14 projects
ai-agent-risk
Risk modeling for AI agents from logs: replay a proposed change over logged episodes and separate what the log settles, what a declared stop valuation fixes, and what needs bounds.
pyod
A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 61 detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.
agent-style
The Elements of Agent Style: a literature-backed English technical-prose writing ruleset for AI agents, with CLI install/enable/disable for 9 primary agent surfaces.
ai4fire
Task metadata and a lookup CLI for the AI4Fire wildfire benchmark for language models and agents
anywhere-agents
Install the anywhere-agents AI agent config (AGENTS.md, skills, guard hook, settings) into any project.
catchbench
CatchBench: a benchmark for auditing agent failures across the full lifecycle.
agent-defs
Definitions for agent security tools: public rule sets and risk corpora, scored against outside benchmarks, watched for changes, and preserved after the source disappears.
auditable
An open-source system of record for AI-agent decisions: it captures what each decision relied on, replays it against live state, and rolls back the committed action when it no longer holds.
vibesignal
Physical status light for coding agents (Claude Code / Codex) via busylight
suod
A Scalable Framework for Unsupervised Outlier Detection (Anomaly Detection)
pytod
Tensor-based outlier detection. A general GPU-accelerated framework.
combo
A Python Toolbox for Machine Learning Model Combination
metaod
Automating Outlier Detection via Meta-Learning (selece/recommend OD model(s) for new datasets)
meta-blocks
A modular toolbox for accelerating meta-learning research :rocket:
