# RankMesh

> How Ayan Parkar builds RankMesh as an AI Engineer Intern: a
> multi-service FastAPI backend, Celery/Redis agent runs with Claude and
> Codex, and a Next.js panel where people review what agents ship.

[← AYAN.WTF](https://www.ayn.wtf/) \ PROJECTS \ RANKMESH

## Overview

RankMesh automates SEO and AI-search visibility. Agents do the
execution: they audit, fix, write, and publish. People stay in review
and approve.

- TYPE: Autonomous SEO and GEO engine
- ROLE: AI Engineer Intern at Ocavior, May 2026 to present
- STACK: FastAPI, Celery/Redis, LangChain, Next.js, PostgreSQL, R2
- SITE: [rankmesh.ai](https://rankmesh.ai)

![RankMesh panel with the Meshy chat prompt and the work areas sidebar: Discover, Create, Manage, Measure](https://www.ayn.wtf/projects/rankmesh-meshy-full.webp)

Meshy, the chat operator.

## Architecture

The backend is multi-service FastAPI: an orchestrator for projects, RAG,
blogs, SEO, marketing, scheduling, and billing, plus specialist agents
for SEO/GEO, prompts, and posts. Long jobs run on Celery/Redis with
Claude and Codex runners. The panel is Next.js with client and manager
workspaces and Meshy as the chat operator.

![RankMesh SEO audit of a site: an overall score, a breakdown by category, and counts of critical, warning and passing checks](https://www.ayn.wtf/projects/rankmesh-seo-full.webp)

An SEO audit in the panel.

## What I built

I've worked almost entirely inside this product, on both the agent
backend and the panel operators use. This is what I ship day to day.

- Shipped across the FastAPI multi-service backend: project auth,
  ingestion and RAG routing, blogs, SEO, marketing workflows,
  scheduling, credits, billing, and activity feeds.
- Built and hardened Celery/Redis autonomous execution with Claude and
  Codex runners, capacity leases, audit to fix-plan to schedule, and
  manager pause/resume/cancel.
- Owned large slices of the Next.js panel rewrite: client and manager
  workspaces, Meshy project chat with SSE, Discover and Manage SEO,
  admin tooling, and the performance work that kept data-heavy polls
  usable as agent output grew.
- Wired Search Console, Analytics, Firecrawl, CMS and GitHub publish
  gates, R2 storage, and review-first content release.

![RankMesh activity feed: agent runs grouped into needs a decision, in progress and completed](https://www.ayn.wtf/projects/rankmesh-activity-full.webp)

The activity feed of agent runs.

## More projects

- [DITTO](https://www.ayn.wtf/projects/ditto): A durable AI coding
  workspace on the web. Each GitHub repo gets its own sandbox with
  parallel sessions: isolated git worktrees, resumable agent runs over
  SSE, and a real commit-to-PR workflow shared by agents and humans.
  Still in active development.
- [BACKPACK](https://www.ayn.wtf/projects/backpack): Self-hostable,
  open-source AI research and chat app in the spirit of NotebookLM: 6+
  LLM providers, RAG research spaces, cross-chat memory, configurable
  MCP servers, web and academic search, and a versioned artifact
  workspace.
- [QUICKVID](https://www.ayn.wtf/projects/quickvid): Summarise, verify
  and chat with any YouTube video using transcripts, Gemini and RAG.
  Featured by LangChain, with 174 GitHub stars and 100+ active users
  before YouTube's crawler blocking made it unsustainable.

[← BACK TO AYAN.WTF](https://www.ayn.wtf/)

---
Screen font: Px437 IBM VGA 8x16, Ultimate Oldschool PC Font Pack
(int10h.org), CC BY-SA 4.0.