Rom Iluz romiluz13

☘️

Building coding agents with evidence: execution harnesses, memory with receipts, and reproducible benchmarks.

Achievements

romiluz13/README.md

I build open-source tools for coding agents, with a focus on the gap between what an agent claims and what the evidence shows.

Hybrid-Search-RAG and Memongo - retrieval and persistent agent memory.

mifal mifal Public

One engineering workflow for Claude Code, Codex, Droid, Pi and OpenCode, with a validator that refuses a record without its evidence. Alpha, macOS.

Python 47 2
cc10x cc10x Public

The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 14 agents · 21 skills · 8 workflows. Fail-closed gates, test honesty, anti-anchored review.

Python 167 25
ClawMongo ClawMongo Public

Forked from openclaw/openclaw

ClawMongo — MongoDB-native AI gateway. Fork of OpenClaw with MongoDB as the only canonical memory backend.

TypeScript 32 2
Memongo Memongo Public

MongoDB-native long-term memory for production AI agents

TypeScript 33 5
Hybrid-Search-RAG Hybrid-Search-RAG Public

Python 67 19
whatsapp_ai whatsapp_ai Public

JavaScript 48 11

Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.

There was an error while loading. Please reload this page.