RadarTopicsBuildersWeeklyReads
Open Source Radar
nowork-studio/

NotFair

GitHubWebsite

NotFair is a local, on-device agent system for defining goals and running a measured improvement loop against them, using Claude Code or Codex as the harness. It stores data locally and provides a UI to monitor progress and actions.

3.3kstars
409forks
6issues
MITlicense
2026since
Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap
Reviewgenerated from repository data · Aug 5, 2026

What it is

NotFair provides goal-driven marketing agents that operate on your machine, attaching to your existing Claude Code or Codex login, and using a local SQLite data store. The system lets you state an ambition, set a measurable target, and run a loop that measures, predicts, and acts within a defined cadence. It emphasizes local data storage (no hosted runtime or API keys) and per-goal agent workflows.

How it works

  • Each ambition creates a dedicated agent that defines a measurable metric and a baseline, then proposes a target and cadence. The loop performs checks, logs predictions, and records diary entries for each action.
  • The loop operates on your cadence and is designed to run continuously, with a spend envelope and observation window governing actions. The agent can perform at most one new move per cycle.
  • Data sources can be connected via MCP endpoints or run locally via a local source using stdout; OAuth connections to data providers are configured through the app.

Getting started

Install options include running via npx or installing globally:

npx notfair@latest doctor   # preflight: Node, harnesses, data dir, port
npx notfair@latest          # launch the UI at http://127.0.0.1:3327

Or:

npm install -g notfair
notfair

From source, clone the repo and install with pnpm, then run the dev server:

git clone https://github.com/nowork-studio/NotFair.git
cd NotFair/notfair
pnpm install
pnpm dev          # dev server with hot reload at http://127.0.0.1:3326

Recent releases

  • RELEASES (latest 0): - none

Traction

  • Stars: 3316
  • Forks: 409
  • Open issues: 6

Behind the repo

Not included in the provided material.

Caveats

  • License: MIT
  • Created: 2026-03-27
  • Last push: 2026-07-31
  • Data resides locally (e.g., ~/.notfair/db.sqlite and ~/.notfair/agents/ directories); OAuth tokens stored in SQLite database (not encrypted at application layer per docs).
  • Prerequisites include Apple Silicon Mac, Node 20+, and an authenticated harness (Codex CLI or Claude Code).
Agent skills inside · 25
All skills →
seo-analysisFull SEO audit: Google Search Console data + URL Inspection API + PageSpeed Insights API + technical crawl + keyword research + metadata audit + schema markup audit + search intent analysis + Core Web Vitals monitoring. Feeds real GSC data and PageSpeed metrics into AI to surface quick wins, diagnose traffic drops, find content gaps, identify metadata mismatches, detect schema gaps, monitor page performance, and produce an actionable 30-day plan. Use this skill whenever the user asks about SEO, search rankings, organic traffic, Google Search Console, keyword performance, traffic drops, conteSecurityscriptsbroken-link-checkerScans a website to find broken links (404s, 500s). Crawls internal pages, identifies broken outbound links, and reports source pages for easy fixing. Use this when the user asks to "check for broken links", "find 404s", "audit my links", or "is my site healthy".Securityscriptsgoogle-adsManage Google Ads — performance, keywords, bids, budgets, negatives, campaigns, ads, search terms, QS, location targeting, bulk operations, experiments, asset management, portfolio bidding, offline conversions. Use for any mention of Google Ads, CPA, ROAS, ad spend, or campaign settings.Content & Marketingkeyword-researchDiscover, analyze, and prioritize keywords for SEO and GEO content strategies from a seed keyword or niche. Identifies high-value opportunities based on search volume, competition, intent, and business relevance. Generates topic clusters. For building a dated editorial calendar from your own Search Console data, use `content-planner` instead — this skill is seed-driven keyword discovery, not calendar scheduling. Use when asked to "find keywords", "keyword research", "keyword analysis", "search volume", "keyword difficulty", "content ideas from a seed", or any keyword discovery task.Data & Analyticsschema-markup-generatorGenerate JSON-LD structured data markup for rich results in Google Search. Supports FAQ, HowTo, Article, Product, LocalBusiness, and multi-type schemas. Validates against Google requirements and provides implementation guidance. Use when asked to "add schema markup", "generate structured data", "JSON-LD", "rich snippets", "FAQ schema", "product markup", "add structured data to my page", "how to get rich snippets", or any structured data task.Data & Analyticsgoogle-ads-landingScore and diagnose Google Ads landing pages. Use when asked to audit a landing page, check landing page quality, diagnose high-CTR but low-conversion-rate ad groups, improve Quality Score's Landing Page Experience component, or compare an ad group's messaging against its landing page. Trigger on "landing page audit", "landing page score", "landing page quality", "why is my conversion rate low", "LPX", "landing page experience", "ad to page match", or when `/google-ads-audit` surfaces a high-CTR / low-CVR ad group.Security
SharePost on XLinkedIn
All trending reposRevenue-verified startups →