FreeAIRepo

The database of free AI tools on GitHub

23,066 open-source AI repos. Find a free alternative to any paid AI tool, or see what developers are talking about.

More filters

15 repos · showing 1–15

QwenLM/Qwen

Access and use Alibaba Cloud's Qwen large language models for chat and text generation.

22kupdated 7mo ago
LLMs & chat
Really freeCommercial OK · Apache-2.05.8 GB VRAMPython
BlinkDL/RWKV-LM

RWKV-7 is a linear-time RNN language model for large-scale inference and chat applications.

15kupdated 27d ago
LLMs & chat
Really freeCommercial OK · Apache-2.07 GB VRAMPython
OpenMOSS/MOSS

An open-source conversational language model supporting Chinese and English.

12kupdated 1mo ago
LLMs & chat
Really freeCommercial OK · Apache-2.07.8 GB VRAMPython
BlinkDL/ChatRWKV

Open-source chatbot powered by RWKV RNN language model.

9.5kupdated 3mo ago
LLMs & chat
Really freeCommercial OK · Apache-2.03 GB VRAMCPU only OKPython
LearningCircuit/local-deep-research

AI research assistant for deep, agentic research using local LLMs and search engines.

9.4kupdated today
LLMs & chat#78 TRENDING
Really freeCommercial OK · MIT8 GB VRAMRuns on MacCPU only OKPython
jingyaogong/minimind-v

Train a 65M-parameter visual-language model in 2 hours.

8.8kupdated 1mo ago
LLMs & chat
Really freeCommercial OK · Apache-2.08 GB VRAMPython
PrismML-Eng/Bonsai-demo

Run Bonsai 2 language models locally for chat, vision, and tools.

3.4kupdated today
LLMs & chat
Really freeCommercial OK · Apache-2.02 GB VRAMRuns on MacCPU only OKShell
balisujohn/localwriter

A LibreOffice Writer extension that adds local-inference generative AI features.

183updated 8mo ago
LLMs & chat
No license8 GB VRAMRuns on MacPython
virtuehearts/HiveMind

HiveMind Protocol - A Local-First, Privacy-Preserving Architecture for Agentic RAG

148updated 7mo ago
LLMs & chat
No license6 GB VRAMTypeScript
roandejager/Hillock

Local, gradient-free neuro-symbolic memory engine combining Hyperdimensional Computing (HDC/VSA), Hebbian plasticity, and graph triples for offline AI.

144updated 15d ago
LLMs & chat
Really freeCopyleft · AGPL-3.01.2 GB VRAMRuns on MacCPU only OKPython
nickzsche21/AirClaw

Run OpenClaw on a local model. Zero API cost. One OpenAI-compatible endpoint over Ollama, llama.cpp, vLLM or LM Studio — plus AirLLM for models bigger than your GPU.

118updated 1mo ago
LLMs & chat
Really freeCommercial OK · MIT4 GB VRAMPython
ManuelSLemos/RabbitLLM

Run 70B+ LLMs on a single 4GB GPU — no quantization required.

87updated 8mo ago
LLMs & chat
Commercial OK · Apache-2.04 GB VRAMRuns on MacPython
edgett/PalmHill.BlazorChat

PalmHill.BlazorChat is a chat application and API built with Blazor WebAssembly, SignalR, and WebAPI, featuring real-time LLM conversations, markdown support, customizable settings, and a responsive d

72updated 8mo ago
LLMs & chat
No license8 GB VRAMC#
DUNKINKKD/lotei-qflipper

🐬 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.

65updated 3mo ago
LLMs & chat
Really freeCopyleft · GPL-3.06 GB VRAMCPU only OKC++
TheLastOxygen/mafdet

You type. It already knows. Local LLMs that read and think while you type.

54updated 2d ago
LLMs & chat
Commercial OK · Apache-2.06 GB VRAMCPU only OKPython