Skip to content
View richardadonnell's full-sized avatar
🥰
🥰
41 followers · 12 following

Achievements

Achievement: Pair ExtraordinaireAchievement: Starstruckx2Achievement: Pull Sharkx3Achievement: YOLOAchievement: Quickdraw

Achievements

Achievement: Pair ExtraordinaireAchievement: Starstruckx2Achievement: Pull Sharkx3Achievement: YOLOAchievement: Quickdraw

Block or report richardadonnell

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
richardadonnell/README.md

Richard Donnell

AI Engineer · LLM Integration & Automation · Full-Stack Systems

I build production AI systems — LLM agents, RAG pipelines, MCP servers, and automation workflows — backed by 25+ years of hands-on engineering. I architect the full stack from model integration to deployment, and self-host everything on my own infrastructure.

Currently shipping AI-augmented trading systems at Verified Investing (TypeScript, Next.js, React Native, real-time data pipelines).

What I Build

🤖 AI Agent Systems — Production agent workflows with multi-model orchestration (OpenAI, Claude, Gemini), tool calling, persistent memory, and structured outputs. 50+ deployed systems handling financial analysis, content synthesis, and data pipelines.

🔍 RAG Pipelines — End-to-end retrieval-augmented generation: ingestion, embeddings (OpenAI), vector search (Supabase/pgvector), and conversational agents with hybrid retrieval + web augmentation.

🔌 MCP Servers — Model Context Protocol integrations that expose real-world APIs to LLM agents. Dual-protocol (MCP + REST), Docker-based, stateless, production-ready.

⚙️ Infrastructure — Self-hosted on Coolify/Hetzner. Docker, CI/CD, Postgres, Supabase, n8n, Linux. I own the full pipeline.

Featured Projects

Project Description
monarch-money-mcp MCP server exposing personal finance data to LLM agents. Python, FastMCP, Docker.
privacy-mcp MCP server for Privacy.com virtual card management via AI agents. Python, FastMCP, Docker.
ai-stock-analysis-engine Automated financial analysis: parallel technical indicators + GPT-4o sentiment + HTML reports.
openwebui-chat-backend Async chat middleware bridging Open WebUI to custom AI agent pipelines with full observability.
youtube-rag-knowledge-base Ingest YouTube channels → Gemini transcription → embeddings → pgvector → conversational RAG agent.
daily-ai-news-brief Automated daily intelligence: RSS ingestion → Perplexity research → AI synthesis → email. Running in production.

Tech Stack

AI/LLM:        OpenAI · Claude · Gemini · LangChain · RAG · MCP · Agent Orchestration · Embeddings
Languages:     TypeScript · Python · JavaScript
Backend:       Next.js · Hono · FastMCP · Starlette · PostgreSQL · Supabase · pgvector · Redis
Frontend:      React · React Native · Tailwind CSS
Infrastructure: Docker · GitHub Actions · Coolify · Hetzner · Linux · Nginx · CI/CD
Automation:    n8n (50+ workflows) · Python scripting · Webhook pipelines

Connect

LinkedIn Website Email

Pinned Loading

  1. autonomous-ai-content-pipeline autonomous-ai-content-pipeline Public

    Production system that captures live video streams via custom RTMP server, generates blog articles using a 4-LLM orchestration pipeline, routes through human-in-the-loop approval via Microsoft Team…

  2. ai-stock-analysis-engine ai-stock-analysis-engine Public

    Automated financial analysis pipeline that pulls real-time market data, computes technical indicators, generates AI-driven sentiment analysis, and delivers formatted HTML reports via email.

  3. youtube-rag-knowledge-base youtube-rag-knowledge-base Public

    Automated pipeline that ingests an entire YouTube channel's video library, transcribes content via Gemini, generates embeddings, stores in a vector database, and exposes a conversational AI agent f…

  4. openwebui-chat-backend openwebui-chat-backend Public

    Full-stack async chat middleware that bridges Open WebUI to custom AI agent pipelines — with user management, real-time status updates, persistent conversation tracking, and graceful error recovery.

  5. monarch-money-mcp monarch-money-mcp Public

    FastMCP Python MCP server + REST API for Monarch Money — Docker-based, stateless, dual-protocol (any MCP client + any REST client)

    Python 1 1

  6. privacy-mcp privacy-mcp Public

    FastMCP Python MCP server + REST API for Privacy.com — Docker-based, stateless, dual-protocol (any MCP client + any REST client)

    Python