Sandlock

Superagent

SDK for AI agent safety that blocks prompt injections and unsafe tool calls, redacts PII and secrets, and runs red-team scenarios.

Pipelock

Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action.

Arcjet Js

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your JS/TS code

OpenAPPA

OpenAPPA is a deterministic guardrail that sits between an AI agent and its tools and tracks how data flows across tool calls, instead of asking a second model to judge each call. Policies decide whether untrusted or sensitive data may reach a given action, which blocks data exfiltration caused by prompt injection or hallucination while letting agents finish their tasks. It plugs into Claude Code, Pi, OpenCode, kAgent and Archestra, comes with reusable policy "batteries", validation, observability and reporting, and is backed by a NeurIPS workshop paper with published benchmarks. It is in preview as an open RFC.

1Password for Agents

1Password for Agents lets personal AI agents sign in to your accounts without ever seeing your passwords or one-time codes. When a supported agent reaches a sign-in page, it asks for a credential from your vault; you approve the request, and 1Password fills it straight into the site, so the secret never enters the model or its memory. You can see and manage which agents have access to what. It launched with integrations for agents such as Claude Duet, ChatGPT Work and dots, Meta's Muse and Grok Bot, and needs a 1Password plan.

Aletheore

Aletheore audits code repositories and backs every finding with evidence. Its deterministic scanner looks for leaked secrets, vulnerable dependencies and dead code, it can watch live endpoints and draw architecture maps, and it reviews pull requests automatically through a GitHub Action. A built-in MCP server lets coding agents run the same audits.