Security●●Solid
AgentSign – Zero trust for AI agents (OWASP-aligned)
Cryptographic agent passports when AI agent security is becoming a crowded category.
Big BrainSolve My Problem
AskCarX
103mo ago
Back to browse
AgentSign – Open-source zero trust engine for AI agents
by AskCarX·Mar 11, 2026·2 points·1 comment
AI Analysis
●●SolidBig BrainBold Bet
Zero trust security for AI agents fills the MCP identity gap before competitors do.
Strengths
- •Runtime code attestation prevents unauthorized agent actions before execution.
- •MCP Trust Layer secures model context protocol connections against tampering.
Weaknesses
- •Complex setup might deter smaller projects without dedicated security teams.
- •Five subsystems create significant integration overhead for simple bots.
Category
Target Audience
AI developers and security engineers
Similar To
Sigstore · SPIFFE
Post Description
Hi HN. This week Meta acquired Moltbook (agent social network), OpenAI acquired Promptfoo (agent testing), and Mandiant's founder raised $190M for Armadin. Agent infrastructure is clearly where things are heading.
We built AgentSign -- a zero trust engine for AI agents. The problem: agents are operating without any identity infrastructure. Moltbook went viral for fake posts because there was zero verification on who or what was posting.
AgentSign gives every agent a cryptographic identity certificate, signs every action into an execution chain, and runs runtime code attestation before anything executes. There's also an MCP Trust Layer for agent-to-MCP server verification, and a Stripe-powered Trust Gate for agent payments.
5 subsystems: identity certs, execution chain verification, runtime code attestation, output tamper detection, and cryptographic trust scoring.
Free and open source. Built in London.
SDK: https://github.com/razashariff/agentsign-sdk
Happy to answer questions.
Similar Projects
Security●●●Banger
MCPS – Cryptographic identity and message signing for MCP agents
TLS for MCP agents with ECDSA passports and L0-L4 trust levels, zero dependencies.
Big BrainZero to One
AskCarX
203mo ago
Security●●Solid
3 AI agent trust systems cross-verified each other's delegation chains
Delegation chains with accumulating caveats narrow authority at each agent hop.
Big BrainNiche Gem
dreynow
203mo ago
AI/ML●●Solid
Agent Trust – Cryptographic identity and reputation for AI agents
Cryptographic proof enforces agent permissions, not just Langfuse-style observability.
Big BrainNiche Gem
dreynow
113mo ago
Infrastructure●Mid
Agntor – Trust infrastructure for AI agents (identity, escrow, guard)
The SDK exposes the exact primitives you want for autonomous-agent commerce: register/resolve identity, attest and badge verification, create/fund/cancel escrows, release/slash settlements, and reputation queries — plus event hooks. It's a smart, timely idea to stitch payments and trust into agent URIs, but the repo still reads like an early SDK: docs and integration examples are thin and there's no clear public security/settlement audit or adoption evidence yet.
Bold BetNiche Gem
zeshama
214mo ago
Open Source●Mid
CambiOS – a new Rust-based, sovereign identity, zero-trust OS
Ambitious Rust microkernel OS, but seL4 and Redox already own the verification-ready space.
Bold BetShip It
jasonricca
807d ago