The institutional record for autonomous work

Provable. Payable.
Institutional.

AiGentsy is a family of signed institutional graphs that makes agent work accountable — provable at handoff, acceptable before consequence, settleable when value moves.

Proof at handoff. Acceptance before consequence. Settlement when value moves.

Try It Now Run Quickstart Read Docs

14 framework integrations · Free today · Apache 2.0

Full protocol live. Specs public. Standalone verifier on PyPI. Agent starter in v1.7.0. Governance by default.

Provable. Payable. Institutional.

Provable

Every consequential agent output can carry cryptographic proof of authority, coordination, and outcome — offline-verifiable without depending on AiGentsy servers.

Payable

Settlement happens only after proof and acceptance. Attach payment providers or downstream release flows without custody, gas, or tokens.

Institutional

AiGentsy is a family of signed graphs that describes every material relationship in autonomous agent work — mandate, coordination, value flow, trust, lineage, agreement, and durable accountability.

Proof at handoff. Verification at acceptance. Settlement when value moves or work advances. Audit after the fact.

Verification proves the artifact held. Acceptance decides whether the work met the mandate.

See it happen in 60 seconds

Live settlement on our production protocol. Real ProofPack, real Merkle log, test-mode Stripe.

Three ways to start
MCP: Claude, Cursor, Cline, and growing

MCP exposes 13 proof, verification, settlement, and acceptance tools to any MCP-compatible runtime. Zero SDK install.

"mcpServers": { "aigentsy": { ... } }
MCP setup guide →
Python SDK + Agent Starter (v1.7.0)

Full protocol client plus create-agent — the first reference adapter for the Settlement-Native Agent Core.

pip install aigentsy==1.7.0

Use create-agent when you want the settlement-native starter.

SDK docs →
Offline Verifier

Verify any proof bundle in-browser or in Python. Zero runtime dependency. RFC 6962 compliant.

pip install aigentsy-verify
Try verifier →
Now in aigentsy v1.7.0
Create a settlement-native agent
pip install aigentsy==1.7.0
aigentsy create-agent my-agent --template settlement-native-mcp

Build your agent anywhere. With AiGentsy, it can be born knowing when work needs proof, acceptance, and settlement.

AiGentsy is the accountability standard agents are built with — the layer agent factories build in.

First reference adapter for the Settlement-Native Agent Core. Local scaffold; no network or credentials needed to run. PyPI →
The protocol flow

Every settlement moves through five linked stages. Proof is stamped, verified, accepted, settled, and exported as a portable record.

Stamp
Agent submits proof
→
Verify
Hash chain + Merkle check
→
Accept
Policy or manual gate
→
Settle
Exactly-once consequence
→
Export
Portable proof bundle

Attach any payment provider on acceptance. No custody.

How settlement happens on AiGentsy

Settlement on acceptance
Settlement triggers only when proof verifies and the appropriate acceptance gate passes. Exactly-once consequence, no custody.
Proof at handoff
Every deliverable becomes a portable, offline-verifiable cryptographic receipt.
Governance before handoff
Compute and authority rules are explicit before consequential work advances. Every consequential decision carries a cryptographic signature, bound into the ProofPack.

Five layers of settlement

Most systems prove a transaction completed. AiGentsy proves the work happened — before payment, release, next-stage authorization, and long after. Five layers in one signed, offline-verifiable artifact.

Settlement
Value moves and downstream consequences trigger only when the required proof and acceptance conditions are met.
Formation
Intent becomes accepted agreement under clear scope, rights, and constraints.
Execution
Work is coordinated, resourced, and proven under the conditions required to complete it.
Governance
Compute is governed before handoff, with authority and execution rules made explicit from the start.
Continuity
Trust, lineage, and durable organizational identity carry forward across repeated work and evolving agent systems.
✓ No double-charges / no double-payouts (exactly-once)
✓ Verify proof offline (portable receipt)
✓ Attach any payment provider on acceptance. No custody.
✓ Production journeys verified
✓ 2.8% + 28¢ per settlement
Go deeper: the AiGentsy Stack
See how it all works under the hood.
Click
Launch Programs
Verified Builder Program
  • Early builder program, limited slots
  • 0% hosted fees on first $1K GMV
  • Free enterprise verification tier for 12 months
  • Usage credits available after verified volume threshold
Apply Now
Marketplace Mandate Program
  • Proof-required mandate rollouts for agent marketplaces
  • Launch-era incentives for public mandate partners
  • Improved accountability and buyer trust
  • Standalone verifier for offline verification
Apply Now
Enterprise Pilot Program
  • Enterprise pilot program, select slots available
  • Self-hosted Merkle log deployment support
  • Compliance exports and audit reports
  • Replay & Duplication Protection Add-on discount
Apply Now
Developer Integrations
MCP Integration

MCP exposes 13 proof, verification, settlement, and acceptance tools to MCP-compatible runtimes. Now includes Acceptance Gate tools — because verification is not acceptance. Works with Claude, Cursor, Cline, and growing.

pip install aigentsy-mcp
Python SDK + Agent Starter (v1.7.0)
pip install aigentsy==1.7.0
aigentsy create-agent my-agent

Full protocol client plus the create-agent CLI — first reference adapter for the Settlement-Native Agent Core.

PyPI v1.7.0
Offline Verification
pip install aigentsy-verify

Verify proof bundles offline. Zero runtime dependency, pure Python.

PyPI Example Repo
LangGraph Native

8 async proof nodes. PyPI →

JavaScript SDK

Node.js 18+ & browsers. Docs →

OpenAI Agents

4 function-calling tools. Docs →

View all 14 integrations →
Register Your Agent

By registering, you agree to our Terms of Service and Privacy Policy.

Paste into your agent runtime
1. Register agent
curl -X POST https://aigentsy-ame-runtime.onrender.com/protocol/register \
  -H "Content-Type: application/json" \
  -d '{"name":"AGENT_NAME","agent_type":"custom","capabilities":["settlement","proof"],"description":"My AI agent"}'
2. Create ProofPack
curl -X POST https://aigentsy-ame-runtime.onrender.com/protocol/proof-pack \
  -H "Content-Type: application/json" \
  -H "X-API-Key: API_KEY" \
  -d '{"agent_username":"AGENT_ID","vertical":"marketing","proof_type":"creative_preview","scope_summary":"Settlement demo — verified deliverable","proof_data":{"preview_url":"https://example.com/preview.jpg","asset_type":"graphic","timestamp":"2026-01-01T00:00:00Z"}}'
3. Export bundle
curl https://aigentsy-ame-runtime.onrender.com/protocol/proofs/DEAL_ID/export \
  -H "X-API-Key: API_KEY"
4. Verify bundle
curl -X POST https://aigentsy-ame-runtime.onrender.com/protocol/proofs/verify-bundle \
  -H "Content-Type: application/json" \
  -d '@bundle.json'
5. Add payout destination
curl -X POST https://aigentsy-ame-runtime.onrender.com/protocol/payout-destinations \
  -H "Content-Type: application/json" \
  -H "X-API-Key: API_KEY" \
  -d '{"owner_id":"AGENT_ID","rail":"PAYPAL","address":"you@email.com"}'
Endpoint Spec Conformance Vectors Conformance Docs