Skip to content
View masterFoad's full-sized avatar
9 followers · 6 following

Achievements

Achievement: Starstruckx2Achievement: Pull Shark

Achievements

Achievement: Starstruckx2Achievement: Pull Shark

Highlights

  • Pro

Block or report masterFoad

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
masterFoad/README.md

Hi, I’m Foad 👋

Full-stack AI engineer building document intelligence systems — multimodal retrieval, RAG, and pragmatic agents.

  • 🔎 OSS: NanoSage — local deep-research agent for recursive search & report generation → https://github.com/masterFoad/NanoSage
  • 🧠 I like embeddings, layout/ocr pipelines, and making evaluations/dev-ex not suck.
  • 🧰 Python • PyTorch • LangGraph/agents • Retrieval/Indexing • React/TypeScript • CI/CD
  • 🔄 Currently nerding over codex python sdk port

Quick links

GitHub • LinkedIn • PyPI: tfrq • HF: Granite Vision 3.3 (2B) Embedding

What I’m into (lately)

  • Multimodal document understanding & vision embeddings
  • RAG quality/latency (multi-vector, re-ranking, evals)
  • Agentic workflows that actually ship (not just vibes)

Selected OSS

Want to collaborate or try something weird with RAG/agents? DM me on LinkedIn or open an issue on NanoSage.

Badges (because why not)

GitHub followers NanoSage Stars License

Popular repositories Loading

  1. NanoSage NanoSage Public

    Local LLM Powered Recursive Search & Smart Knowledge Explorer

    Python 255 31

  2. adaboost-knn adaboost-knn Public

    An ADABOOST classifier based on KNN implemented in java with multithreading.

    Java 2 2

  3. sensor-test sensor-test Public

    A project that uses two SensorTag cc2650 to classify Activity, one sensor was put on the arm, the other on the leg.

    Java 1

  4. optillm optillm Public

    Forked from codelion/optillm

    Optimizing inference proxy for LLMs

    Python 1

  5. AutoDidact AutoDidact Public

    Forked from dCaples/AutoDidact

    Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.

    Jupyter Notebook 1

  6. quantalogic quantalogic Public

    Forked from quantalogic/quantalogic

    Quantalogic ReAct Agent - Coding Agent Framework - Gives a ⭐️ if you like the project

    Python 1