Agent Passport – OAuth-like identity verification for AI agents
Hi HN, I built Agent Passport, an open-source identity verification layer for AI agents. Think "Sign in with Google, but for Agents." The problem: AI agents are everywhere now (OpenClaw has 180K+ GitHub stars, Moltbook had 2.3M agent accounts), but there's no standard way for agents to prove their identity. Malicious agents can impersonate others, and skill/plugin marketplaces have no auth layer. Cisco's security team already found data exfiltration in third-party agent skills. Agent Passport solves this with: - Ed25519 challenge-response authentication (private keys never leave the…
In plain words
Agent Passport is an open-source identity verification system for AI agents that works similarly to OAuth login services. It addresses the lack of standardized authentication as AI agents become increasingly common, preventing malicious agents from impersonating legitimate ones and securing skill and plugin marketplaces. The system uses Ed25519 cryptography for challenge-response authentication, issues time-limited JWT tokens, and includes a risk-scoring engine that rates agents for allowing or blocking access. Developers can verify agent identity with a single line of code using the npm SDK.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN, I built Agent Passport, an open-source identity verification layer for AI agents. Think "Sign in with Google, but for Agents." The problem: AI agents are everywhere now (OpenClaw has 180K+ GitHub stars, Moltbook had 2.3M agent accounts), but there's no standard way for agents to prove their identity. Malicious agents can impersonate others, and skill/plugin marketplaces have no auth layer. Cisco's security team already found data exfiltration in third-party agent skills. Agent Passport solves this with: - Ed25519 challenge-response authentication (private keys never leave the agent) - JWT identity tokens (60-min TTL, revocable) - Risk engine that scores agents 0-100 (allow/throttle/block) - One-line verification for apps: `const result = await passport.verify(token)` It's fully open source (MIT), runs on free tiers ($0/month), and has a published npm SDK. GitHub: https://github.com/zerobase-labs/agent-passport Docs: https://github.com/zerobase-labs/agent-passport/blob/main/do... Live demo: https://agent-passport.vercel.app Built this because I kept seeing the same security gap in every agent platform. Happy to answer questions about the architecture or the agent identity problem in general.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
