SpendOS for agent teams.
Control plane for agent operations: governed wallet spend + AI spend governance across IDE, CLI, and agent workflows. Every spend is policy-checked, privacy-preserving, efficiency-aware, and audit-ready.
Live: Frontend · API · PromptOS Terminal
- Canton DevNet — sealed-bid RFP auctions with structural sub-transaction privacy and atomic multi-party reveal.
- SigNoz — OpenTelemetry-native observability for the full agent governance decision tree.
- Agentic commerce — governed wallets, policy-checked spend, FHE-encrypted evaluation, durable audit trail.
pnpm install
pnpm build
pnpm startMinimum .env:
API_KEY=your-api-key-here
OWS_VAULT_SECRET=your-vault-secret
CHAINGPT_API_KEY=your-chain-gpt-key # Optional: Web3 LLM + auditFor local setup, API reference, and production deployment, see the Developer Guide.
| Doc | What's in it |
|---|---|
| Architecture | System design, data flows, Fhenix / Canton / ChainGPT / Ledger integrations |
| Canton | Daml sealed-bid model, hydration, sandbox + DevNet runbooks |
| Canton DevNet materials | Endpoints, auth, allocated parties, Daml user id |
| Canton final submission runbook | Cutover / config that is already done for DevNet |
| Canton hackathon submission | Track 1: Canton private RFP — enterprise framing, DevNet proof pack |
| SigNoz submission | OpenTelemetry instrumentation of the full agent governance decision tree |
| KeeperHub — Agents Onchain submission | Sapience-driven rebalance loop through KeeperHub Direct Execution + MCP for editor agents, with a local round-trip test rig |
| SigNoz dashboard definitions | 3 dashboards: governance overview, LLM provider health, HTTP SLO + audit |
| Agent governance integration spec | Wire the sealed-bid auction to the agent-governance layer |
| Prompt-injection controls plan | Source-aware authorization, spend enforcement, and adversarial test plan |
| Agentic commerce demo runbook | End-to-end demo path for the agentic-commerce track |
| Agentic commerce demo script | Narration + timing for the agent-governance demo |
| Canton demo script | Narration + timing for the Canton sealed-bid demo |
| Pitch deck source | Source for the open-house / pitch deck |
| Product & GTM canvas | Product Canvas + GTM Canvas — wedge, why-now, why-onchain, distribution loops |
| Product UX vision | Experience principles, route blueprint, and UX delivery plan |
| UX validation checklist | Task-based acceptance checks for the core product workflows |
| UX implementation plan | Phased work plan for Audit, shared states, Settings, Runs, analytics, and validation |
| Developer guide | Local setup, API reference, testing, production readiness |
| Deployment | Hetzner / PM2 / nginx, env vars, health checks |
| Tester guide | 5-minute hands-on walk-through of the live product |
| Prava hackathon | Agents of Commerce — Cognivern as governance layer + Prava as payment execution |
| Agent guidance for AI / humans | How to verify Canton runtime state without re-diagnosing it |
| Iteration log | Write-verify-fix history of the build |
MIT