# rlshaw-ml/BlastLoop

> A framework for AI coding agents: three build altitudes (Blast, Mid, Inner) plus ordered T1 structural, T2 bug/ops and T3 adversarial quality gates.

- Magnitude: 1.1 out of 10 — Quiet
- Stars: 12 total · +2 stars measured 2026-10-15, 20:47–22:46 UTC
- Star trust: star growth looks organic
- Category: AI agents · License: MIT · Created: 2026-10-06 · Last push: 2026-10-15
- GitHub: https://github.com/rlshaw-ml/BlastLoop · Page: https://gitnova.dev/en/r/rlshaw-ml/BlastLoop

## Useful for

- Point an agent at AGENTS.md and prompts to write code at the right altitude
- Run changes through T1, T2 and T3 gates before shipping
- Restart the loop at T1 when T3 finds a structural problem

## Why it’s here

- Star-counter measurements on 2026-10-15 (UTC), 20:47–22:46: 10 → 12 stars (+2). This is the change over that interval.
- The repository is 9 days old and already has 12 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Hacker News: “Show HN: BlastLoop, a structure-first coding method for AI agents” — 11 points, 6 h ago.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 0
- Issues and pull requests: 4
- Watchers: 0
- Average over the last week: 0 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 2
- Latest release: v1.0.0 (2026-10-06)

## Stars per day, last 10 days (oldest → newest, today is partial)

2026-10-06 … 2026-10-15: 0, 0, 0, 0, 0, 0, 0, 0, 0, 2

## Hacker News

- Show HN: BlastLoop, a structure-first coding method for AI agents — 11 points, 1 comments: https://news.ycombinator.com/item?id=50106062

## Spotted in now

- Spotted on Hacker News

## More in this category

1. **morluto/rea** — 7.4 · Breakout · AI agents · TypeScript · +27,271 stars measured 2026-10-15, 00:20–22:48 UTC
   A reverse-engineering tool that lets AI agents inspect apps and native binaries: it connects agents to Hopper or Ghidra via MCP and CLI, helping explain how a feature works and rebuild it in your own project.
   Full card: https://gitnova.dev/en/r/morluto/rea.md
2. **outcrawlai/scout** — 6.7 · Early signal · AI agents · TypeScript · +181 stars measured 2026-10-15, 00:20–22:36 UTC
   Open-source browser agent in TypeScript: takes a task in plain words, opens a real browser, reads pages, clicks, types and scrolls until the job is done, then returns the answer. Works with any chat completions API service or a local model.
   Full card: https://gitnova.dev/en/r/outcrawlai/scout.md
3. **anthropics/claude-plugins-official** — 6.4 · Breakout · AI agents · Python · +919 stars measured 2026-10-15, 00:22–22:36 UTC
   Official Anthropic-managed directory of Claude Code plugins: internal plugins plus third-party ones from partners, installable via the built-in marketplace.
   Full card: https://gitnova.dev/en/r/anthropics/claude-plugins-official.md
4. **onehumanbeing/esp32-iphone-agent** — 6.1 · Peaking · AI agents · C · +335 stars measured 2026-10-15, 00:20–22:36 UTC
   Lets an AI model drive a real iPhone via an ESP32-S3: the screen is mirrored over AirPlay while the board emulates a USB mouse and keyboard. No Mac, Xcode, Apple developer account or jailbreak required.
   Full card: https://gitnova.dev/en/r/onehumanbeing/esp32-iphone-agent.md
5. **K-Dense-AI/scientific-agent-skills** — 6.0 · Breakout · AI agents · Python · +1,084 stars measured 2026-10-15, 00:21–22:36 UTC
   A library of 166 ready-to-use skills for AI agents covering bioinformatics, chemoinformatics, medicine, materials science and more, with access to 100+ scientific databases. Compatible with Cursor, Claude Code, Codex and the open Agent…
   Full card: https://gitnova.dev/en/r/K-Dense-AI/scientific-agent-skills.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-15 22:49 UTC, updated every 30 minutes.