cinderline/northcinder

Open-source MCP server for comparing products and asking the buyer before purchase.

AI agentsJavaScript#agentic-commerce#human-in-the-loop#local-first#mcp#mcp-server

0.1 Quiet Magnitude out of 10. Unusual star pattern. Data as of September 21, 2026.

About the project

A local-first MCP server that compares products across stores you choose, explains rankings with sources, and requires buyer approval before any purchase.

Useful for

Connect to an MCP-capable AI app and compare running shoes by price, delivery, and seller trust
Inspect the local audit log to see why one offer ranked first and others were rejected
Ask the agent for a cart link instead of letting it pay with card details

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

The repository is 35 days old and already has 1,212 stars.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 1,212
Stars in a day: 0
Forks: 10
Issues and pull requests: 5
Watchers: 5
Language: JavaScript
License: MIT
Latest release: v0.2.1 · August 22, 2026
Created: August 17, 2026
Last push: August 22, 2026

Star trust

Unusual star pattern. The magnitude is lowered, not zeroed:

Stars arrived in one batch on a single day (1,144) and stopped right after: 40 over the next two days. Real interest usually fades gradually.
Fewer forks than usual: 10 for 1,212 stars.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

September 15, 2026Top new repositories this month: #61
September 14, 2026Top new repositories this month: #54
September 13, 2026Top new repositories this month: #52

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/cinderline/northcinder.svg?lang=en)](https://gitnova.dev/en/r/cinderline/northcinder)

Similar projects

9.6
NandhaKishorM/laya
Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.

BreakoutAI agentsPython+2,199 stars in a day
8.7
zai-org/ZCode
Z.ai's coding agent workbench: an Electron desktop app, browser UI and terminal Agent CLI. The repo contains the client, backend, shared UI and the agent CLI/runtime sources.

Early signalAI agentsTypeScript+1,351 stars in a day
8.7
browser-use/jev-ultrafast
A browser agent with a dynamic, indexed action space: given one natural-language goal it picks an operation (CLICK, TYPE_TEXT, SELECT, etc.) and an element, using a small LLM to generate text only for typing.

PeakingAI agentsPython+2,119 stars in a day
7.3
trycua/cua
Open-source toolkit for computer-use agents: cloud and local desktops, an app automation driver, and benchmarks for training and evaluation. For those giving AI agents control of a computer.

BreakoutAI agentsHTML+414 stars in a day
7.2
vercel-labs/json-render
Generative UI framework: an LLM turns prompts into JSON interfaces constrained to a catalog of components you define, keeping output predictable and safe. Supports React, Vue, Svelte, Solid, React Native, Next.js, 3D,…

BreakoutAI agentsTypeScript+385 stars in a day
7.1
typesafe-ai/skills
Agent skills for building with TypeSafe's System One API: typed decisions and probabilities for LLM agents. Installs as a Claude Code plugin or via skills.sh.

Early signalAI agents+320 stars in a day