Stipendex
Give your agent a stipend, not your credit card.
Open payment infrastructure for the agent economy: protocol + wallet + trust registry. Any LLM agent can safely pay any verified receiver — from half a cent for a paid MCP tool call to an $80 goods order.
Formerly working-titled ATP (Agent Transaction Protocol). The name is secured: stipendex.com · npm
stipendex
@stipendexscope · GitHub orgstipendex; trademark screening is pending (see roadmap). Status: specification 0.1-draft; the on-chain profile is live on Base Sepolia (LMB token, faucet, Market with purchase-bound reviews, market at 4agnts.com). English is the primary language of this documentation; a Russian mirror lives in docs/ru/.
The idea in three sentences
Agents have learned to act (MCP gave them hands) but not to pay: there is no standard way to delegate money to an agent with verifiable boundaries. Stipendex defines a minimal payment cycle (Quote → Proof → Receipt), a deterministic wallet kernel with a signed mandate — the only place where a payment decision is made (the LLM never touches money) — and a trust registry that answers "who may be paid at all". Settlement is executed by existing rails (Stripe, x402, ledger accounts) through adapters — Stipendex builds no new rails and competes with none.
Components
| Component | What it is | Openness |
|---|---|---|
| Stipendex specification | Quote/Proof/Receipt envelope, mandate, transports (MCP, HTTP), profiles | open spec |
@stipendex/wallet |
wallet kernel: SDK for agent hosts (limits, HITL, keys) | open source |
@stipendex/server |
paywall middleware for MCP servers and HTTP APIs | open source |
| Trust registry | signed descriptors of verified receivers; federated providers | open format; providers are commercial |
| Facilitator | accounts, payment verification, HITL queue, anti-fraud | open reference API; packages/facilitator is archived (see the on-chain profile) |
| On-chain profile | LMB token (EIP-3009), faucet with gas stipend, Market contract, catalog and relay at 4agnts.com | open source, live on Base Sepolia |
Three profiles
- Service profile — an agent pays for its own tools: micro-amounts, high frequency, session aggregation ("tab"), instant settlement. The protocol core.
- Checkout profile — an agent buys goods for a human: two-phase payment (hold on estimate+tolerance → capture of the confirmed amount), mandatory human confirmation, an evidence chain for disputes. Built on the 4agents order-flow v2.1 model.
- On-chain profile — no facilitator: a testnet token with a faucet, a market contract that records listings, purchases, encrypted deliveries and purchase-bound reviews. The live path today: docs/spec/onchain-profile.md.
Relationship to 4agents
4agents (a sibling project) is a trust layer for agentic shopping. The projects complement each other and share components:
- 4agents is the first Stipendex showcase: both the checkout profile (purchases from verified merchants) and the service profile (paid access to premium catalog tools).
- The 4agents verified-merchant registry is the first trust registry provider.
- The
@stipendex/walletis the agent-side GTM for 4agents ("install the wallet — your agent can buy safely") and the standard implementation of the HITL confirmation step from its order flow.
Details: docs/product.md.
Document map
| Document | Contents |
|---|---|
| docs/product.md | problem, positioning, 2026 landscape, distribution strategy, monetization |
| docs/spec/overview.md | roles, objects, invariants, adoption levels L0–L3 |
| docs/spec/envelope.md | Quote / Proof / Receipt, tolerance, tab sessions, idempotency |
| docs/spec/mandate-wallet.md | mandate, wallet kernel, HITL modes, Confirmation |
| docs/spec/transports.md | bindings: MCP (-32402) and HTTP (402) |
| docs/spec/rails.md | rail adapters: account, stripe-mpp, stripe-connect, x402 |
| docs/spec/checkout-profile.md | goods profile: hold→ACCEPT→capture, 4agents integration |
| docs/spec/onchain-profile.md | on-chain profile (live): LMB, faucet, Market, delivery envelopes, relay and catalog APIs |
| docs/security.md | threat model and normative requirements |
| docs/trust-registry.md | trust registry: descriptors, API, federation |
| docs/roadmap.md | phases, publication, licenses, MCP SEP |
| docs/ru/ | Russian mirror of this documentation |
| CONCEPT.md | archive (Russian): original concept v1 → critique → v2 (decision history) |
Principles (short version)
- The LLM never touches money. Payment decisions are made by a deterministic wallet against a signed mandate; the model has no "transfer to X" operation.
- A thin layer, not a sixth protocol. The envelope and the authority model are ours; the rails are others' (Stripe, x402, ledger accounts); commerce scenarios are others' (ACP/UCP/4agents).
- Works out of the box. The default
accountrail plus a hosted facilitator: a server monetizes in ~10 lines, an agent connects a wallet in ~5. - Aggregation by default. Micropayments accumulate on a session tab and settle on a threshold or session close; per-call settlement is an option, not the default.
- Default deny. Payments go only to receivers on the allowlist / trust registry; a new receiver always requires human confirmation.
- Honest amounts. When the final amount is unknown — hold on estimate+tolerance, capture only the confirmed amount (≤ hold). No blank checks.