Master Repo For PearAI
Repository Index
132,241 visible repositories in the index
25–39 of 39 · Most stars
PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.
Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3.8, Muse-Glimmer, Nemotron, LFM2.5, Ornith-1.0, ternary Bonsai-27B.
- apple-silicon
- claude-code
- codex
- dflash2
Local AI talk with a custom voice based on Zephyr 7B model. Uses RealtimeSTT with faster_whisper for transcription and RealtimeTTS with Coqui XTTS for synthesis.
- chatbot
- python
- realtime
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
- avx2
- c
- cpu-inference
- gguf
Faster than your agent alone. And better. A workflow plugin that takes a bug, idea or ticket to a verified pull request: specs, cross-model review by risk, live QA, receipts in your repo. Claude Code · Codex · Cursor · Droid · Grok Build · OpenCode · Muse Code.
- claude-code
- execution
- marketplace
- planning
Your personal AI assistant, running on your own computer. Long-running tasks, real memory, proactive help, voice, phones and smart glasses. Any model, local or cloud. No account.
138 bilingual AI marketing skills (69 VN + 69 Global) for Claude Code, OpenCode, Codex, VS Code. Four role SOP packs — content, design, performance, leader ops — plus strategy, personal brand, AI avatar, dropshipping, design master, knowledge library. 4 regions (US/EU/SEA/LATAM) + Vietnam 2025-2026. Companion: opa-kit.
Ollama for classical ML models. AOT compiler that turns XGBoost, LightGBM, scikit-learn, CatBoost & ONNX models into native C99 inference code. One command to load, one command to serve. 336x faster than Python inference.
- c99
- catboost
- compiler
- decision-trees
Transcribe and translate voice into LRC file using Whisper and LLMs (GPT, Claude, et,al). 使用whisper和LLM(GPT,Claude等)来转录、翻译你的音频为字幕文件。
- faster-whisper
- lyrics
- lyrics-generator
- openai-api
Library for faster pinned CPU <-> GPU transfer in Pytorch
- cpu-pinned-tensors
- pytorch-variables
- gpu-transfer
- cuda-variables
Human + AI music production workflow for Suno - skills, templates, and tools
- claude
- claude-code
- claude-code-plugin
- claude-code-plugin-marketplace
Sales & Dungeons — Thermal Printer as D&D / TTRPG Utility
- dnd-tools
- thermal-printer
- dnd5e
- dungeons-and-dragons
A Playwright-based Node.js tool that bypasses search engine anti-scraping mechanisms to execute Google searches. Local alternative to SERP APIs with MCP server integration.
- ai
- google-search
- llm
- mcp-server
TranslatedAn AI avatar for real-time voice/text conversations with idols from "The iDOLM@STER Shiny Colors": original Japanese voice + Chinese subtitles, recalling the original story, memory shared across characters; supports Google/GitHub login and bring-your-own key, one-command deployment with Docker Compose (inspired by LAPLACE Eidolon)
- ai-companion
- character-ai
- fastapi
- idolmaster