Search

Capsule plugin for the LiteLLM gateway — forwards completion requests to the Capsule agentsecurity service for centralized policy enforcement and audit.

A system-level defense framework for AI agents that intercepts and blocks indirect prompt injection attacks using strict instruction provenance and dynamic policy enforcement.

Open-source MCP server that lets AI agents call APIs without ever seeing the credentials. Policy-enforced secret injection into HTTP calls and subprocesses, with encrypted audit trail.

Credential isolation for AI agents. Store, guard, and record — your agent never sees your API keys.

Terminal proxy that intercepts AI agent shell commands and requires human confirmation before destructive operations

A general immune system for LLM applications: two lines, every call, reflexes at every boundary.

RL-based adversarial red-team agent for LLM systems

Paid social-engineering workbench CLI for AI agents.

v0.6 signing-time gate for Solana: decode any base64 tx offline, classify 37 danger primitives + Native Stake + bounded ATA/Memo recognition + a 14-program DeFi/NFT clear-signing registry, resolve ALTs and clear-sign Squads proposals with --rpc, optionall

Production hardening guide for AI agents — prompt injection defense, tool sandboxing, and credential management

A hardened, containerized environment for running Claude Code as an AI agent with access to local tools via the Model Context Protocol (MCP).

Deterministic, zero-LLM defense layer for AI agents — block prompt injection and tool hijacking with taint tracking

Real-time adversarial-input firewall for Pipecat voice agents — blocks prompt injection, PII-extraction, and policy-override before the LLM acts on it.

Scan repositories to detect GenAI and Agentic AI applications, identify LLM usage, and analyze agent intent

Riverbraid v1.5.0 | Resonant Intelligence Architecture

Layered operator screening and session-hijack resistance for AI-agent platforms (alpha)

A curated collection of Claude Agent Skills designed to enhance AI workflows with specialized capabilities.

Reverse proxy firewall + LLM Gateway for AI agents

Native safety hooks for Claude Code — blocks destructive commands, enforces tool-call budgets, guards file reads, masks secrets, and audits every agent action. Fail-closed C++ daemon with extensible rule engine.

Compound-path and cross-release analysis of what an AI agent is permitted to do