its behavior. Written in Python, it has a modular str
★ 3,370 · PythonXTRUING: PERSONALIZE YOUR LLM
xTuring simplifies creating and personalizing your own LLMs: from data preparation to fine‑tuning. The tool supports adapters, ready‑made pipelines and model export. Join
★ 2,681 · PythonAI Film Studio on TensorFold
Plan films with crew workflows, generate images with Qwen-Image/FLUX and videos with MiniMax H3 on TensorFold runtime for Mac and NVIDIA DGX Spark.
★ 1,087 · PythonTensorFold AI Film Studio
Plan films with Slate workflow, generate Qwen-Image/FLUX images and MiniMax H3/FastH3 videos with sound on Mac or NVIDIA DGX Spark via TensorFold.
★ 1,055 · PythonHALO: FRAMEWORK FOR LLM TRAINING
Halo is an open-source framework from White Circle for training large language and multimodal models. It supports agent-based training, async-RL, distributed training, an
★ 862 · PythonOVERMIND: PLATFORM FOR AI AGENTS
Overmind — platform for the continuous improvement of AI agents: automated evaluation, fine‑tuning and integration with LLM operations. It allows tracking metrics, runnin
★ 759 · PythonAI Engineer Notebooks
A practical collection of framework-free Jupyter notebooks for learning AI engineer skills: model APIs, structured output, tool calling, RAG, evaluation, agents, fine-tun
★ 749 · Jupyter NotebookFact memory via LoRA
Hypernetworks that allow language models to memorize factual data via LoRA. For AI research and model fine-tuning.
★ 726 · PythonComfyUI Tools and Tests
The repository contains ready-made ComfyUI workflows, benchmark configs, and utilities for local inference on four RTX 3090s.
★ 699 · HTMLRandOpt: Task Experts Optimization
Code for ICML 2026: diverse task experts are densest around pretrained weights.
★ 590 · PythonOpen Character File Format
The .char format bundles face, body, wardrobe, and voice into a single portable file for consistent characters across any AI model.
★ 585 · PythonAcoustic Drone Detector
Detects drones by listening for propeller sounds using a microphone, enabling detection of silent fiber‑optic FPV aircraft that emit no RF signal.
★ 474 · CWorld Action Model Toolkit
Provides a unified Python framework for training, fine-tuning, and evaluating World Action Models (WAMs) with modular components and standard APIs.
★ 411 · PythonLoRA Dataset Studio
A self‑hosted, single‑page environment for the full LoRA workflow: create character/concept/style datasets, curate, caption, remove watermarks, train locally or in the cl
★ 357 · PythonPMETAL: THE ACCEL LLM ON APPLE SILICON
PMetal — Rust framework for high‑performance LLM inference on Apple Silicon. Supports local inference, LoRA/QLoRA fine‑tuning, serving, quantization, and MLX/Metal accele
★ 333 · RustHUD-Python RL Evaluation
An OSS environment for RL with ready‑to‑use agent evaluation tools. Run, configure, and get results.
★ 329 · PythonMix-Studio: AI Workspace
Mix-Studio provides a clean, responsive interface for running finely tuned image and video workflows based on ComfyUI — directly from your PC or smartphone. No complex in
★ 304 · JavaScriptFonaTech Chronos
The Chronos project achieves zero‑latency Mixture‑of‑Experts inference via lookahead prediction and asynchronous DMA prefetch from SSD, plus GPU‑optimized kernels. Hybrid
★ 299 · PythonPortable ESP32-P4 SDR Scanner
Standalone handheld SDR scanner for ESP32-P4 with RTL-SDR/LR2021 support, decoding P25, ADS-B, POCSAG, FM/AM plus LoRa mesh and GPS.
★ 295 · COrcSDR Portable SDR
OrcSDR is a portable Software Defined Radio receiver based on M5Stack Tab5 and RTL-SDR Blog V4, operating without a PC connection. It displays spectrum and waterfall, and
★ 283 · C++phi - Simple Phi-4 Launch
Run the powerful multimodal Phi-4 model directly on your Mac with Apple Silicon — no cloud, no complex setup.
★ 280 · Jupyter NotebookBUILD YOUR AI INTRANET
Autonomous grid unites your computers into a single infrastructure for running AI models: training, fine‑tuning and inference. Supports distributed computing, fine‑tuning
★ 278 · PythonAnima Reference Image Adapter
ComfyUI node for character and style transfer from reference images to Anima using offset-RoPE and LoRA.
★ 238 · PythonLight fine-tuning of LLM assistants
Zero-friction fine-tuning of any LLMs for Claude Code, Gemini CLI, and ACP agents: from environment setup to training (LoRA, SFT, DPO, GRPO) with NVIDIA and Apple Silicon
★ 237 · PythontheDAW: AI Music Studio
theDAW combines generation, editing, mixing, and live visuals in a unified environment for creating music with AI. The project is designed for producers, DJs, and visual
★ 237 · TypeScriptRemiqora: AI Music Studio
Remiqora combines the ACE-Step 1.5 and YuE2-3B models in a single Vue interface, enabling text-to-music generation, stem separation, MIDI transcription, LoRA fine-tuning,
★ 225 · VueLLM Alignment Tuning
Automatic calibration of the language model's censorship layer via direct weight modification and the use of LoRA and MoE experts.
★ 221 · PythonUltrasonic drone detector
batear — a drone detection system using ultrasonic detector and edge computing to protect airspace.
★ 213 · CComfyUI Model & Workflow Browser
Browse models with Civitai covers and trigger words, find missing models in workflows, search outputs by prompt or LoRA, and manage workflows with undo history.
★ 204 · JavaScriptTyped Decisions With Probabilities
Open-weight Python model that outputs typed decisions with probabilities in one forward pass. Apache-2.0 licensed weights and code.
★ 168 · PythonWeight-Direction One-Step Image Synthesis
Official PyTorch implementation of the efficient CVPR 2026 one-step image synthesis method with weight direction.
★ 158 · PythonLoRA Fine-Tuning Sprint
Project accelerates LoRA fine-tuning by fixing task and hardware, and posts results to a public wall-clock leaderboard based on modified nanogpt.
★ 151 · PythonLoRa Base Station
Open LoRa base station for Meshtastic/MeshCore on Raspberry Pi with SX1302/SX1303: passive multi-channel capture, local panel, and native forwarding.
★ 144 · PythonGalahad: Blindness Research
The Galahad project studies instruction blindness in vision-language-action policies, offering diagnostics and a low-rank data correction method. It includes a paper, mod
★ 142 · PythonViggle-Animate H3 ComfyUI Nodes
Adds ComfyUI nodes to run the Viggle-Animate minimax H3 fine-tuned model for video generation.
★ 140 · PythonSystem 1 Model Framework
Framework to train, test, and serve System 1 decision models on language and multimodal platforms.
★ 137 · PythonNSFW Content Creation Plugin
Purge-compatible DeepSeek Harness plugin for creating adult images, voiced videos, and multi-shot films with self-hosted models, reference editing, LoRA control, and agen
★ 133 · TypeScriptMeshCore Touch Firmware
Custom MeshCore companion firmware with touch UI for multiple LoRa boards. Compatible with official MeshCore apps.
★ 131 · PythonBlackBox Mesh AI Node
Autonomous mesh node with local AI, TAK integration, and Bitcoin Cashu payments based on Meshtastic. Fully offline solution for mesh networks.
★ 130 · JavaScriptMultimodal Image Retrieval System
Practical multimodal image retrieval with intent recognition, prompt engineering, Qwen LoRA, EmbeddingGemma 2, InfoNCE contrastive learning, and RAG components.
★ 129 · PythonHands-On LLM Full-Stack Course
Comprehensive tutorial implementing LLMs from scratch: builds Transformer in PyTorch, reproduces Pretrain/SFT/LoRA/DPO/GRPO on single GPU, covers PEFT/Agent/RAG with real
★ 124 · PythonVoxCPM2 TTS for ComfyUI
The VoxCPM2 module adds speech generation in ComfyUI for 30 languages with voice settings, voice cloning, and LoRA adapter training for personalization.
★ 115 · PythonLocal AI Film Studio
Run a full AI film studio locally with recurring characters, video generation, voices, music, and a timeline editor. Includes 214 MCP tools for AI agent control.
★ 104 · JavaScriptOffline Tourist Safety
The heard project implements an offline group safety network for hikers based on ESP32, GPS, and LoRa, including a firmware‑in‑the‑loop simulator and 3D trajectory viewer
★ 89 · PythonLocal AI Video Studio
Open-source video creation suite running locally on ComfyUI. Train characters, direct 3D scenes, sketch-to-video, and restore footage using only open-weight models.
★ 79 · TypeScriptRose — PyTorch Optimizer
Stateless PyTorch optimizer that normalizes gradients for stable and balanced model training.
★ 60 · PythonEasy Stable Diffusion Tuning
njgymb/diffusers-sculptor offers a fast, flexible framework for fine‑tuning Stable Diffusion through simple configuration files, lowering resource demands.
★ 56 · HTMLAutomatic LoRA Docker Pipeline
The project automates building Docker images for training LoRA models in Alibaba Cloud, providing a CI/CD pipeline, GPU support, and publishing to a container registry.
★ 55 · HTMLImage AI Generator 2026
Powerful desktop application for creating high-quality images, photorealistic renders, and creative concepts using AI.
★ 52ComfyUI Nodes for Open-H3-Regenerate
Provides ComfyUI nodes, workflows, and a converted LoRA for the Open-H3-Regenerate-2K-IC model.
★ 49 · PythonHiDream O1 nodes for ComfyUI
HiDream O1 nodes for image generation and LoRA training in ComfyUI pipelines on Python.
★ 46 · PythonTraining GPT for $50
The project shows how to train your own GPT-like model on a $50 budget using accessible cloud resources and open-source code.
★ 45 · PythonPoseidon M5Stack Firmware
The Poseidon firmware turns the M5Stack Cardputer-Adv into a multifunctional device with Wi‑Fi, BLE, sub‑GHz, LoRa, BadUSB and various attack capabilities, and includes s
★ 40 · C++LabLLM on macOS
LabLLM is a native macOS app where you can build the architecture of a tiny language model, train its weights, and see the model emerge from scratch on Apple Silicon usin
★ 39 · SwiftNew projects on this topic in Telegram
Telegram →