Work
Products and open source.
Real things that run. I lead with what they do and whether the tests pass, not vanity numbers.
Products
Shipped and in use.
FLAGSHIP
Poplygo
Live Q&A and real-time polling for any audience. Anonymous questions with upvoting, instant polls, moderation, present mode, an OBS/vMix overlay, QR join, and CSV export. Free, no signup.
STUDIO
Dynarq
My software studio building AI-native web ecosystems and digital employees that run the work around the clock. AI integration, custom software, automation, and cloud.
PRODUCT
TUTUS
A lightweight Windows app that locks sensitive desktop apps behind master-password authentication. Offline, quiet in the background, and free.
Open source
Small, tested, runnable.
Python
jsonmend
A zero-dependency library and CLI that extracts and repairs JSON from messy LLM output: Markdown fences, prose, single and smart quotes, Python constants, unquoted keys, comments, trailing commas, and responses truncated mid-object.
CI passingTypeScript
envaudit
A zero-dependency CLI that audits environment variables across modern JS stacks: vars the code reads but nothing defines, dead vars, credentials committed to .env.example, and secret-looking names inlined into the client bundle.
CI passingPython
dynarq-shield
A prompt-injection and data-leak firewall for LLM apps. Channel-gated detectors, Unicode normalization to defeat evasion, additive risk scoring, allow/flag/block. Pure stdlib, zero runtime deps.
CI passingPython
rag-pipeline
A retrieval-augmented generation pipeline from scratch: chunk, embed, FAISS store, retrieve, and generate grounded answers with citations. Local no-GPU, optional hosted mode.
CI passingPython
dynarq-agent
A minimal AI agent runtime with a tool and skill interface, a tool-calling loop, and pluggable backends. Six built-in tools with path-traversal and SSRF guards.
CI passingPython
llm-finetune-lab
LoRA and PEFT instruction fine-tuning with prompt masking. TinyLlama by default, a distilgpt2 CPU smoke test, and a generate script to try the trained adapter.
CI passingPython
llm-eval-harness
Deterministic evaluation of model answers: exact match, contains, token F1, ROUGE-L, and retrieval metrics, plus an optional LLM judge and a report renderer.
CI passing