20 projects
trainlens
Notebook-first tools for understanding datasets and machine-learning training runs.
emdashify
Convert double hyphens into em dashes in Python, Markdown, and Word documents. No AI required.
astscribe
Understand unfamiliar ML notebooks with evidence-backed explanations inside Jupyter, without LLMs.
lastlight
Low-power, offline retrieval for disaster and infrastructure-failure guidance.
nexo-agent-protocol
Agent-to-agent messages, plain text, image transfer, and optional encryption
spectralaudit
Explainable, offline DSP for spectral audio forensics and persistent frequency-pattern analysis
text-to-music-prompt-structurer
Create and validate structured Suno prompts with NLP-inspired music parsing.
egypttranslit
A small Python library for converting Egyptological transliteration to IFAO-style or canonical Unicode.
matplotlib-dark
Automatic dark themes for Matplotlib, with one-line activation
vlm-prior-probe
Black-box behavioral probes for measuring visual-evidence reliance and learned-prior persistence in Vision-Language Models.
evidenceflow
Analyze how retrieved and tool-generated evidence propagates through AI-agent execution traces.
context-dedup
Detect and remove redundant context before sending it to an LLM.
vlm-occlusion
Find which image regions influence a VLM claim through grid-based occlusion testing.
parametricbench
Catch LLM and VLM regressions with lightweight, parameterized benchmarks for any Python callable.
visual-patch-audit
Compare and audit image patches for VLM and computer vision workflows.
embedding-drift-lite
Compare two embedding sets and detect drift between versions.
rag-chunk-audit
Find common quality and safety issues in RAG chunks before indexing.
metaclean-vlm
Remove metadata from image datasets before VLM training or ingestion to reduce hidden prompt injection risk.
promptshield-llm
Redact sensitive data from LLM prompts before sending them to a model.
openai-image-token-counter
Calculate token costs for images in OpenAI Vision API
