Product engineer building AI tools for real workflows.

I build product surfaces, agent infrastructure, and local-first AI tools across developer workflows, internal platforms, and web3-adjacent networks.

Contact Stealth work

Current Work

01 / Product Work

Product engineering for specialized teams.

I work across frontend product development, backend workflows, customer support, documentation, and new product exploration.

02 / Root Node Labs

Vertical agents for focused operators.

Building focused agent systems with RAG pipelines, MCP integrations, fine-tuning loops, and domain-specific interfaces for complex work.

Operating System

Product systems

Frontend, backend, docs, support, and customer feedback loops for engineering software.

Agent tooling

MCP servers, RAG pipelines, local model workflows, and vertical assistants with real inputs.

Domain workflows

Interfaces and automation for specialized teams, messy data, and high-friction internal processes.

Projects

shipped systems / prototypes / infrastructure

01 / Product messaging workflow

mStack

A product communication workflow for coding agents. It helps founders and product teams collect context, choose the strongest angle, draft launch updates, critique weak copy, and package channel-specific assets.

Turns messy release context into a structured launch loop: context, angle, draft, critique, package, retro, remember.

Status: Open source
Stack: Codex / Claude Code / agent skills
Link: Open project ->

02 / Grounded expert panel

Lenny's Council

A local-first AI expert panel over Lenny Rachitsky's podcast and newsletter corpus. It selects relevant experts, runs multi-round discussions, and cites claims back to the source chunks.

Turns 295 podcast episodes and 349 newsletter essays into a cited advisory board for product questions.

Status: Open source
Stack: SvelteKit / Postgres / pgvector / Ollama / Bun
Link: Open project ->

03 / Local AI tool

Obsidian Local LLM Helper

An Obsidian plugin that connects notes to locally running models for writing assistance, summarization, and organization without sending vault data to a cloud service.

Keeps private writing workflows inside the user vault.

Status: Open source
Stack: Obsidian / Ollama / LM Studio
Link: Open project ->

04 / Browser AI

Sidekick

A Chrome extension for local AI assistance in the browser: summarize pages, rewrite text, and ask questions about visible content using local models.

Brings private AI actions directly into day-to-day browsing.

Status: Chrome extension
Stack: Extension APIs / local models / page context
Link: Open project ->

05 / AI news system

GitInformed

An AI-powered RSS aggregator that curates and summarizes developer news across sources, with models filtering for relevance before anything reaches the reader.

Turns noisy developer feeds into a smaller set of useful signals.

Status: Live
Stack: Next.js / LLM filtering / RSS
Link: Open project ->

06 / Agent infrastructure

TheVerge MCP Server

A Model Context Protocol server that fetches and parses recent articles from The Verge for assistants that need live product and industry context.

Gives MCP-compatible assistants current tech coverage.

Status: Open source
Stack: MCP / feeds / parsing
Link: Open project ->

07 / Social protocol tooling

Farcaster MCP Server

An MCP server for Farcaster that can pull casts from users, search channels, and expose protocol activity to AI assistants through a stable tool layer.

Turns decentralized social context into agent-readable tools.