Skip to content
View Enucatl's full-sized avatar
15 followers · 3 following
  • Switzerland

Achievements

Achievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: Arctic Code Vault ContributorAchievement: Pull Sharkx2

Achievements

Achievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: Arctic Code Vault ContributorAchievement: Pull Sharkx2

Block or report Enucatl

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
Enucatl/README.md

Matteo

I build agentic AI systems that combine LLMs, retrieval, memory, multimodal document processing, automation, and infrastructure.

My focus is practical AI: systems that read and search private data, use tools, keep state, and run reliably across self-hosted and cloud environments.

Current Focus

  • Agentic RAG and document intelligence
  • Multimodal OCR and metadata extraction
  • Long-term memory systems for AI agents
  • Self-hosted AI infrastructure and model serving
  • Workflow automation with LLM-powered tools

What I Build

I work on AI systems that connect language models to real infrastructure, private data, and long-running workflows.

  • Agentic systems: tool use, memory, retrieval, orchestration, and stateful workflows.
  • Document intelligence: OCR, metadata extraction, vector search, and RAG over private archives.
  • Self-hosted AI infrastructure: local inference, model serving, Docker-based deployment, and observability.
  • Automation systems: bots, background workers, scheduled jobs, and operational tooling.
  • Infrastructure as code: Proxmox, VyOS networking, Puppet, Vault, FreeIPA, backups, and monitoring.

Technical Stack

  • Languages: Python, Rust, Shell
  • AI/LLM: RAG, embeddings, vector search, OCR, multimodal pipelines, agent memory, training, finetuning
  • Infrastructure: Docker, Proxmox, Puppet, Ansible, VyOS, Vault, FreeIPA
  • Operations: Linux, networking, observability, backups, self-hosted services
  • Cloud: Google, Azure

Pinned Loading

  1. docker-paperless-ai docker-paperless-ai Public

    A platform that combines agentic RAG, multimodal OCR and metadata extraction pipelines, self-hosted models, vector search, to automate AI over Paperless-ngx archives.

    Python 3

  2. camillo camillo Public

    Memory backbone for agentic AI with MCP, hybrid recall, associative links, dreaming and forgetting.

    Python

  3. fish-speech fish-speech Public

    Forked from fishaudio/fish-speech

    A fine-tuning project, with custom layers on a SOTA Open Source TTS

    Python 1

  4. puppet-control-repo puppet-control-repo Public

    Production-style homelab infrastructure as code: hardware buildout, Proxmox provisioning, VyOS networking, Puppet configuration, Docker services, PKI, backups, and observability.

    Shell 1

  5. crabberbot crabberbot Public

    Telegram Bot to download media from websites with yt-dlp and read them with AI

    Rust 1