
MedTrace AI supports doctors, nurses, and general practitioners where specialists and clean electronic records are scarce. It accepts the messy reality of care—handwritten prescriptions, scanned labs, vitals, notes, transcripts, and images—and extracts medical facts with links back to sources. Those facts feed a temporal patient knowledge graph, so clinicians can ask questions like “what changed before this symptom?” instead of piecing the story from memory alone. When a clinician runs the Cause Explorer, the system retrieves patient-grounded context first, then uses a fine-tuned open medical model (with efficient tuning such as LoRA/QLoRA) to output possible causes to investigate, supporting evidence, missing information, red flags, and next questions—always framed for review, never as a definitive diagnosis or treatment plan. The hackathon MVP demonstrates dashboard, uploads, extraction review, timeline, graph view, Cause Explorer, safety messaging, and an AMD-focused benchmark (latency, VRAM, structured output). Open models and AMD optimization matter because they move capable, auditable clinical support closer to rural clinics and district hospitals—where one missed detail can change a life.
10 May 2026

Agents Market is a demo marketplace for autonomous agents and their tools on Circle Arc (testnet). Sellers onboard listings with per-tool USDC pricing; the app supports discovery, catalog views, and payment-gated invocation of seller-configured HTTP providers. The stack implements two payment rails so different buyers can participate without one-size-fits-all custody. External buyers integrate Circle Gateway Nanopayments over standard HTTP 402 flows (e.g. via circlekit on arcTestnet), which fits agent-to-agent and pay-per-call use cases. Registered marketplace buyers use USDC on ARC-TESTNET through Circle developer-controlled wallets, including automatic wallet provisioning when no address is supplied, on-chain USDC transfers for settlement, and optional ERC-8004-style lifecycle hooks for agent registration and reputation on Arc. The FastAPI backend combines marketplace CRUD, SQL persistence for usage and payment events, provider proxying with safety checks on outbound hosts, and APIs that expose a clear description of which rail was used. The React frontend supports browsing agents, registering listings, editing tool prices, and reviewing activity with Arcscan links so judges and developers can verify flows on chain. Together, the project shows how USDC-first infrastructure, nanopayments, and hosted wallets can support a scalable pattern for monetized agent commerce.
26 Apr 2026