潜力新星（90天）

Streaming ASR, audio captioning and speech QA over a whisper-style encoder with pluggable LLM backends

Production-grade recipe for DeepSeek-V4-Flash-0731 (284B MoE) on 2x NVIDIA DGX Spark: self-healing 2-node vLLM cluster, reboot-verified, tuned DSpark speculative decoding (~75 tok/s), full benchmarks, OpenAI Codex CLI integration

Local LLM chat app for Apple Silicon Macs.

Search knowledge by what documents mean and how they look — not one or the other.

Self-hosted, OpenAI-compatible speech server: faster-whisper STT and Piper/Kokoro TTS. A local voice backend for Open WebUI, CLIs, and custom agents.

Real-time meeting & audio transcription for Windows (system audio + mic) — live captions via Deepgram, AI summaries via OpenAI. Tauri 2 + React.

Run the LLM Swarm Router on machines to distribute Local Ai to the Swarm - More Machines - MORE SPEED

VL-JEPA inspired pipeline — compress images/text locally via Ollama, send compact payloads to any LLM API. Cut token costs by ~80%.

Local-first desktop assistant for the whole job hunt — scrape listings, match with a local LLM, generate applications in your own voice, and track everything on a Kanban board.

LLM-free, layout-aware PDF chunking for RAG pipelines. Preserves document structure via regex and font heuristics. Written in pure Rust.

🚁 Can Vision-Language Models Think from the Sky? UAVReason for Aerial Reasoning and Generation

OpenAI-compatible reverse proxy for free multimodal AI APIs (chat / images / videos / audio / 3d)

Local, real-time system-audio captioner + translator for macOS — Whisper + a local LLM + a glass overlay. Fully offline.

Open-source desktop client for the xAI Grok API — chat, image & video generation, voice, and an agentic coding module with local file access. Bring your own key, no telemetry.

A fine-tuning SDK — any open model, any harness, any method. 12 training methods behind one argument; pure-stdlib core.

Don't write a bug report — record it. Local MCP: screen recording → transcript, frames, OCR, wall-clock evidence for coding agents.

Talk to your coding agents — press a hotkey, speak your prompt, and it lands in Claude Code, Codex, or Cursor. Fully local voice dictation (Parakeet + Gemma), nothing leaves your machine. Windows, macOS & Linux.

Locally fine-tuned Russian RAG models: document splitter, query expansion, retrieval embedder. Teacher distillation → GGUF → llama.cpp on AMD Vulkan. Commercial-OK licenses.

Writing that's kin to yours

Local-first, capability-aware, traceable audio and video transcription Skill for Codex