Skip to main content
Available for new work~13,000 GitHub contributions · 100+ repos

Hey, I'm 👋

Griffin Long

Agentic AI Engineer · Technical Founder

A self-taught AI engineer who went from line cook to shipping production agent systems.

I don't out-type teams — I build and direct the AI agent tooling that lets one person ship at team scale.

scroll
scroll down
#01

My story

How a line cook ended up building AI agent systems.

I didn’t take the traditional route into software. I taught myself to build with AI while working as a line cook and taking college classes — experimenting with ChatGPT on the side until it turned into something real.

In March 2025 I turned that into GRAIsol. In the ~15 months since, it's grown into roughly 13,000 GitHub contributions across 100+ repos: an open-source agent runtime (agent-afk), a 369K-LOC AI GTM-automation platform, and 12 published open-source packages.

The throughline: I don't out-type teams — I build and direct the AI agent tooling that lets one person ship at team scale. Same energy I brought to the kitchen — high tempo, reliable under pressure — now pointed at shipping software end to end.

Dual monitors glowing in a dim room — the workspace where the agent tooling gets built
where the work happens
A desk lit by a monitor at night — notes and papers scattered across it, mid-build
deep in it
#02

Things I've built

Open-source tools, production platforms, and the agent infrastructure behind them.

AgentGRAI

Modular Next.js / React AI lead-intelligence and outbound platform with multi-stage enrichment, async queue architecture, Gmail outbound engine, and AI SDR layer

LOC

~369K

commits

~1,900

timeframe

~5 months

Next.jsReactTypeScriptPostgreSQLRedis

Full Python CLI wrapping Substack's unofficial API with write-safety gates and destructive-op guards

LOC ~7,142
tests 234
commands 50+
PythonSubstack APICLI

Native macOS terminal in Swift 6 / AppKit — no Electron, no Xcode project — with a file-tree sidebar, 22-language syntax-highlighted editor, git status badges, split panes, shell integration, and 10 color themes gated by 345 contrast assertions

source files 91
editor languages 22
color themes 10
Swift 6AppKitSwiftTermMetal

ElevenLabs Voice MCP

tools: 23

ClickUp MCP

tools: 19

Cursor Agent MCP

merged PRs: 40

E2B MCP

Twilio MCP

Smartlead MCP

GPT Image MCP

Full TypeScript CLI for the X/Twitter API v2 with OAuth 1.0a, OAuth 2.0, and Bearer auth

TypeScriptX APICLI
~6,143 loc

Python CLI for the Google Analytics 4 API covering properties, reports, acquisition, referrers, and trends

PythonGoogle AnalyticsCLI
~633 loc

agent-framework

Claude Code / agent-afk plugin for autonomous task execution through composable skills, subagents, and hooks

PythonClaude Codeagent-afk

gadscli

Async Rust CLI for the Google Ads API, published to npm (npm-only)

RustGoogle Adsnpm

A/B Experimentation Platform

5-service Docker Compose system with chi-squared significance from scratch, SHA-256 user bucketing, and database-level race-condition handling

FastifyNext.jsPostgreSQL
5 services

On-Device AI Tools

Local macOS menu-bar dictation (mlx-whisper) and system-wide inline ghost-text completion (MLX Swift) for Apple Silicon

SwiftMLXApple Silicon
#03

Tools I build with

The stack behind the projects above.

Languages

TypeScriptJavaScriptPythonRustSwiftSQL

Frameworks & Runtimes

Node.jsNext.jsReactAstroFastifyTailwind CSS

AI & Agents

agent-afkClaude Agent SDKOpenAI APIModel Context Protocol (MCP)Agentic orchestrationMulti-agent systemsPrompt engineeringLLM evalsPlaywright automationLocal models (MLX, llama.cpp, Ollama, LM Studio)

Data & Infrastructure

PostgreSQLSupabaseFirebaseRedisUpstash QStashDockerVercelRailwayStripeTwilioElevenLabsGoogle APIsSentryPostHogSelf-hosted CI/CD
#04

Experience

From founding GRAIsol to embedded contract work and independent consulting.

Special Projects Engineer (Contract)

Capital Mischief / R360 / Charlie Garcia · Remote (Daytona Beach)

Jul 2026 – PresentCurrent
  • Built a daily editorial intelligence pipeline (~7,960 LOC Python, 3 packages) for a 22K-subscriber finance Substack (~$1.76M ARR): prep, editorial judgment, brief generation, essay drafting, publish verdicts, and post-hoc scorecards.
  • Designed deterministic anti-fabrication guards that drop any AI-drafted content whose facts, numbers, or named entities are not verbatim in the author's published words; human-in-the-loop approval required before anything ships.
  • Built and run 7 automated cron/daemon tasks delivering daily research briefs, analytics pulses, desk dashboards, and Monday team briefings to 3 Telegram channels.
  • Built a 4-panel HTML desk dashboard (fleet health, workflows, review queue, signal desk) with daily email delivery; packaged all systems as an agent-afk plugin with 100 test functions.

Founder and AI Systems Engineer

GRAIsol (opens in new tab) · Daytona Beach, FL

Mar 2025 – PresentCurrent
  • Built and open-sourced agent-afk (agentafk.com), a TypeScript agentic coding-agent runtime/harness: ~308K LOC, 1,542 commits, 408 published npm versions, Apache-2.0.
  • Architected AgentGRAI, a modular Next.js / React AI lead-intelligence and outbound platform (~369K LOC, ~1,900 commits in ~5 months): multi-stage enrichment on async QStash queues with Redis-semaphore concurrency control.
  • Extended it with a Gmail outbound engine (multi-inbox rotation, AI sequences, open/click tracking, AI reply classification) and an AI SDR layer with ICP scoring and human-handoff routing.
  • Published 12 open-source packages across npm and GitHub: 7 MCP servers (ElevenLabs Voice – 23 tools, ClickUp – 19 tools, Cursor Agent – 40 merged PRs / SSE on Vercel, E2B, Twilio, Smartlead, GPT Image), plus agent-afk, gadscli, substack-cli, x-api-cli, and ga-cli.
  • Ran a one-person AI-leveraged studio delivering 30+ client and product builds.
  • Accumulated ~13,000 GitHub contributions across 100+ repos since Mar 2025.

AI Systems Engineer (Contract)

Atlas Digital · Remote

Oct 2025 – Mar 2026
  • Embedded directly with client leadership to design and deploy an end-to-end CRM and agent automation pipeline: lead intake, enrichment, scoring, qualification, and outbound handoff in production.
  • Built customer-facing agent workflows on Claude Agent SDK and OpenAI with structured fallback/retry logic and production observability; owned architecture end-to-end from design through deployment.

Independent AI Consultant

Remote

2026Current
  • Fuly Kids (fulykids.com): Diagnosed recurring LLM over-spend in FulyScan (AI food-scanning nutrition tool); shipped fix via merged PR adding Supabase/Postgres caching so repeat scans reuse stored results instead of re-invoking Claude.
  • adside.ai: Delivered prioritized UX and product audit covering onboarding friction, cognitive overload, missing agency-facing tooling, data-freshness gaps, agent latency, and strategic positioning.
#05

Right now

Last updated Sep 2026.