Open specification
ReddiAgent ADL
The open Agent Definition Language — define an AI agent once: model envelope, operating harness, and payment authority. Validate it deterministically. Run it anywhere.
The thesis
Agent = model definition + harness definition + settlement/reputation extensionUseful agents shouldn't start as vendor-specific scripts. ADL describes the job, model needs, tools, policies, eval gates, observability, and payment intent once — then compatibility reports tell you exactly what survives on each target (Microsoft Agent Framework, Google ADK, LangGraph, OpenAI, Anthropic, Gemini, Ollama…): supported, degraded, or unsupported. Nothing silently dropped.
Settlement is not success
USENIX Security 2026 research found security-rule violations in all 15 major x402 payment facilitators. Our answer ships in this release: a receipt-integrity validator that refuses to treat payment proof as service success — receipts must bind delegated authority, payment evidence, service outcome, and eval evidence across 10 layers, tested against a 14-case threat model (replay, wrong-payee, paid-but-denied). Hardened by three rounds of adversarial review: 33 attack probes, every one failing closed.
| x402 | payment challenge/proof — the rail |
| AP2 / Verifiable Intent | delegated authority — who allowed what |
| MCP | protected-resource access — what was touched |
| Solana | settlement proof — where value moved |
| RAP | receipts, accounting, reputation — bound above the rail |
Agents paying agents — both sides, today
Buyer side
A paid-research agent with a full payment authority contract: principal, spender, cap, expiry, revocation, receipts — human approval before any spend.
Seller side
Three delegation services (research, pricing, review) other agents can discover and pay — charge intents, receipt binding, reputation signals.
Dry-run rail only
Every example runs on x402-dry-run. Live settlement stays gated behind external audit — fail-closed by design.
Download
The bundle: canonical spec + machine-checked schema + 16 validated examples + v0.1→v0.2 migration guide + the receipt-integrity validator and conformance checker (runnable: python3 scripts/adl_v02_conformance.py examples/v0.2/simple-agent.yaml).
Spec home
The specification lives at github.com/nissan/reddiagent-lab — issues and structured review intake included.