Open framework for confidential AI
FIBO is a SOTA, first open-source, JSON-native text-to-image model built for controllable, predictable, and legally safe image generation.
Neural Network Verification Software Tool https://www.verivital.com Documentation:
The course provides guidance on best practices for prompting and building applications with the powerful open commercial license models of Llama 2.
See and fix what AI tools can read. One .offsend.yml keeps secrets out of AI context — synced to .cursorignore, .claudeignore & every AI ignore file. Local-first checks for prompts, file reads, shell, MCP, and agent history.
Safety harness for autonomous AI agents: Spec-driven AI factory. Use with any agentic CLI. Language-agnostic. Safe by design.
AAAI 2025 Tutorial on AI Safety
Security firewall and supply-chain verifier for Claude Code / Codex / Agent skills and MCPs.
Safety-Constrained Reinforcement Learning for Assistive Robot Navigation
Official implementation of "Uncertainty-Guided Semi-Supervised Learning for Safe Medical Image Classification".
Heike — The deterministic runtime for reliable AI agents. No more prompt roulette. 侍
Production-Grade LLM Alignment Engine (TruthProbe + ADT)
Evaluate high school math reasoning in LLMs with baseline and Chain-of-Thought (CoT) prompts. Includes confidence calibration metrics, JSON output parsing, and reliability analysis.
SOEA-Plus (PDEMC): 3-task biomedical metacognition benchmark evaluating LLM metacognitive control across 2 frontier models on 300 real PubMed examples. Reveals the Control Collapse Gap
A governed world-model evidence layer for AI agents: simulate bounded scenarios, track assumptions, score prediction-vs-reality error, and produce human-reviewable execution evidence.
Computable metric for autonomous internal dynamics in neural systems (CCI + MRC-C)
Bilingual public-safe tool for evaluating AI draft answers before release. Derived from ELUZA AI safety research; not ELUZA AI itself.
Official public beta hub for SignalOS by TanziTech — growth intelligence, approval-gated AI execution, guided testing, and product feedback.
Add a description, image, and links to the safe-ai topic page so that developers can more easily learn about it.
To associate your repository with the safe-ai topic, visit your repo's landing page and select "manage topics."