FAQ
What is AGLedger™?
The accountability layer for agent-to-agent and agent-to-system transactions. AGLedger is a self-hosted, signed, append-only ledger for the commitment-delivery-approval lifecycle of automated work — a notary service for the things agents and backend systems do to and for each other. Every unit of work moves through commitment, delivery, decision, and closure. Each phase is cryptographically signed and hash-chained, verifiable offline by anyone with the public keys.
How is this different from logging or observability?
Logging records what happened after the fact, spread across whatever systems the agent touched. AGLedger records accountability as it happens — structured, agent-queryable, with mandate IDs as join keys. It sits underneath your logging and SIEM tools, not as a replacement for them. When your auditor asks “who committed to this, who delivered it, who approved it?” the chain already exists.
How does AGLedger relate to Microsoft Agent Governance Toolkit, Kong, or Galileo?
They solve different problems. Policy controls (Microsoft Agent Governance Toolkit, Kong AI Gateway, Galileo, WSO2) decide whether an agent can act. Agent guardrails (Composio, Snyk) shape how it acts. AGLedger records what was committed, what was delivered, and how each decision was made — signed, ordered, verifiable offline. We plug into gateways and guardrails, not compete with them. A gateway says yes or no; AGLedger records what happened after the gateway said yes. We’ve tested interop with Microsoft’s toolkit specifically.
Does AGLedger judge the quality of work?
No. AGLedger records what was agreed (mandate), what was delivered (receipt), and whether it was accepted (verdict). The principal — human or system — renders the verdict. AGLedger enforces structure, not content.
What is an Audit Agent?
A customer-built agent that queries AGLedger to answer audit questions. Your existing logs scatter the accountability story across six systems and take days to reconstruct. AGLedger records the story in structured, agent-queryable form from the moment work starts. Point your Audit Agent at it and ask: who committed to this delivery? Who approved this payment? Was this purchase within policy? Answers come back in seconds with signed proof attached.
What is a Settlement Signal?
When a mandate involves payment, AGLedger produces a Settlement Signal (SETTLE or HOLD) that routes to your payment platforms via webhook. AGLedger doesn’t move money — it produces the signal your financial systems act on. As agent-to-agent payment rails come online, this signal becomes the accountability layer those systems need.
Can I just build this myself?
You can build a signed, hash-chained ledger in a sprint. A competent engineer with AI tooling could ship one in a week or two. What you can’t build in a sprint is counterparty adoption. Federation only works if both sides speak the same protocol. $8K perpetual is roughly one engineer-week — the price is positioned below the build threshold for a reason. You’re paying for the network of counterparties already speaking AOAP, not the code itself.
What LLM providers are supported?
AGLedger is LLM-agnostic, but the critical accountability path doesn’t depend on model quality. Our testbed runs agents from Anthropic, OpenAI, Google, and Amazon across every integration pattern. Some providers fabricate mandate IDs or invent contract types when asked to self-document; when the enterprise system owns the mandate and receipt, accountability works across every provider tested.
How do agents integrate with AGLedger?
The primary path is the native REST API — fastest and most token-efficient. SDKs are available for TypeScript (@agledger/sdk) and Python (agledger). A CLI ships via npm. MCP is supported for agents that need it. No rewrites required — your existing agents add AGLedger calls alongside what they already do.
Does AGLedger work with LangChain, CrewAI, or AutoGen?
Yes. AGLedger is the accountability layer underneath orchestration frameworks, not a replacement. Your framework handles orchestration. AGLedger handles the accountability record. They’re complementary.
How long does integration take?
Single agent with the SDK: hours. Fleet instrumentation: weeks, not months. If your agent can talk HTTP, it’s ready to participate.
Do my agents need code changes?
For direct integration, yes — your agents (or your enterprise systems) create mandates and submit receipts via API. When the enterprise system owns the mandate and receipt, the agent itself often needs no AGLedger code at all — your ERP, CRM, or workflow tool is the integration point.
What happens if AGLedger is unavailable?
Agents are not blocked. AGLedger is a record-keeping layer, not an execution gate. If AGLedger is down, agents continue operating. PostgreSQL is the single dependency — standard HA (streaming replication, Aurora/RDS) applies. Append-only audit chain means no data loss on restart.
Where does my data live?
In your infrastructure. AGLedger is self-hosted — your accountability records live in your PostgreSQL 17+ database, in the region you choose. We never see your data. Export your full audit trail anytime in JSON, CSV, or NDJSON.
Can AGLedger run air-gapped?
Yes. AGLedger supports fully disconnected operation with no phone-home licensing. Licenses are validated using Ed25519 signatures and never require outbound connectivity.
What are the cryptographic guarantees?
Established standards at every layer: SHA-256 hash chain + Ed25519 signatures for the audit vault, HMAC-SHA256 for webhooks and API auth, RFC 9421 HTTP Message Signatures + Ed25519 for federation, X25519 ECDH + AES-256-GCM for encrypted criteria transfer, and RFC 8785 (JCS) for canonical form. Your keys — AGLedger never generates or holds private key material.
What’s the storage profile at scale?
Mandates, receipts, and audit entries are stored in PostgreSQL. Storage scales linearly with the number of mandates. The append-only audit chain adds overhead per entry but is designed for standard PostgreSQL operational patterns — vacuuming, partitioning, and archival all work as expected.
How does AGLedger help with EU AI Act compliance?
AGLedger maps to 11 articles of the EU AI Act (Articles 9, 12, 13, 14, 15, 17, 18, 20, 26, 27, and 49). The mapping separates what AGLedger provides (infrastructure and records) from what the enterprise still owns (judgment, policies, decisions). This mapping is tested — the AGLedger testbed runs a full EU AI Act compliance scenario end-to-end.
Does AGLedger help with NIST AI RMF?
Yes. AGLedger maps to all four functions of the NIST AI Risk Management Framework: GOVERN (accountability structures, role identity), MAP (risk categorization per contract type), MEASURE (audit vault queries, tolerance-band enforcement, timeliness evidence), and MANAGE (dispute resolution, remediation, audit export).
Can I export audit trails for compliance?
Yes. Full chain export is available at any time in JSON, CSV, or NDJSON. OCSF v1.4.0 export maps to standard security event formats. Audit exports are formatted for regulatory submission and third-party audit.
How do I track agent reliability over time?
Built-in reputation scoring tracks agent performance across mandates using the verdict chain — whether deliveries were accepted, rejected, or required revision, aggregated per agent and per contract type. Drift detection surfaces when a model’s acceptance rate shifts between versions. Reputation becomes most valuable in federated deployments where you’re comparing agents across counterparties or providers; in a single-instance deployment the signal is narrower.
What is federation?
Federation allows multiple AGLedger instances to coordinate across organizational boundaries. Each party keeps their own vault, their own keys, their own data. You define custom schemas for your domain and share them with federated partners so both sides speak the same structured language. The protocol crosses boundaries — the data doesn’t.
What happens when both sides disagree?
The protocol supports 3-tier dispute resolution. Tier 1: self-resolution between principal and performer (revision requests, remediation). Tier 2: third-party mediation with an accessor granted access to the mandate chain. Tier 3: human-in-the-loop escalation with the complete cryptographic record of what was agreed, delivered, and where it diverged.
What happens if AGLedger LLC dissolves?
Your software keeps running. You hold a perpetual license, your data lives in your PostgreSQL database, and AGLedger makes zero outbound connections in Standalone mode — there is no kill switch, no phone-home, no dependency on us being in business. Licenses are validated locally with Ed25519 signatures. Security fixes are always free while we operate, and your audit vault remains cryptographically verifiable with standard tooling regardless of whether AGLedger LLC exists. Enterprise licensees have source access for exactly this reason.
Is AGLedger open source?
No. AGLedger is proprietary software. The SDKs are source-visible (published on npm and PyPI). Enterprise licensees get source access for security and compliance review. The AOAP™ specification is available to licensees; public publication under an open license is under evaluation.