Search

Turn the bots hunting your site for secrets (.env, .git, SSH keys) into its safest answers. A standard and zero-dependency audit: a clean 4xx, nothing shaped like a credential, no traps, and, if you want, a harmless joke with a note for the AI agents that

Local-first endpoint sensor for AI coding agents: hash-chained audit trail, MITRE-mapped sequence detection, DLP

A security scanner for your LLM agentic workflows

Verifiable security contracts for AI agent actions

Zero-trust API firewall and security integrity layer for autonomous AI agents & Model Context Protocol (MCP) tool execution. Secure, TOCTOU-proof, fail-closed.

Inter-agent security firewall for multi-agent AI systems

Collaborative application security testing between humans and agents via CLI and MCP

DevFortress SDK — API and application security with automated threat response, session privacy, and AI agent observability.

CLI tool to manage OpenTrust AI Agent Runtime Security Platform — setup, start, stop, status, logs

Ares — AI-native host security investigator for Linux: continuous eBPF telemetry with minute-by-minute AI investigation.

A lightweight security layer that filters the inputs and outputs of LLM and agent applications — prompt injection, jailbreaks, leakage, secrets, PII and unsafe actions.

Security runtime for AI agents — intercepts tool calls, enforces capability tokens, tracks provenance, and produces tamper-evident audit logs

Security-first agent harness built for long horizon research and work capabilities with increased focus on math, computer science, and domain science research

AI-native security scanner for the post-LLM era. Detects secrets, IaC misconfigurations, MCP tool poisoning risks, and OWASP LLM Top 10.

Sandboxed multi-scanner security for AI skills, MCP servers, and package trees — coverage honesty, SIE judging, heatmap posture, guided triage and fix. Scan what agents install; fail closed.

Security sandbox, permission system and tool guard for the Pi coding agent (pi): enforce filesystem allow/deny lists and network domain allowlists on read, write, edit, bash, grep, find, ls, fetch_content and web_search, with interactive ask prompts, secr

Multi-agent AI penetration testing workbench. Evidence-enforced anti-hallucination, agent-agnostic (Claude/Codex/OpenCode/Cline/Trae), continuously growing memory.

Next-Gen AI-Aware Git

Semgrep rules for AI agent code: static analysis for LLM applications in Python, TypeScript and JavaScript. Finds model output reaching exec, shells, SQL, URLs, files and HTML, user input in system prompts, over-broad tools, MCP servers without auth, leaked keys and unsafe model loading. 36 tested rules, CWE and OWASP mapping.

Tiered prompt-injection validation layer. Zero-dep sub-ms Tier 0 core (Node + edge identical), optional local ML + remote guard tiers.