# GorOhanyan/decisions-mcp

> An MCP server that lets coding agents search large codebases via OpenRouter decision models, returning ranked file:line hits instead of reading whole files. Cuts context from hundreds of thousands of tokens to about a thousand.

- Magnitude: 0.0 out of 10 — Quiet
- Stars: 1 total · Not enough measurements today
- Star trust: star growth looks organic
- Category: AI agents · Language: JavaScript · License: MIT · Created: 2026-10-14 · Last push: 2026-10-14
- GitHub: https://github.com/GorOhanyan/decisions-mcp · Page: https://gitnova.dev/en/r/GorOhanyan/decisions-mcp

## Useful for

- Locate a bug by its symptom across dozens of files without loading them into context
- Classify files into labels like test, config or dead-code with confidence scores
- Ask typed yes/no or choice questions per file, e.g. whether it uses a database

## Why it’s here

- There are not enough fresh counter measurements for today's UTC day. The gain is unknown.
- The repository is 21 days old and already has 1 star.

## 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: 0
- Watchers: 0
- Average over the last week: 0 per day
- Usual pace: 0 per day

## Stars per day, last 22 days (oldest → newest, today is partial)

2026-10-14 … 2026-11-04: 1, 0, 0, 0, 0, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

10-22 0.0, 10-23 0.0, 10-24 0.0, 10-25 0.0, 10-26 0.0, 10-27 0.0, 10-28 0.0, 10-29 0.0, 10-30 0.0, 10-31 0.0, 11-01 0.0, 11-02 0.0, 11-03 0.0, 11-04 0.0

## More in this category

1. **storytold/craft-anything** — 8.9 · Breakout · AI agents · Rust · +200 stars measured 2026-11-04, 00:17–01:47 UTC, ≈ 3,038 by evening
   A pure-Rust reverse-engineering engine with 284 tools that inspects websites, apps and games, then has a coding agent rebuild a similar version and checks the result against the original.
   Full card: https://gitnova.dev/en/r/storytold/craft-anything.md
2. **vercel-labs/agent-desktop** — 8.7 · Breakout · AI agents · Rust · +176 stars measured 2026-11-04, 00:17–01:47 UTC, ≈ 1,969 by evening
   Rust CLI that lets AI agents control desktop apps via macOS accessibility trees, with stable element refs and a snapshot-to-action loop. Combines a native binary with a C-ABI cdylib for Python/Swift/Go/Node bindings.
   Full card: https://gitnova.dev/en/r/vercel-labs/agent-desktop.md
3. **pingdotgg/t3code** — 8.2 · Breakout · AI agents · TypeScript · +129 stars measured 2026-11-04, 00:17–01:47 UTC, ≈ 1,827 by evening
   T3 Code is an agent harness control surface for agents on your machine, with mobile (iOS, Android), web and Electron desktop apps. It works with your Claude Code, Codex, Cursor, Grok Build, OpenCode and Google Antigravity subscriptions if…
   Full card: https://gitnova.dev/en/r/pingdotgg/t3code.md
4. **KKKKhazix/agent-autoloop** — 7.9 · Early signal · AI agents · TypeScript · +262 stars measured 2026-11-04, 01:02–01:47 UTC, ≈ 921 by evening
   A lightweight scheduler for CLI agents (Claude Code, Codex, etc.): runs them in the background on events and schedules, and sends a card to a messenger or desktop when a decision is needed. Runs locally on Mac or Linux with no cloud and…
   Full card: https://gitnova.dev/en/r/KKKKhazix/agent-autoloop.md
5. **deepseek-ai/dsh-superagent-prototype** — 7.9 · Cooling · AI agents · TypeScript · +190 stars measured 2026-11-04, 00:17–01:47 UTC, ≈ 2,192 by evening
   Research prototype of a proactive coding agent for a single GitHub repository, packaged as a bundle for DeepSeek Harness: it listens to GitHub and Feishu, opens work items and replies in the original conversation, for example with a pull…
   Full card: https://gitnova.dev/en/r/deepseek-ai/dsh-superagent-prototype.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 2026-11-04 01:58 UTC, updated every 30 minutes.