
ironclaw
Secure, private AI agent operating system with local encrypted storage, OAuth/SSO authentication, policy-based access control, and extensible…

Secure, private AI agent operating system with local encrypted storage, OAuth/SSO authentication, policy-based access control, and extensible…

Runtime Security for tool-using AI agents, with local policies, pre-action enforcement, and forensic audit trails.

🔱 The only independent credential proxy for AI agents: bring-your-own-vault isolation & least-privilege request policies. Your keys stay where you…

Runtime security gateway for AI agents: cryptographically attests tool calls, enforces policies, sandboxes execution, and logs tamper-evident audit…

Agent-Isolated Credential Broker for AI Agents

Overlay network protocol giving AI agents permanent addresses, authenticated encrypted tunnels, and a trust model over UDP. Includes NAT traversal,…

Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.

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

A HTTP credential proxy and vault for AI agents like Claude Code, OpenClaw, Hermes, custom agents + harnesses, and more.

Thin TypeScript + zero-dep Python client and recipes to gate high-risk actions behind a payload-bound passkey approval.

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

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

Ed25519 signed receipts + Cedar policies for AI agents. Finance mandate gate (Legate), proof packs, 3 IETF Internet-Drafts. npx protect-mcp

CVE-2026-54519 / GHSA-qv97-83w4-ff86: ai-agent-automation memory authorization advisory landing page

Open-source security gateway & static scanner for AI agents. Enforce role-based access control (RBAC), human-in-the-loop approvals, segregation of…

Cryptographically signed delegation receipts for AI agents. Define exactly what an AI can and can't do — signed, verifiable, tamper-proof.

Research and analysis of the ServiceNow Virtual Agent vulnerability (CVE-2025-12420), including attack flow, MITRE ATT&CK mapping, detection…

A unified, security-first wire protocol for tool access and agent coordination. UAP eliminates CVE-2025-49596 and MCP tool-poisoning vulnerabilities…