# 44872

- **Event:** [The Harness Engineering & Model Wrangling Hackathon](https://cerebralvalley.ai/e/mongodb-nyc-hackathon)
- **When:** Sat, Sep 26 at 9:00 AM – 10:00 PM (EDT)
- **Where:** New York, NY
- **Team:** [Kaveesh Khattar](https://cerebralvalley.ai/u/kaveeshkhattar), [Ashwin Rudraraju](https://cerebralvalley.ai/u/WynAsh), [Nishanth Patri](https://cerebralvalley.ai/u/n-patri), [Rahul Radhakrishna](https://cerebralvalley.ai/u/Rahulkris)
- **GitHub:** https://github.com/WynAsh/Mongo-Hackathon/tree/feat/demo-branch
- **Demo video:** https://streamable.com/wkz1vb
- **Gallery:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/55

Harness Architect: an autonomous infrastructure engineer for GPU inference

Owning GPUs shouldn't require becoming an inference expert. Describe your hardware and workload, and Harness plans an open-source serving stack, then keeps improving it as traffic changes, proving every change first.

Plan: sizes the model to your GPUs, picks from six open-source projects (KServe, llm-d, vLLM, SGLang, Dynamo, Envoy AI Gateway), and outputs schema-validated YAML plus an install.sh.
Diagnose: turns incident metrics into one config fix, then confirms it worked.
Evolve: a long-running campaign tests each change against the current setup on identical replayed traffic; deterministic gates, not the model, pick the winner. In a long-prompt surge, p95 was 20.9s, doubling the GPUs gave 9.7s, and the agent's fix gave 2.2s.

MongoDB Atlas: change streams hot-reload each promoted architecture, time-series collections record every request, and Vector Search recalls what worked before. Checkpoints and a lease make runs crash-safe, and context manifests make every decision auditable.

Stack: Python, FastAPI, MongoDB Atlas, Strands Agents, OpenRouter, Kubernetes, KServe, llm-d, NVIDIA Dynamo, vLLM, SGLang, Envoy AI Gateway.

## More from The Harness Engineering & Model Wrangling Hackathon

- [AI Lobang](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/52)
- [MF Goalkeeper](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/53)
- [Alter](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/54)
- [Grue Lab](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/56)
- [OneShot(Aegis)](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/57)
- [CyclopsDiary](https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/58)

---

Markdown version of https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/55. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt