Blog
Updates on our agents, Khadim and Blop, and what we are building on.
BlopBlop: Tests as Code and Agentic Browser QA
Blop drives real Playwright browsers to verify your running app. Tests live as .blop.ts files in your repo, and runs emit results.json, events.jsonl, JUnit XML, and screenshots. Here is how it works.
Hanan Choudhary Hadayat
KhadimKhadim: An Open-Source, Local-First Coding Agent
Khadim is our working open-source coding agent. It runs locally, ships as a CLI today, and supports 19+ providers. Here is what it is, what it does today, and what is still in progress.
Hanan Choudhary Hadayat
MCPWhat Is MCP, and Why Is It Useful? How Unravel AI Uses an Open Standard for AI Integration
Model Context Protocol is an open standard introduced by Anthropic. Here is what it is, how it works, and why it is practical for AI agents that need to use real tools.
Hanan Choudhary Hadayat