Launching today
AEVS
proof-of-execution for AI agents
161 followers
proof-of-execution for AI agents
161 followers
AEVS (Agent Execution Verification System) is a drop-in SDK that records every AI agent tool call and gives agents verifiable execution receipts. It captures the tool, inputs, outputs, status, and timing as tamper-evident proof, so teams can verify what an agent actually executed without relying on chat history or fragile logs.
Hey Product Hunt 👋
We built AEVS at Fetch AI because as AI agents start doing real work, it’s becoming harder to answer a simple but important question:
What did the agent actually execute? 🤔
Chat history can tell you what an agent said. Logs can help, but they’re often scattered, incomplete, or easy to lose. For agents that call tools, trigger workflows, move data, or interact with external systems, teams need something stronger: a verifiable record of execution ✅
That’s what AEVS provides.
AEVS is a drop-in SDK that records every AI agent tool call as a tamper-evident execution receipt
Each receipt captures the tool used, inputs, outputs, status, and timing, so teams can verify what an agent actually did without relying only on chat history or fragile logs.
The goal is to make agent execution more trustworthy, auditable, and production-ready 🔐
It’s designed for builders working with agent frameworks like LangChain/LangGraph, MCP tools, and custom agent stacks 🛠️
You can add AEVS to your existing workflow and start generating verifiable receipts for tool calls without rebuilding your agent from scratch 🚀
We’re especially interested in use cases where agents perform actions that matter: customer support workflows, financial operations, internal tools, compliance-sensitive tasks, data pipelines, and API automation
I’d love feedback from agent builders, infra teams, and anyone thinking about trust and verification for AI systems 🙌
The receipt model makes sense for agent workflows where a tool call can change customer state, like support ops or billing automation, and chat logs are not enough. Capturing inputs, outputs, status, and timing as a receipt feels useful, but the edge case I’d worry about is sensitive payloads. Can teams redact specific fields before the receipt is written while still keeping the proof tamper-evident?
@hazy0 Great question. AEVS doesn't always store complete receipt data, we designed it with privacy in mind and support 3 visibility levels:
• Public: full receipt data is visible to verifiers
• Private: only key metadata and input/output hashes are visible to verifiers, while the owner can still access the full data in the dashboard
• Proof Only: only receipt metadata is shared with AEVS; no input/output data leaves the agent runtime
And along with receipt visibility levels you can also choose whether receipts are discoverable on the AEVS Explorer or remain private.
That split is helpful, especially Proof Only for internal tools where the verifier needs integrity without payload exposure. If a team switches a workflow from Private to Proof Only later, do existing receipts keep their original visibility, or can the owner rotate/redact old receipts after the fact?
@hazy0 Receipts are immutable once created. If a workflow is switched from Private to Proof Only later, existing receipts retain the visibility mode they were created with. Visibility settings apply only to future receipts, and past receipts cannot be retroactively modified or redacted without breaking their cryptographic integrity.
This resonates. I ship an MCP server for ad-account monitoring, and the audit log of every tool call (tool, sanitized params, latency, result) turned out to be the feature people trusted most, especially once agents could trigger actions on live accounts. The piece I'd add: receipts answer "what happened," but for actions that move money or change customer state, the bigger win is gating the write before it executes, not just proving it after. Receipt plus an approval step is the real combo. Are you thinking about a pre-execution hook, or is AEVS purely the record after the call fires?
@hunter_upscale really good idea, pre-approval on specific tool calls is worth exploring for high-stakes actions
This hits a real trust gap for agents: chat history is not an execution log. Tamper-evident receipts for tool calls could become table stakes. Are receipts designed to be portable across agent frameworks, or mostly SDK-local at launch?
@sarveshsea receipts are just standard structure and can be created for any framework, currently AEVS support Langchain, and MCP framework and support for CrewAI is lined up for next release
Can AEVS verify why an agent made a decision, or only what action it executed?
AEVS
@therohanraghuwanshi AEVS focuses on verifying what an agent executed, not why it made a particular decision. It captures and verifies actions, tool calls, inputs, outputs, and execution metadata, creating an auditable record of what actually happened. The agent's internal reasoning remains separate from the verification layer.
One thing we're particularly excited about is how easy AEVS is to adopt.
✅ ~2 lines of code to integrate
✅ Supports LangChain, LangGraph, and MCP today
✅ CrewAI support coming soon
You can even tell your coding agent:
and it can help integrate AEVS directly into your workflow.
Our goal was simple: make verifiable agent execution accessible without forcing developers to redesign their existing stack.
Stripo.email
Congrats on the launch! As agents become more autonomous, knowing what they actually did becomes just as important as what they said. The execution receipt concept is really interesting.
@alina_tyslenok_ Thanks! We believe verifiable execution will become a core building block as agents take on more real-world responsibilities.