6 projects
agent-safety
Idiomatic, zero-dependency, provider-agnostic Python safety layer for AI agents: least-privilege permissions, prompt/input/output guards, sandbox + SSRF guards, quotas/rate/deadline/concurrency/risk budgets, loop detection, human-in-the-loop approval, constitutional rules, action previews, honeytokens, audit/tracing, and Claude/OpenAI/Gemini/MCP tool-call integration.
pokemon-card-recognizer
Pokemon TCG Card Recognizer
pokemon-go-video-analysis
Pokemon Go Video Analysis
ocr-ops
OCR-Ops
algo-ops
Algo-Ops Framework
ezplotly
An easy wrapper for making Plotly plots in Jupyter notebooks
