🎙️ AI-powered Telegram bot for voice-to-text transcription using OpenAI Whisper. CPU-only, no GPU required, privacy-focused with local processing.
DeepSeek V4 Flash prompt engineering + Flux free image generation. Zero cost, no GPU, China-friendly AI image workflow.
No-GPU 3D scanning from phone rotation videos — pure geometry, no neural networks, no cloud
Run local LLMs & build a knowledge base on an old computer or low-spec PC - no GPU, no API key, offline, privacy-first. ｜ SynomosAI skill - medxpert-llm-library - (c) 2026 SynomosAI - MIT
Cascade MoE: a CPU-only expert system that turns plain-language sysadmin and networking questions into shell commands. No GPU, no cloud, no external model weights. Russian-first: 80% of held-out Russian queries answered with a working command, 38% in English. Patent pending. The benchmark that measures it ships with the source.
Zero-memory, multi-core-CPU local AI training for ordinary laptops.
Change text in scanned documents & photos using the document's own letters — typewriter, printed fonts, handwriting. Python + OpenCV, no GPU.
CPU-trained reasoning model pipeline. LoRA SFT + DPO on SmolLM2-360M, GSM8K math reasoning, single-laptop deployment.
Free offline AI voice generator for Windows. One-click installer, no GPU, no API key, no account. Powered by Kokoro-82M - paste a script, get a 24 kHz WAV voiceover. Runs on any laptop CPU. Unlimited, private, no subscription.
Pixel-perfect click coordinates for AI agents. Vision models miss by 30–40 px; OCR + template matching land on the exact pixel. Pure-CPU screen automation — no GPU, no cloud API, no token cost.
Extract burned-in (hardcoded) bilingual subtitles from video into SRT on any CPU - then let AI proofread every line against the actual frames. No GPU, no API key, offline. 视频硬字幕提取 + AI 逐帧校对
无独显笔记本跑 30B 代码模型：ik_llama.cpp + MoE 量化，纯 CPU 13.67 tok/s，OpenAI 兼容、断网可用、零 API 费用 | CPU-only local LLM on Windows, no GPU needed
Training-free deepfake and face-swap detection. Explainable forensic analysis of images and video — no model download, no GPU, runs offline. The inverse of deepfakes/faceswap.
CPU/边缘优先的轻量本地推理服务：OpenAI 兼容 API、内存自适应量化降级、完全离线，无需 GPU | Lightweight CPU/edge-first local LLM inference server, OpenAI-compatible API, no GPU needed.
Free code for the Same State Guide, a setup guide for building your own Human AI Brain. What I call a Human AI Brain is AI that recalls your own notes and drafts the work, with a safety check and your approval. Runs on your own computer, no GPU needed. Apache-2.0.
Python ctypes binding for LC Runtime — CPU-native, bit-exact, no-GPU inference. Companion to bracoTuxbr/local-coherence.
To associate your repository with the no-gpu topic, visit your repo's landing page and select "manage topics."