Featured

AI agent

New 2026

Claude Code skill that forensically audits what the xAI Grok Build CLI uploaded from your machine — detects codebase uploads and secret leakage in ~/.grok logs, then generates a checksummed evidence package and a GDPR/CCPA data-deletion request. Secret values never leave your machine.

New 2026

Claude Code adopted a Codex model. The crab kept the terminal. OAuth bridge with adjustable agent effort.

New 2026

Local-first AI agent memory, your agent's brain is an Obsidian vault you can open, read, and edit

New 2026

Run a coding agent in a sandboxed environment

New 2026

Codex plugin for delegating reviews, rescue tasks, and media generation to Grok

New 2026

Two LLM agents (Claude vs GPT) forecast Kalshi prediction markets daily — Brier-scored, self-evolving prompts, immutable risk engine, pre-registered go/no-go gate.

New 2026

🌶️ A product-thinking layer for vibe coders — grills a raw idea into build-ready docs through 13 expert personas. Claude Code plugin.

New 2026

Sovereign AI agent runtime — self-funded · self-modifying · constitution-bound

New 2026

Morphe's AI-powered Android APK patching workspace — multi-agent pipeline for APK analysis, target hunting, patch writing & deployment.

New 2026

Deterministic replay and counterfactual debugging for AI agent reliability. Bit-exact replay of agent runs with zero model calls — record once, replay forever, mutate freely.

New 2026

Record Unity playtests and review motion across video-capable and frame-only coding agents.

New 2026

SKA Protocol

New 2026

The visual Kanban for long-running AI agents. Watch your agent's plan organize itself: dependencies unlock into Ready, the critical path lights up, the one next move is obvious. Nobody wants to read a markdown plan.

New 2026

WebUI for claude code

New 2026

Local-first, zero-trust agentic IDE for verifiable autonomous software development.

New 2026

A macOS GUI for driving Claude Code agent sessions, built on swift-kernelee