Questions teams ask before the first call.

No. BondFoundry is designed to sit alongside whatever OMS or book-of-record a desk already runs. It is the AI agent layer with governance built in — not the OMS itself.

MIT. The full source is on GitHub. You can fork it, self-host it, and modify it for your domain (loans, derivatives, etc.) without any commercial license.

AIGF v2.0 is the FINOS-published taxonomy of 23 AI risks and 23 mitigations for agentic AI in financial services. BondFoundry is the working reference implementation: every risk has a mapped mitigation in code, every mitigation has at least one passing eval case, every audit row carries a framework_ref.

Claude is the reference model and what we use in the demo. The model boundary is a tool-call interface, so swapping in another frontier model is a configuration change — not a re-architecture.

Start with `make demo` from the GitHub repo for a sixty-second Docker compose run, or book a twenty-minute walkthrough on /book to see the policy gate, HITL queue, and audit chain end-to-end.

The agent generates an HMAC-signed approval envelope scoped to the exact ISIN, notional, and side. A trader (or for T3 irreversible actions, two distinct approvers with manager role) approves the envelope via Slack, Teams, or the operator workspace. The envelope expires 90 seconds after issuance.

No. BondFoundry tracks a session-aggregate materiality ledger, so cumulative notional within a session triggers HITL even if no individual slice does. The split-trade bypass is closed at the gate.

CSV, US Treasury, and ECB are shipped today. Bloomberg BVAL and Refinitiv RDP adapters are in flight. Adding a new provider is a single file under packages/bondfoundry_engine — there is a documented adding-a-curve-provider guide in the repo.

Scaffolded but not parity-tested. Vanilla bonds are parity-tested against QuantLib. For non-vanilla instruments you bring reference pricings and we extend the harness — we are deliberate about not over-claiming on this.

Because you can fuzz it, reason about invariants from the signature, embed it into multiple callers without drift, and replay any historical decision from the audit row context payload. "Show me the decision logic on June 1" is answered with `git show`, not a runtime config archive.

Postgres BEFORE UPDATE/DELETE triggers reject mutations at the database layer. To remove a row you would have to drop and recreate the trigger — which itself writes to a meta-audit log and is monitored.

Yes. The agent loop communicates with the model via MCP and tool calls. Replacing the provider is a config change. We default to Claude because the policy + audit story is easier to demonstrate with a frontier model, but the boundary is provider-agnostic.

Fork the repo. The control plane (policy gate, audit, HITL, eval) is isolated from the bonds domain. Swap packages/bondfoundry_engine for your domain, keep the control plane, inherit AIGF alignment.

Accuracy (pricing and risk against QuantLib reference); policy (adversarial prompts that try to bypass tier routing or HITL); robustness (prompt injection, jailbreak, manifest tampering); latency (per-tier SLO commitments). Coverage is computed per dimension per AIGF risk.

LangChain and AutoGen optimize for orchestration flexibility. BondFoundry optimizes for governance auditability — pure-function gate, hash-chained audit, framework-ref mapping. There is a comparison post on the blog and a vs-langchain-and-autogen doc in the repo.

Yes — that is the design point. packages/bondfoundry_policy is publishable on its own. Embed it in any agent loop, regardless of the rest of the BondFoundry stack.

23 of 23 risks have mapped mitigations in code; each mitigation has at least one passing eval case. CI fails any PR that drops coverage below 85% or leaves any risk with zero passing cases.

air-accelerator is the slot for a runnable AIGF reference implementation. BondFoundry is filling that slot for fixed-income; the same control plane forks to other domains.

NIST AI RMF, NIST 800-53r5, EU AI Act, ISO 42001, SR 11-7, FFIEC, OWASP LLM Top-10 2025, and MAS. Each AIGF mitigation in BondFoundry carries the corresponding refs.

Run `bondfoundry-finos evidence-pack --period 30d`. The output is a directory of: AIGF coverage matrix, per-risk passing eval cases, audit-chain verification report, materiality ledger summary, and a list of every framework_ref written in the window with row counts.