Integrate AgentGuard into your stack. Read agentguard.run/llms.txt and follow the quickstart.
Every agent action is Ed25519-signed at execution time. No database admin, infrastructure operator, or post-hoc modification can forge or alter a signed receipt. Centaur stores Postgres rows. AgentGuard signs them.
Works with Centaur, LangChain, Claude Code, Amp, Stripe Agents, or any custom stack. AgentGuard operates at the SDK layer, below orchestration. One npm install. No platform lock-in.
Per-agent financial limits enforced at the SDK level, not the application layer. Each cap check produces a signed, verifiable receipt. Auditable by regulators, investors, and compliance teams.
Multi-agent workflows produce a cryptographically linked attestation graph. Every hop is independently verifiable. No central authority required. Holds up to external audit without trusting the database.
The circuit-breaker and control-bus layer for agent pipelines. Drop-in npm package. Intercepts actions, applies policy, emits signed receipts. Works with any harness or model provider.
npm install agentguard-cb →Signed, tamper-evident audit trail for any agent stack. Ed25519 receipts chain across turns and agents. Cannot be altered post-execution, even by the infrastructure operator. In production.
Integration guide →Per-agent spend caps enforced at the SDK layer with signed receipts at each enforcement point. Verifiable limits, not application-layer trust. Shipped v0.1.0 with Ed25519 chain and tamper-detection verifier.
View on GitHub →
The cryptographic primitive below orchestration, above the model.
Orchestration handles control flow. AgentGuard proves what happened.