潜力新星（90天）

Free, open-source voice dictation for Windows, macOS, Linux & Android — hold a hotkey, speak, and cleaned-up text lands in whatever app you're in. Bring your own Groq key.

给 DeepSeek 补上「眼睛和耳朵」的多模态视觉插件：看图 / OCR / 物体检测 / 视频理解 / 语音转写 / 截图直读，一键安装（DSH 插件）。

中文网文写作工具包 · Chinese web-novel writing toolkit (23 skills) — a Claude Code plugin, also works in ChatGPT / DeepSeek / Gemini

AI skill for rewriting machine-generated text to sound human-written across 9 languages - 5-stage pipeline: cleanup → specificity → tone → rhythm → proofread.

Pixel-native visual RAG ported to Rust on the ruvector ANN substrate (HNSW + IVF-Flat) — screenshot/document retrieval over visual embeddings, a Rust port of PixelRAG, with a metaharness benchmark CLI: npx rupixel

Build & prompt Qwen3.x agents in their native dialect — extracted from qwen-code & Qwen-Agent

Methodology + templates for a trustworthy, traceable, self-growing AI data-analyst agent: metrics-first, independent read-only validation, and a self-growing rule library.

Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embeddings, RAG and vector search. No Python, no HTTP microservices, no Docker sidecars.

Open-source Codex plugin for Sol-governed multi-agent coding, bounded AI code review, model routing, and LLM cost optimization

On-device voice transcription. Your audio never leaves your phone.

A browser game to learn prompt engineering by playing — explore a world and solve challenges by writing prompts. Techniques from OpenAI, Anthropic, Google & xAI, each cited.

A curated skillstack for AI agents. Make your AI code editor write code like a Tech Lead. Stop copy-pasting instructions. Install 794 expert rules, workflows, and custom personas in Cursor, Claude Code, and Windsurf with one CLI command.

High-fidelity Claude Fable 5 (Mythos) environment emulation and automated multi-agent jailbreak (Pack Hunt) research laboratory.

Multimodal foundation model predicting transcriptome-wide virtual spatial transcriptomics from histology.

GLM-5.2 (744B/40B MoE) on a 4× DGX Spark / GB10 (sm_121) cluster: portable Triton sparse-MLA kernels, a data-free expert prune, MTP draft, and a one-script bootstrap.

Self-hosted voice for coding agents. Talk from any browser or a Telegram call, interrupt mid-sentence, clone any voice, and hand real work to agents that ship PRs. Local STT/TTS; real-time voice client for ACP.

CareerDesk: Your Personal Career Assistant

Aileron Protocol: A strict system harness override enforcing deterministic AI behavior through codebase-first execution, strict token economics, and rigorous debugging limits.

Interview questions and prep for AI Engineer, LLM Engineer, and Applied AI roles. Built for software engineers breaking into AI and ML practitioners levelling up: company-specific question sets, role-based study maps, worked answers, and from-scratch coding challenges.

Make AI text sound human - rules + a Claude Code skill, built for Russian, works for English too.