15 min read—
iFixAi: Independent AI Agent Audit That Checks Behaviour
iFixAi audits AI agents through business simulations and a separate judge, grading A–F with transcript evidence. Setup, mock demo, and staging audit guide.
Posts
All the articles I've posted.
- 11 min read—
Orca: Run Multiple AI Coding Agents in Parallel
Orca runs multiple AI coding agents in parallel in separate git worktrees — review diffs and merge from desktop, mobile, or a remote server. Setup and limits.
- 10 min read—
OpenMausBot: Open-Source Grok Bot You Can Self-Host
OpenMausBot is an open-source Grok Bot alternative: a team of AI bots in a chat app, each with its own computer, running on your Claude, Codex, or grok CLI.
- 9 min read—
Self-Host OpenMAIC: AI Multi-Agent Classroom
Self-host OpenMAIC with Docker Compose and turn any topic or document into an interactive AI classroom with AI teachers, classmates, quizzes, and PBL.
- 9 min read—
GitHub Spec Kit: Spec-Driven Development Explained
GitHub Spec Kit (Specify CLI) makes AI coding agents work from a written spec: constitution, specify, plan, tasks, implement, converge. A v1.3.1 guide.
- 9 min read—
Auto Ontology: A Semantic Layer for AI Agents
NVIDIA Auto Ontology builds a certified semantic layer for AI agents: verified definitions generate SQL with provenance, and out-of-scope questions are refused.
- 14 min read—
Craft Anything: Learn Software, Let AI Rebuild It
Craft Anything studies how a website, app or game works, then lets Claude Code rebuild your version. Install guide, Clean-room vs Deep mode and alpha limits.
- 12 min read—
Orkas: Local-First Multi-Agent Team for Your Desktop
Orkas turns Claude Code, Codex and 16 specialist agents into a local-first desktop team that keeps projects, to-dos and scheduled work moving across days.