新秀榜（30天）

Distributed 56M-parameter LLM inference across 3 ESP32-S3 boards via ESP-NOW , Split-PLE + KV cache, fully offline.

A native macOS lab for teaching tiny language models to think — build the architecture, train the weights, and watch a small LLM emerge from scratch, locally on Apple Silicon with custom data, tokenizers, checkpoints, and MLX acceleration.

Make Claude talk like a human: 17 installable output styles for Claude Code, built on credited methodologies

A privacy-first, provider-neutral personal AI workbench with chat, memory, auditable tools, MCP, and isolated project plugins.

Real-event-anchored benchmark for detecting AI-generated videos in real-world crisis settings.

让 Agent 的工作方式可组合、可审查、可持续改进，最终实现 Agent Self Evoling。 DeepSeek Harness Web plugin with composable task controls and isolated, human-reviewed self-evolution.

Self-contained DeepSeek Harness (DSH) plugin for Provider/Auth login, model switching, image fallback, token/cost analytics, and same-port Web restart. Useful? A star helps.

Zero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.

Brevia · 言录(https://brevia.work): A minimal meeting recorder that stays on your device. Transcribe, distill with AI, remember—without the cloud. Clean interface, local storage, complete privacy. Zen-inspired design.

Local, persistent and auditable memory layer for Claude Code, Codex, Cursor & Gemini CLI. Your coding agent stops treating you like a stranger every morning.

讓 AI 用台灣人的繁體中文講話，並把已寫好的文字清掉 AI 味。Claude Code、claude.ai、ChatGPT Codex 與一般聊天都能用。

An agent that edits your Word and Excel files — then looks at them, through real Microsoft Office, to check its own work

Benchmark your local LLMs: speed, memory, and quality, in one command. TUI leaderboard for Ollama, LM Studio, llama.cpp, and vLLM.

DeepSeek V4 特化思维链引导规范：we need to 句式，任意 agent 客户端可接入（纯提示词层）

A beginner-friendly guide to building and launching apps with Base44—using plain-English prompts, practical examples, and zero coding experience.

AI short-drama story architecture, Studio routing, model-aware shot timelines, continuity, validation, and resumable workflows for Codex and Claude Code.

Agent Skills von LOGIN zur freien Nutzung - SKILL.md-Format fuer Claude Code, Claude-App und API

Open-source, self-hosted LangGraph Agent Server. Production Postgres + Redis. Same SDK. Same Studio. Zero code changes.

🕸️ E.V. — Peter Parker's homemade AI from Spider-Man: Brand New Day, running locally on YOUR PC. Voice assistant + cyber HUD, real PC control, long-term memory. Whisper + Ollama, no cloud. TR/EN.

A practical guide to AI: from running your first local model to building your own agents. 52 files covering LLMs, Ollama, RAG, prompt engineering, machine learning, AI agents, and local AI tools.