The database of free AI tools on GitHub
22,947 open-source AI repos. Find a free alternative to any paid AI tool, or see what developers are talking about.
123 repos · showing 91–120
PokeClaw (PocketClaw) — first on-device AI that controls your Android phone. Gemma 4, no cloud, no API key. Poke is short for Pocket.
jevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices and scores with probabilities, on your laptop's CPU.
Custom ComfyUI Nodes for interacting with Ollama using the ollama python client.
Active Learning for Text Classification in Python
🏗️ Fine-tune, build, and deploy open-source LLMs easily!
A desktop app for running Large Language Models locally.
On-device LLM Inference Powered by X-Bit Quantization
To know what models don't say out loud.
Compute Node of Dria Knowledge Network.
A Python package for converting PDFs to markdown while extracting images and tables, generate descriptive text descriptions for extracted tables/images using several LLM clients. And many more functio
GenAI & LLM usecases and applications
Local diagnostic CLI for NVIDIA DGX Spark (GB10). Detects power caps, UMA pressure, thermal risk, CUDA 13/SM_121 wheel mismatches, Docker issues, and validates vLLM/Ollama/llama.cpp/SGLang recipes.
A simple to use Ollama autocompletion engine with options exposed and streaming functionality
Local, gradient-free neuro-symbolic memory engine combining Hyperdimensional Computing (HDC/VSA), Hebbian plasticity, and graph triples for offline AI.
Run Open Source/Open Weight LLMs locally with OpenAI compatible APIs
GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.
PasLLM - LLM inference engine in Object Pascal (synced from my private work repository)
An offline coding agent for local models. One command sets up the best model your GPU can run, and on 24 GB+ RTX 30/40/50-series cards Qwen3.8-27B runs up to 1.9x faster than llama.cpp.
Self-hosted meeting notes with no bot in the call. Records Meet, Teams and Zoom from the browser, transcribes on your own hardware, and lets Claude or ChatGPT read and edit your library over MCP.
This repository provides code and resources for automating manufacturing feature recognition in CAD designs using vision-language models.
Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option. 0.8B GGUF on CPU, Jev-style API.
Open-source AI text detector and ChatGPT detector: 23 engines, one calibrated score, every number measured on a public benchmark. Self-hosted, runs on CPU.
GGUF Loader with its Agentic Mode, and floating button, ai Models | Open Source & Offline. Mistral, Deepseek, llama, gemma, qwen
CPU-only, pure-Rust implementation of LiquidAI's LFM2.5-8B-A1B LLM
🐬 A pink qFlipper fork with LOTEI — a 100% local AI dolphin (Ollama) that chats, talks, watches your Flipper's screen, and one-click-installs custom firmware.
A production-grade control layer that sits between your application logic and any LLM — input validation, schema enforcement, circuit breaking, targeted retry, and audit logging in one composable pipe
Minimal CPU-only Ollama Docker Image
A GPT built and trained in 243 lines of pure, dependency-free Python - no PyTorch, no NumPy. Based on Andrej Karpathy's microgpt, it hand-rolls autograd, attention and Adam to show how little a langua
.NET samples for LM-Kit.NET
You type. It already knows. Local LLMs that read and think while you type.