Security●●●Banger
AERF – cryptographic receipts for AI agents, like cosign for evidence
Cosign for AI agents: cryptographically signed receipts for every agent action.
Bold BetZero to One
keertahacker
201mo ago
Back to browse
GitHub Repository
Agent Evidence Receipt Format (AERF) — an open specification for tamper-evident, independently verifiable records of AI agent actions.
4 starsPython
AERF, signed receipts for AI agent actions
by keertahacker·Jun 2, 2026·2 points·1 comment
AI Analysis
●●SolidBig BrainBold Bet
Cosign for agent evidence with compliance mappings, but still draft spec.
Strengths
- •Single-file Go verifier using only standard library enables independent audit
- •Maps to AIUC-1, HIPAA, SOC 2, ISO 42001, EU AI Act compliance frameworks
- •Ed25519 signatures over canonical JSON allow verification without AERF software
Weaknesses
- •v0.1.0-draft.1 spec with no stable release, producer lives in separate repo
- •Spec-first approach means adoption depends on framework integration
Category
Target Audience
Compliance teams, AI governance engineers, auditors
Similar To
cosign · SLSA · sigstore
Similar Projects
Security●●●Banger
Signet – Cryptographic action receipts for AI agents
Ed25519-signed action receipts for AI agents with hash-chained local audit logs.
Big BrainSolve My ProblemShip It
PrismerAI
302mo ago
AI/ML●●●Banger
Signed receipts for agent actions
Ed25519 signed receipts solve AI agent accountability across org boundaries.
Zero to OneBig Brain
jithinraj
203mo ago
Security●●Solid
Sanna – Enforce AI agent constitutions with cryptographic receipts
Governance rules live in version-controlled YAML and can be applied either by decorating functions with @sanna_observe or by dropping a gateway between an MCP client and downstream tools. It emits portable Ed25519-signed receipts you can persist and verify, which is a neat, practical way to build an auditable trail — the tough part will be ecosystem adoption around MCP and agent integrations.
Big BrainNiche Gem
nicallen
113mo ago
Infrastructure●●●Banger
AgentGate – Stake-Gated Action Microservice for AI Agents
Reintroduces economic friction to AI agents via stake-gated execution—genuinely novel.
Big BrainZero to One
selfradiance
103mo ago
AI/ML●●Solid
Hive Trust – Ed25519-signed benchmarks for every AI inference primitive
Ed25519-signed benchmark receipts when most AI claims are unverifiable marketing.
Big BrainNiche Gem
thehivery
2014d ago