fikrikarim/parlor
On-device, real-time multimodal AI. Have natural voice and vision conversations with an AI that runs entirely on your machine. Powered by Gemma 4 E2B and Kokoro.
Language: HTML
#apple_silicon #gemma #kokoro #litert_lm #local_llm #mlx #multimodal #on_device_ai #python #real_time #speech_recognition #text_to_speech #voice_assistant
Stars: 1183 Issues: 3 Forks: 114
https://github.com/fikrikarim/parlor

Keychron/Keychron-Keyboards-Hardware-Design
All the industrial design files for Keychron keyboards and mice. Includes CAD models (case, plate, stabilizer, encoder, keycap) for Q, Q Pro, Q HE, K Pro, K Max, K HE, V Max, P HE series and M1–M7 mice. 100+ models. STEP/DXF/PDF formats. This project is source-available. Commercial use is strictly prohibited.
Language: Python
#3d_printing #cad #gaming #gaming_keyboard #gaming_mouse #hardware_designs #keyboard #keyboard_firmware #keychron #mechanical_keyboard #mouse #qmk #qmk_firmware #zephyr #zmk #zmk_firmware
Stars: 1310 Issues: 4 Forks: 99
https://github.com/Keychron/Keychron-Keyboards-Hardware-Design

mattmireles/gemma-tuner-multimodal
Fine-tune Gemma 4 and 3n with audio, images and text on Apple Silicon, using PyTorch and Metal Performance Shaders.
Language: Python
Stars: 1068 Issues: 8 Forks: 61
https://github.com/mattmireles/gemma-tuner-multimodal

hilash/cabinet
AI-first knowledge base and startup OS
Language: TypeScript
Stars: 1003 Issues: 14 Forks: 95
https://github.com/hilash/cabinet

PrathamLearnsToCode/paper2code
Agent skill to turn any arxiv paper into a working implementation
Language: Python
#agent #claude_code #skills
Stars: 813 Issues: 1 Forks: 104
https://github.com/PrathamLearnsToCode/paper2code

garrytan/gbrain
Garry's Opinionated OpenClaw/Hermes Agent Brain
Language: TypeScript
Stars: 3293 Issues: 10 Forks: 362
https://github.com/garrytan/gbrain

phuryn/claude-usage
A local dashboard for tracking your Claude Code token usage, costs, and session history. Pro and Max subscribers get a progress bar. This gives you the full picture.
Language: Python
#claude_code
Stars: 818 Issues: 9 Forks: 118
https://github.com/phuryn/claude-usage

Houseofmvps/codesight
Universal AI context generator. Saves thousands of tokens per conversation in Claude Code, Cursor, Copilot, Codex, and more.
Language: TypeScript
#ai #claude #cli #code_analysis #codebase #codex #context_engineering #copilot #cursor #developer_tools #llm #mcp #repo_map #token_savings
Stars: 813 Issues: 0 Forks: 76
https://github.com/Houseofmvps/codesight

wxtsky/CodeIsland
Language: Swift
Stars: 803 Issues: 12 Forks: 89
https://github.com/wxtsky/CodeIsland

yizhiyanhua-ai/fireworks-tech-graph
Claude Code skill for generating production-quality SVG+PNG technical diagrams. Supports 8 diagram types, 5 visual styles, and deep AI/Agent domain knowledge.
Language: Shell
Stars: 1150 Issues: 0 Forks: 85
https://github.com/yizhiyanhua-ai/fireworks-tech-graph

nashsu/llm_wiki
LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from your sources。
Language: TypeScript
Stars: 739 Issues: 7 Forks: 93
https://github.com/nashsu/llm_wiki

xtclovver/RKNHardering
Language: Kotlin
Stars: 688 Issues: 10 Forks: 35
https://github.com/xtclovver/RKNHardering

kessler/gemma-gem
Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine.
Language: TypeScript
#ai #chrome_extension #gemma4 #gemma4_2b #gemma4_agent_skills #llm
Stars: 648 Issues: 6 Forks: 60
https://github.com/kessler/gemma-gem

joeynyc/hermes-hudui
Web UI consciousness monitor for Hermes — the AI agent with persistent memory
Language: Python
Stars: 750 Issues: 6 Forks: 79
https://github.com/joeynyc/hermes-hudui

AgriciDaniel/claude-obsidian
Claude + Obsidian knowledge companion. Persistent, compounding wiki vault based on Karpathy's LLM Wiki pattern. /wiki /save /autoresearch
Language: Shell
#ai #claude_code #claude_code_skill #knowledge_management #obsidian #open_source #second_brain
Stars: 746 Issues: 2 Forks: 71
https://github.com/AgriciDaniel/claude-obsidian

vyfor/rattles
🪇 Minimal terminal spinners for Rust
Language: Rust
#animation #cli #no_std #ratatui #rattles #rust #spinner #spinners #terminal #tui
Stars: 680 Issues: 1 Forks: 13
https://github.com/vyfor/rattles

coleam00/claude-memory-compiler
Give Claude Code a memory that evolves with your codebase. Hooks automatically capture sessions, the Claude Agent SDK extracts key decisions and lessons, and an LLM compiler organizes everything into structured, cross-referenced knowledge articles - inspired by Karpathy's LLM Knowledge Base architecture.
Language: Python
Stars: 630 Issues: 11 Forks: 170
https://github.com/coleam00/claude-memory-compiler

momenbasel/PureMac
Free, open-source macOS cleaner. CleanMyMac alternative with zero telemetry. Native SwiftUI, scheduled auto-cleaning, Xcode/Homebrew/system cache cleanup. MIT licensed.
Language: Swift
#cache_cleaner #cleanmymac #cleanup #disk_cleaner #disk_space #homebrew #mac_utility #macos #macos_app #macos_cleaner #macosx #native #oss #osx #privacy #swift #swiftui #system_cleaner #xcode_cleaner
Stars: 1153 Issues: 17 Forks: 54
https://github.com/momenbasel/PureMac

hexiecs/talk-normal
Make any LLM talk like a normal person. A system prompt that removes AI slop.
Language: Shell
Stars: 757 Issues: 0 Forks: 18
https://github.com/hexiecs/talk-normal

obdev/littlesnitch-linux
Open Source components of Little Snitch for Linux
Language: Rust
Stars: 655 Issues: 3 Forks: 21
https://github.com/obdev/littlesnitch-linux