Skip to content
View syzayd's full-sized avatar

Block or report syzayd

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
syzayd/README.md

Typing SVG


I build AI systems that go beyond chatbots.

Not wrappers. Not demos. Real architectures: multi-agent coordination, novel RAG retrieval, voice-vision pipelines, fine-tuned models — shipped end-to-end with tests, CI, and evals.

Building in public. Looking for AI engineer / applied AI internship roles.


Flagship Projects

CivilizationOS — Multi-Agent AI Society

A living simulation: 10 autonomous citizen-agents + 5 institutional councils (35 AI agents) debate, remember, and react to injected crises — Pandemic, Drought, Cyberattack, Election, Crime Wave.

Novel contribution — Temporal-Causal Memory Fusion (TCMF): Standard RAG retrieves by semantic similarity alone. TCMF fuses two streams:

AGORA stream    — citizen episodic memories scored by relevance x recency x importance
PANTHEON stream — societal causal graph (NetworkX DiGraph): crisis -> decision -> outcome

Fused score = episodic_score(m, q) x (1 + lambda x causal_boost(m))

A witness to a root cause outranks someone who heard about it second-hand. No off-the-shelf RAG system does this.

3-tier LLM router:  Ollama/Qwen2.5-3B ($0) -> Gemini Flash ($0) -> Claude API (~$0.002/debate)
Fine-tuning:        LoRA on Qwen2.5-3B | MLflow tracking | persona-consistency eval harness
Full-stack:         FastAPI + WebSocket <-> React + PixiJS isometric city UI
Tests:              48 passing
Total cost:         Under $5 to build. 118 commits.

Python TypeScript FastAPI React ChromaDB Ollama Gemini Claude LoRA MLflow NetworkX


Recall — Spatial AI Memory

Point your phone camera at your space. Ask out loud "where did I leave my keys?" Get a spoken answer with the exact frame it was seen in.

Not another AI wrapper. Persistent spatial memory across sessions. Time-decay re-ranking. Gemini Live function-calling into local ChromaDB. The voice model doesn't hallucinate locations — it calls a tool that searches a vector store built from what the camera actually saw.

Eval (June 2026):   Recall@1 100% (10/10) | Recall@3 100% (10/10) | Median latency 149ms
Embeddings:         all-MiniLM-L6-v2 via ONNX — fully local, zero embedding cost
Voice:              Gemini Live push-to-talk with function calling
Quota management:   120s minimum between vision calls + daily budget counter on-screen
Total commits:      162

Python FastAPI React ChromaDB Gemini Live ONNX WebSocket cloudflared


resume-job-fit-ai — AI Resume Scorer | Live Demo

Fit scoring, keyword analysis, AI-rewritten bullet diffs, multi-tone cover letter, interview prep, skills gap roadmap, LinkedIn optimizer — one click.

Deployed:    Streamlit Community Cloud (live now, free tier, no credit card)
Tests:       26 unit tests | GitHub Actions CI on every push
Outputs:     Pydantic-validated structured JSON — no brittle string parsing
Features:    12+ tools: multi-job comparison, application tracker, cover letter, DOCX export

Python Gemini Streamlit Pydantic SQLite pdfplumber GitHub Actions


Tech Stack

ai_ml    = ["RAG architectures", "multi-agent systems", "LoRA fine-tuning",
            "vector DBs", "LLM orchestration", "structured outputs", "evals"]

apis     = ["Gemini", "Claude (Anthropic)", "Ollama", "Gemini Live"]

backend  = ["Python 3.11+", "FastAPI", "WebSocket", "Node.js"]

frontend = ["React", "TypeScript", "Vite", "PixiJS"]

infra    = ["AWS", "Google Cloud", "Docker", "Streamlit Cloud", "cloudflared"]

tracking = ["MLflow", "Pydantic", "ChromaDB", "SQLite", "GitHub Actions CI"]

Currently

  • Building in public — LinkedIn
  • Open to AI engineer internships, applied AI roles, early-stage startups
  • Next: demo video for Recall + open-sourcing CivilizationOS fully

GitHub Stats

Top Languages

Popular repositories Loading

  1. Creding Creding Public

    1

  2. syzayd syzayd Public

    1

  3. github-profile-achievements github-profile-achievements Public archive

    Forked from Schweinepriester/github-profile-achievements

    A collection listing all Achievements available on the GitHub profile 🏆

    Markdown

  4. novatorem novatorem Public archive

    Forked from novatorem/novatorem

    Dynamic realtime profile ReadMe linked with spotify

    Python

  5. DeceptAI DeceptAI Public

    This project is about building an Artificial Intelligence system that can estimate whether a person is lying without listening to what they are saying. Traditional lie detection systems depend on: …

    Python

  6. clinical_trial_coordinator_env clinical_trial_coordinator_env Public

    Clinical trials generate billions in pharmaceutical revenue while directly affecting patient safety. Every trial depends on Clinical Research Coordinators (CRCs) who perform high-stakes, rule-bound…

    Python