# reticlehq/reticle

> Reticle is a dev-only SDK and MCP toolset that lets coding agents drive a real running web or desktop app and verify the result of their changes. It returns a pass/fail/unknown verdict with evidence and the file:line to fix.

- Magnitude: 1.9 out of 10 — Steady
- Stars: 1,268 total · +2 stars measured 2026-10-20, 10:54–12:31 UTC, ≈ 4 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · Created: 2026-06-11 · Last push: 2026-10-20
- GitHub: https://github.com/reticlehq/reticle · Homepage: https://app.reticle.sh · Page: https://gitnova.dev/en/r/reticlehq/reticle

## Useful for

- Verify an agent's fix actually works by driving the running app and getting an evidence-backed verdict
- Save a passing journey as a flow and re-verify it deterministically without an LLM
- Add reticle gate to CI to block changes that break saved flows

## Why it’s here

- Star-counter measurements on 2026-10-20 (UTC), 10:54–12:31: 1266 → 1268 stars (+2). This is the change over that interval.
- Estimated end-of-day forecast: about +4 stars, using observed gains and the previous day.
- Hacker News: “Show HN: Make AI coding agents verify its own work” — 11 points, 2 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: 214
- Issues and pull requests: 1,794
- Watchers: 6
- Average over the last week: 8 per day
- Usual pace: 16 per day
- Stars in the last hour (measured): 1
- Latest release: v3.7.0 (2026-10-13)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-21 … 2026-10-20: 30, 10, 9, 20, 39, 10, 8, 11, 99, 10, 85, 47, 5, 7, 10, 10, 9, 7, 8, 7, 6, 6, 2, 13, 12, 4, 6, 7, 6, 2

## Hacker News

- Show HN: Make AI coding agents verify its own work — 11 points, 6 comments: https://news.ycombinator.com/item?id=50163896

## Spotted in now

- Spotted on Hacker News

## More in this category

1. **google-research/harness2** — 9.7 · Breakout · AI agents · Python · +2,038 stars measured 2026-10-20, 00:22–12:24 UTC, ≈ 4,071 by evening
   A framework for recursive optimization of AI agent harnesses (prompts, tools, memory, skills) without fine-tuning model weights, with JobBench, LAB and WorkBuddy-Bench benchmarks.
   Full card: https://gitnova.dev/en/r/google-research/harness2.md
2. **MadsLorentzen/ai-job-search** — 9.3 · Breakout · AI agents · Python · +1,935 stars measured 2026-10-20, 00:22–12:24 UTC, ≈ 3,746 by evening
   A job application framework built on Claude Code: evaluates postings, tailors CVs, and writes cover letters. Runs locally, focused on the Danish job market.
   Full card: https://gitnova.dev/en/r/MadsLorentzen/ai-job-search.md
3. **anomalyco/opencode** — 7.9 · Breakout · AI agents · TypeScript · +604 stars measured 2026-10-20, 00:22–12:24 UTC, ≈ 1,174 by evening
   Open source AI coding agent with terminal and desktop interfaces. Ships with a build agent (full edit and command access) and a read-only plan agent for code analysis.
   Full card: https://gitnova.dev/en/r/anomalyco/opencode.md
4. **IsuruMaduranga/harness-engineering-101** — 7.3 · Early signal · AI agents · Python · +104 stars measured 2026-10-20, 00:22–12:24 UTC, ≈ 224 by evening
   A book series explaining how to build AI agents from first principles, treating the LLM as a stateless brain and the harness as the program that manages the conversation array. It grows a ~300-line toy agent in plain Python across 16…
   Full card: https://gitnova.dev/en/r/IsuruMaduranga/harness-engineering-101.md
5. **JoasASantos/REA-Prompts** — 7.1 · Early signal · AI agents · +362 stars measured 2026-10-20, 05:55–12:24 UTC, ≈ 572 by evening
   A curated collection of prompts for using REA (Reverse Engineer Anything) with AI coding agents to inspect binaries, firmware, kernels, games, APKs, Electron apps and websites. Covers installation, feature tracing, cloning, vulnerability…
   Full card: https://gitnova.dev/en/r/JoasASantos/REA-Prompts.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 2026-10-20 12:38 UTC, updated every 30 minutes.