
Responsible-Alliance-Protocol
Safety cannot be a prompt instruction. TBP provides an external execution-layer boundary for autonomous agents, enforcing hard F/I/W invariants via…

Safety cannot be a prompt instruction. TBP provides an external execution-layer boundary for autonomous agents, enforcing hard F/I/W invariants via…

agent runtime security - zero trust, zero setup, zero latency agent sandboxing

Fail-closed Cedar policy gate plus signed receipts for AI agent tool calls. npx protect-mcp

Theory and implemantation of the TBP protocol to secure networked AI in small to open web networks

Open-source sandboxed runtime for AI agents — gVisor/Docker isolation, credential vault, immutable audit log. Built after CVE-2026-25253.

credential isolation for AI agents. Agents never see real API keys - structural guarantee, not policy.

Open-source sandboxed agent harness for teams. Giving every employee a secured personal agent.

An SSH Agent that provides SSH keys stored in Bitwarden Secrets Manager

SRO PKCS11 – SSH Agent CNG est un agent Windows souverain, ultra‑léger et zéro‑dépendance qui unifie PKCS#11, SSH-agent, Pageant et CNG/Smartcard…

Agent Control Protocol (ACP) — Official English specification. Cryptographically verifiable authorization architecture for autonomous AI agents.

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

AI runtime inventory: discover shadow AI, trace LLM calls