Skip to content
View juanmanueldaza's full-sized avatar
22 followers · 76 following
  • Buenos Aires, Buenos Aires Province, Argentina
  • 15:00 (UTC -12:00)

Achievements

Achievement: Pair Extraordinairex2Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pair Extraordinairex2Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLO

Highlights

Organizations

@roofsonfire

Block or report juanmanueldaza

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
juanmanueldaza/README.md

Hi, I'm Juan Manuel Daza 👋

Agentic AI Engineer — Building production AI agent infrastructure. Open-source first. GPLv2 all the way.

Previously a journalist for 15 years (Clarín, Rolling Stone AR). I write docs that explain why, not just what. All my projects are zero-dependency CLIs, OWASP-reviewed by default, GPLv2 everywhere.

Based in Buenos Aires. EU citizen (Spain). Open to remote AI Engineer roles across Europe.

What I Build

Agent Infrastructure

Project ⭐ What it does
NERV — Spec-Driven Development for AI coding agents. A2A task delegation hub, MAGI persistent semantic memory, 9 specialized subagents. Runs nerv init to scaffold 45+ files. First community PR just landed! 🎉
invencible — Persistent memory + cross-agent delegation for Claude Code & Copilot CLI. Agents forget — invencible gives them shared context, coding standards, and a task hub so they can delegate to each other.
fu7ur3pr00f — AI career agent: 41 tools, 12 MCP clients, 5 specialists. Takes your LinkedIn/GitHub/GitLab data, builds a RAG knowledge base, analyzes skill gaps, and generates ATS-optimized CVs.
l06_p0s3 — A newsroom OS — Ableton Live for journalists. Orchestrates AI agents for sourcing, research, and drafting with human-in-the-loop control. Next.js + LangGraph.

Data-to-Markdown Pipeline

Zero-dependency Python CLIs that convert platform exports into clean Markdown for LLM analysis:

Project ⭐ What it does
linkedin2md 13 LinkedIn data exports → Markdown & PDF resumes. 149 tests, OWASP-reviewed.
github2md — GitHub profile data → Markdown. SOLID architecture, protocol-based DI.
gitlab2md — GitLab profile data → Markdown. 177 tests, OWASP-reviewed.

Stack
Agent frameworks OpenCode, LangChain, MCP, Claude Code, Copilot CLI, Hermes Agent
Languages Python, TypeScript, Go
LLM / RAG ChromaDB, OpenAI, Claude, Gemini
Infra Docker, Linux, GitHub Actions, Azure
Package mgmt UV (tools), pip (projects)

Connect

Built things with AI agents likely reading this right now. 🤖

Pinned Loading

  1. wallpapers wallpapers Public

    An evergrowing collection of wallpapers made with my film shots, home developed and scanned.

    TypeScript 1 1

  2. start start Public

    My start site.

    JavaScript

  3. pokedex pokedex Public

    A beautiful Pokedex that's being built by @opablon, @l0urencocarlos, and @juanmanueldaza.

    Vue 7 3

  4. linkedin2md linkedin2md Public

    Convert LinkedIn data exports to clean Markdown for LLM analysis & PDF resume generation. Zero-dependency Python CLI tool for AI career intelligence.

    Python 15 2