OpenAI's privacy filter NER model architecture implemented in a minimal C++/GGML runtime

Offensive knowledge, offline. One search box for every playbook.

The new generation chameleon based on NRF52840 makes the performance of card emulation more stable. And gave the chameleon the ability to read, write, and decrypt cards.

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

Soul-driven AI agent with permission-hardened tools, token budgets, and multi-channel access. Runs 24/7 from CLI or Telegram.

Garry's Opinionated OpenClaw/Hermes Agent Brain

Surf the supersonic tsunami.

The agent that grows with you

QVAC - Local AI SDK and libraries for building private, cross-platform, peer-to-peer AI applications. Run LLMs, speech-to-text, translation, and more locally on Linux, macOS, Windows, Android, and …

Window management made elegant.

Peer side mirror manager

qwen running locally in your browser

Run Pear app from app p2p with pear:// link

Native process spawning for JavaScript

Synchronize files from link to dir peer-to-peer or from-disk

Create and manage daemon processes in JavaScript

Template repository for creating Pear applings

monospace typeface designed for symbol-rich programming

Awesome Pears

Official implementation of "Continuous Autoregressive Language Models"

🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.

Peer that is blind

Universal multi-language runner and smart REPL written in Rust.

Open-source implementation of Imagine with Claude

A blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

Checkpoint-engine is a simple middleware to update model weights in LLM inference engines

App Eraser is a Free and Open Source macOS app removal tool.

The best open-source alternative to Superwhisper & Wispr Flow. Voice-to-text app for macOS with no subscription