cryptographic-receipts

Autonomous BTC & SOL trading bot for Polymarket. ARB (100% WR) + SNIPE strategies. Auto-trades via py-clob-client, auto-claims resolved positions, Ed25519 signed receipts.

Stop Claude Code from doing irreversible damage. Policy-gated execution + receipts so you can ship agents without sweating production.

Trust infrastructure for AI agents — constitution enforcement and cryptographic receipts. Python SDK.

Cryptographic audit receipts for AI coding agents. Ed25519 + Merkle + RFC 3161 TSA. Supports Claude Code, Codex CLI & Cursor.

Constitution enforcement and cryptographic receipts for OpenClaw agents. Every tool call governed, every decision signed.

Append-only event kernel with Ed25519-signed Merkle checkpoints. Every AI action gets a verifiable receipt.

Private, signed work receipts for AI agents. Local-first MCP server with EIP-712/Ed25519 proof, replay protection, and optional AIPOU rewards on Base.

Apache-2.0 licensed lightweight agent sandbox: Cedar policy + Ed25519-signed receipts in one Rust binary. Design-partner preview.

Defines the decision layer for AI systems where deployment outcomes are governed, recorded, and reconstructable. 5th conforming implementation of draft-farley-acta-signed-receipts (IETF).

Trust infrastructure for AI agents — constitution enforcement and cryptographic receipts. TypeScript SDK.

RIO Receipt Protocol — Cryptographic proof for AI actions. Open standard for tamper-evident receipts, hash-chained ledgers, and independent verification.

The receipt format for licensed human identity: spec, JSON Schema, API surface, and a zero-dependency verifier. Check our receipts yourself.

Coordination primitive for bounded disclosure between AI agents

kolm — the AI compiler. Compile any task into a signed .kolm artifact that runs locally. RS-1 open spec, MIT.

Sanna Protocol v1.2 — specification, JSON schemas, and golden test fixtures for AI governance receipts.

The Internet of AI — autonomous infrastructure for AI agents. Identity, memory, compute, deployment, payments, reputation, verification. All on-chain.

MCP server for EverMint — Tamper-evident receipts for AI agent actions. The notary layer for agent-to-agent transactions.

Persistent memory for AI agents. Provenance-aware scientific knowledge graph, read-only MCP server, signed contributions, quarantined publication, schemas and an offline receipt verifier.

Cryptographic execution receipts for AI agents: signed, hash-chained proof of authorized tool use. If it changes it can't be run, if it runs, it can be proven.

Hands-on practical guide to runx: governed agent skills, cryptographic receipts, and skill authoring