潜力新星（90天）

Self-hosted voice assistant. Speak to your computer: it answers aloud, types your dictation, and operates your apps.

Full-stack LiveKit voice agent starter: a Python voice worker, FastAPI token server, and React frontend. Run, deploy, and swap each piece on its own. Ask for ShipVoice pro

[ECCV 2026 Oral] Official Pytorch implementation for See & Sniff: Learning Visuo-Olfactory Representations

Train linear embedding adapters with triplet loss to align retrieval embeddings with your queries (RAG).

VideoNote：视频链接 → 结构化笔记。理解画面/弹幕/评论；支持主流平台；工具解耦；多格式导出。

Blazing fast Go port of gemini-web2api. Convert Google Gemini web into OpenAI-compatible API. Zero cost, single static binary.

Open-source local implementation of MiniMax H3 Context-IR. Turn simple prompts into structured, validated H3 video briefs.

Publication-quality LLM architecture figures from config.json — Raschka-style towers, diffs, posters, VRAM math. No weights needed.

Light-MER for efficient multimodal emotion recognition with sub-1B MLLMs.

Self-hosted, private family AI health steward. Multimodal AI structures health data into a person-centric profile with dashboard & AI consultation (Feishu/Lark integration). 开源可私有化部署的家庭 AI 健康管家：多模态大模型 + 健康画像看板 + AI 咨询 + 飞书渠道。

Distributed peer-to-peer LLM inference. Your prompt never leaves your device in clear text.

Speak. It types. Typex is an open-source, desktop AI voice input tool.

面向开发者与初学者的 nano-vLLM 交互式源码教程 - 通过 13 个 HTML 互动实验 + 13 章中文教程理解大模型推理引擎

Local-first macOS dictation and meeting transcription app

Uncensor Qwen 3.8 27B with a pre-baked system pack for Ollama, plus GGUF download links.

Use your X Premium or SuperGrok subscription in pi.

Open-source, voice-first AI mock interviewer. Upload your CV + a job description, practice out loud with an adaptive multilingual interviewer, get scored and coached on your weak areas. LiveKit · LangGraph · Next.js

Deterministic, read-only static auditor for GGUF models: behavioral chat-template backdoors + SSTI, tokenizer, config, and model-card surfaces - never renders, never loads weights. 192,032 repos, 137,698 templates analyzed, 0 reviewed false-positive FAILs.

Truthful scheduler-step and streaming visualization for local LLM inference

100% local video dubbing on your desktop — dub videos in your own voice. Private AI dubbing with no cloud, no uploads, no time-stretching.