Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

TypeScript-to-Native Compiler

Dahrk edge client - deliberate nodes that run deterministic multi-stage agent workflows per Linear issue

The most RAM efficient harness

Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents

AirPods liberated from Apple's ecosystem.

[ECCV 2026] Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings

Sudoku Solver using Z3

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills b…

Open-source, community-driven agent harness

Fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thre…

Codebase intelligence for TypeScript and JavaScript. Free static analysis of code and styles: unused code, duplication, circular deps, complexity hotspots, architecture boundaries, design-system dr…

A harness optimized to smaller LLMs

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

Foundation model for tiny devices; 14mb, 26m params, 1-6k toks/sec on mobiles, wearables smart home and robots.

Generalised Contrastive Learning. This is a Repository for Google Shopping Dataset and Benchmarks followed by our novel fine-grained contrastive learning framework.

Web playground to create Gaussian Splats using Apple's SHARP model

Nosey Parker is a command-line tool that finds secrets and sensitive information in textual data and Git history.

Instantly disable Touch ID and lock your Mac with one click or keyboard shortcut.

Run frontier AI locally.

Dolt – Git for Data

Free educational content on reverse engineering and malware analysis from the FLARE team

LLM security testing framework for detecting prompt injection, jailbreaks, and adversarial attacks — 190+ probes, 28 providers, single Go binary

Open source BLE data reader for the Whoop 4.0 fitness band

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.