A cryptographic utility providing verifiable Ed25519 proofs for any computation using AWS Nitro Enclave technology.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install prethereum
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install prethereum using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
Prethereum is a sophisticated security tool designed to provide verifiable proofs for arbitrary computations. By utilizing Ed25519 signatures over SHA-256 digests, it creates a tamper-proof record of data states. This tool is especially powerful for users of Openclaw Skills who require high-assurance proof that specific data was processed by a secure, hardware-isolated Trusted Execution Environment (TEE).
The core value of Prethereum lies in its security model: the notary service runs inside an AWS Nitro Enclave, ensuring that signing keys are never exposed and no data is persisted. This architecture allows developers to build trust into AI-driven workflows, providing a verifiable bridge between agentic actions and cryptographic certainty.
To start using this tool with your Openclaw Skills setup, install the core package:
npm install prethereum
For AI agent integration via the Model Context Protocol (MCP), install the server globally:
npm install -g @prethereum/[email protected]
You may optionally configure the OCC_NOTARY_URL environment variable to point to a specific enclave endpoint.
Prethereum utilizes a self-contained JSON wire format for its proofs. It prioritizes privacy by ensuring no data persistence on the notary side.
| Component | Type | Description |
|---|---|---|
| Bytes | Input | User-provided data to be signed |
| Digest | SHA-256 | The cryptographic hash of the input bytes |
| Signature | Ed25519 | The TEE-generated signature over the digest |
| Proof | JSON | The final package containing the signature and necessary metadata for offline verification |
Loading
A cryptographic auditing plugin for OpenClaw that generates tamper-proof proofs for every action the agent takes.

A systematic framework for AI agents to log errors, user corrections, and new insights to drive continuous performance improvement.

An advanced intelligence pipeline that synthesizes raw multi-source data into authoritative, high-density geopolitical briefings.

A high-performance execution environment that allows AI agents to write and run code on the fly to solve any computational or system task.

A time-blind friendly planning framework for Openclaw Skills designed to support executive function and neurodivergent workflows.

An expert AI skill providing structured guidance in Jungian analytical psychology, shadow work, and archetypal analysis.








































