潜力新星（90天）

Your agent seeks what search can't find. A self-hosted perception MCP server that transcribes speech, reads behind logins, sees images and video frames, crosses languages, and remembers.

Fully local AI for Polish legal case files - zero fabricated citations by construction. Free; please support a Wroclaw animal shelter instead.

Operational doctrine for practical AI systems design.

Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

Local-first CLI that reads your Spec-Driven Development artifacts and recommends the best value-for-money AI model to implement them. Powered by Ollama — your specs never leave your machine.

AI-powered mock interview simulator for Tech & Behavioral rounds. Master German & English job interviews using the STAR method in complete privacy before taking real offers.

Local-first AI research assistant: plans sub-queries, searches the web, and writes fully cited reports. LangChain + LangGraph multi-agent + FastAPI + Next.js, with email-OTP auth and per-user Postgres storage.

Local-first video-to-notes CLI for YouTube/Bilibili transcripts, Whisper fallback, timestamped AI summaries, and Notion/Obsidian export.

Sparse-upcycle a dense Gemma-3-270m into a Mixture-of-Experts (gemma3moe) and serve it on llama.cpp (CPU). Upcycle, train, inspect routing, GGUF.

Evano Studio is an open-source local AI desktop app for agents, automation, knowledge, and productivity.

Agent skill that rewrites rough prompts into polished, model-specific prompts — grounded in the official Anthropic prompting guides

Unify every AI agent on ONE local shared memory over MCP. Obsidian vault + gbrain (by Garry Tan) + Ollama. 100% offline, $0 API. Orchestrate with OpenClaw or Hermes.

Claude skill for generating and beautifying resumes — 11 print-ready HTML templates, structured data pipeline, three entry flows (beautify / LinkedIn import / chat interview).

🤫 Token-lean sessions at the harness level. An easy to grasp output style, output-shrinking hooks, and log compression cut both input and output tokens.

Screenplay breakdown & AI prompt-pack studio — import a script, get scenes, elements, bibles, shot lists & a timeline, then export self-executing prompt packs for any LLM and any video/image generator. No API keys.uggested Donation of $30 if you you can to help me keep making these tools.https://ko-fi.com/samwasserman

Stop agents from designing sloppy UI. Inspired by Impeccable, but without the plugin machinery. Just one SKILL.md file.

Voice input that transcribes what you said, grounded in what's on your screen. macOS, Windows, Android, iOS.

DeepSeek Harness (DSH) 插件：✨ 提示词一键增强 + 💬 语音识别（说完自动停·云端/本地双引擎）· 附 🔁 服务异常一键重启

该项目是无人机的租赁系统，也可以是其他的设备、器材租赁，技术栈：Java 21 + Spring Boot 3.5.13 + Vue 3 + Spring AI + MCP + AI Memory，其他的技术栈Dify/Coze、 Python LangChain/LangGraph Agent 。项目是开源的，免费学习的，star支持一下，不断更新中。

A reasoning skill for AI agents to improve complex judgment, premise auditing, counterargument pressure, and verifiable conclusions.