潜力新星（90天）

小红书图文笔记 Agent Skill，支持看图理解、主动提问、智能选题、实时热梗搜索、标题正文、标签评论钩子和风险检查。

Why is LLM inference slow — and how do you make it fast? A hands-on, first-principles course: roofline → KV cache → quantization → parallelism → vLLM/SGLang, with GPU labs on open models.

Free, local voice dictation for Windows and Mac. Hold a key, speak, your words appear at the cursor. On-device Whisper, no cloud, no account, no telemetry.

soundcore Work（安克 AI 录音豆 / D3200）本地管理 App：BLE 配对连接、录音管理、AI 实时转写、Wi-Fi SoftAP 批量导出

Proxima lets existing GPUs serve 4x more concurrent requests

a smol tool for managing local models

Private, on-device AI meeting notetaker that runs entirely in your browser — live transcription, speaker ID, and note extraction with no audio leaving your machine (WebGPU + WASM).

The multi-paradigm database expert for Claude Code — design a schema, audit it on two never-blended scores (Design & Integrity / Performance & Scale), and safely migrate. SQL · document · key-value · vector · time-series · graph. Works offline.

Reference Java & Spring implementation of the Open Ingestion Standard (OIS). It provides a secure, decoupled, and vendor-neutral enterprise data integration platform leveraging modern Java 25 features, Spring Boot, Spring AI and vector search infrastructure to orchestrate data flows

🎙️ Uzbek system-wide speech-to-text dictation for macOS (rubaiSTT + whisper.cpp, Metal, offline). Press Ctrl+Opt+D anywhere.

Serve Poolside Laguna S 2.1 (NVFP4) on the NVIDIA DGX Spark (GB10) without hanging your box. Working stack, crash-safe configs, benchmarks, and the exact gotchas.

Network-faithful simulation of LLM serving and training deployments

Streaming on-device speech recognition for Android — NEON-accelerated FastConformer (32M params), cache-aware streaming with 80 ms look-ahead, no cloud. Powered by the VoxRT runtime.

Let your AI agent call your phone and talk to you — MCP servers for live, interruptible voice calls + tiered alerts, using free self-hosted pieces (pjsua2 + whisper.cpp + Linphone). No paid telephony, no extra API key.

Rivo Agent is a private, local-first mobile AI assistant that runs compact GGUF language models directly on your phone. It lets users download a compatible model, chat offline, keep local memory, customize assistant behavior, and use AI privately without sending conversations to a remote inference server.

面向小团队的一站式 NLP 小模型平台:数据集版本管理 · 训练 · 评估 · 在线部署 · Badcase 闭环,内置大模型 Prompt 盲测评测(人工 + AI 双指标)。

Fast, privacy-first voice typing with streaming transcription and BYOK. 快速、隐私优先的流式语音输入工具，支持自带 API Key。

A comprehensive, production-focused guide to acing AI/ML system design interviews at top tech companies.

Open-source, Python-first RAG platform with FastAPI APIs, LangGraph-native agents, pluggable vector stores (Qdrant/Weaviate/Milvus/pgvector/Elasticsearch), and multi-provider LLM support (OpenAI/Anthropic/Gemini/Ollama/vLLM).

🎤 游戏玩家的 Windows 桌面语音输入工具 — 按住热键说话，本地流式转写，松开一键发送到游戏聊天框。Tauri 2 + Rust + sherpa-onnx，识别全程本机完成。