BiasClear is open-source structural persuasion detection infrastructure for the AI ecosystem. It audits text for rhetorical manipulation patterns such as manufactured consensus, authority substitut...
Open-source npm package for entity matching across inconsistent government databases — resolving identities between FEC filings, Congress.gov records, lobbying disclosures, and committee data.
Civic intelligence platform serving 198 API endpoints across 19 government data sources (Congress.gov, FEC, USASpending, Senate lobbying disclosures, Federal Register, OpenStates, Census Bureau, an...
Open-source npm package providing statistical analysis primitives for civic data — correlation analysis, peer comparison, confidence scoring, and baseline calculations designed for government acc...
toqito is an open-source Python library for studying quantum information and quantum computing. It provides a comprehensive suite of tools for working with quantum states, channels, measurements, a...
Python-based Discord bot for community data access and engagement.
iOS application for AQI monitoring (Work in Progress).
TypeScript-based web interface for the initiative and AQI monitoring.
Android application for hyper-local AQI monitoring.
Python backend API handling Open-Meteo and AirGradient sensor data processing. As well as being publicly available to access, either freely or through the apps/website/bot.
CLI pipeline that pulls model metadata from HuggingFace, W&B, and MLflow, runs fairness analysis, checks EU AI Act compliance, and exports model cards.
Supply chain security for LLM artifacts using Sigstore, in-toto, and SLSA frameworks. Generates signed attestations for model weights, training data, and inference outputs.
Cryptographic ledger for AI output verification using Merkle trees and digital signatures. Tracks, timestamps, and proves the authenticity of AI-generated content with tamper-evident audit trails.
Rule-driven scanner that checks AI systems against EU AI Act, UK AI regulations, and NIST AI RMF requirements. Deterministic pass/warn/fail scoring.
Multi-modal safety evaluation benchmark for AI systems. Covers 20 hazard categories and 9 attack strategies aligned with MLCommons AI Safety standards.
Multi-modal AI content detection and C2PA provenance verification across text, images, audio, and video. Explainable confidence scoring with signal-by-signal breakdown.
Policy-first retrieval-augmented generation gateway with PHI/PII redaction, access control, and audit logging. Self-hostable with no mandatory cloud dependencies.
Runtime firewall that detects and blocks prompt injection attacks against LLM applications. Covers OWASP LLM Top 10 attack vectors with configurable detection rules.
Kubernetes-native observability tool using eBPF to capture kernel signals and correlate them with OpenTelemetry traces for LLM SLO attribution.
Transparent proxy for multi-provider LLM cost tracking, budgeting, and optimization. Supports OpenAI, Anthropic, Azure, Bedrock, and Vertex AI with real-time cost headers.
Bradley Slimp
BreatheOSS