AEVS
AIOpen-source SDK that creates tamper-evident, cryptographically signed receipts for every tool call an AI agent makes.
AEVS
Open-source SDK that creates tamper-evident, cryptographically signed receipts for every tool call an AI agent makes.
About AEVS
AEVS (Agent Execution Verification System) is a drop-in SDK that produces tamper-evident proof of execution for AI agent actions. It sits between an agent and its tools and captures every invocation — tool name, inputs, output, timing, and errors — then seals each record as an ECDSA (P-256) signed receipt linked to the previous one in a hash chain, so any alteration or skipped step is detectable. Receipts can be verified independently through a public API or explorer using a reference ID, without access to the original codebase. AEVS auto-detects frameworks like LangChain and MCP, installs via pip, and is open source under fetchai/AEVS-sdk, currently in beta.
Screenshots
Key Features
Use Cases
Frequently asked questions about AEVS
What is AEVS?
Open-source SDK that creates tamper-evident, cryptographically signed receipts for every tool call an AI agent makes.
How does AEVS work?
AEVS works by combining Signed Receipts: Records every tool call and seals it with an ECDSA P-256 signature backed by KMS., Hash-Chained Logs: Links each receipt to the previous one so tampering or skipped steps are detectable., Independent Verification: Confirms signatures via a public API or explorer using only a reference ID., Drop-In SDK: Installs with pip and wraps existing tools without changing them., Framework Auto-Detection: Automatically integrates with LangChain and MCP-based agents. to help users with Agent Auditing: Keep a verifiable record of exactly what an agent did and when., High-Stakes Actions: Prove execution of sensitive operations such as payments or refunds., Compliance Evidence: Provide tamper-evident logs for regulated or accountable workflows., Debugging Agents: Inspect tool inputs, outputs, timing, and errors for each call., Third-Party Verification: Let external parties confirm an action occurred without sharing source code..
What are the main features of AEVS?
Key features include Signed Receipts: Records every tool call and seals it with an ECDSA P-256 signature backed by KMS., Hash-Chained Logs: Links each receipt to the previous one so tampering or skipped steps are detectable., Independent Verification: Confirms signatures via a public API or explorer using only a reference ID., Drop-In SDK: Installs with pip and wraps existing tools without changing them., Framework Auto-Detection: Automatically integrates with LangChain and MCP-based agents..
Who is AEVS for?
AEVS is useful for anyone interested in Agent Auditing: Keep a verifiable record of exactly what an agent did and when., High-Stakes Actions: Prove execution of sensitive operations such as payments or refunds., Compliance Evidence: Provide tamper-evident logs for regulated or accountable workflows., Debugging Agents: Inspect tool inputs, outputs, timing, and errors for each call., Third-Party Verification: Let external parties confirm an action occurred without sharing source code..
How much does AEVS cost?
AEVS is free to use.
How do I get started with AEVS?
Visit https://aevs.fetch.ai/ to sign up and explore AEVS.
Explore more AI Ai Tools tools
Browse all Ai Tools tools →Compare AEVS: vs Halo by Scam AI · vs Cleanlist AI · vs Screencap · vs OpenCodeReview