Validate what an MCP server declares against what it actually does. Declared-vs-observed checks with a tamper-evident SHA-256 evidence ledger. Zero runtime...

You've probably been using agents irresponsibly. Today, you can turn a new leaf.

Open AI Permit specification for pre-execution AI action authorization records

Static AI Agent Risk Analyzer for AI applications. Detects capabilities, prompt risks, tool permissions, MCP integrations, governance gaps, and autonomy...

A next-generation, source-available AI workspace with a self-evolving agent runtime for editable code, design, presentations, websites, and video—a Codex...

MEGaNorm is a Python package for normative modeling on MEG and EEG data.

Normative modelling of neuroimaging data

Versioned, machine-readable dataset answering: does a given Claude Code CLI flag, env var, or command exist in version X? Sourced only from official public...

A tiny, dependency-light Go daemon that hosts a remote Claude Code session over SSH: CLI-version manager + process supervisor + JSON-RPC multiplexer (with a...

Analyzes installed packages allowing to verify compliance with allowed licenses.

Context-aware LLM naming for Strava activities — single-athlete backend service

Provael red-teams open vision-language-action (VLA) robot policies in simulation and reports an Attack Success Rate with a confidence interval. Every attack...

Opinionated MongoDB application toolkit for .NET (Dilcore MongoDB v2 roadmap)

Credential-brokered enforcement and cryptographic evidence for autonomous AI agents. Part of the Empire Stack — built on ACI, AIP, and AJSON open standards.

Standalone open-source verifier for WitnessOS evidence bundles - SHA-256, Merkle chains, certificate validation. Verify AI action receipts with no gateway...

base85n

Diagnostic tool for detecting ungoverned, unregistered, or misbehaving AI agents in your environment

Open specification for describing organizations to autonomous agents through structured, machine-readable contracts.