# The Harness Engineering & Model Wrangling Hackathon: Project Gallery

- **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
- **Hosts:** [MongoDB](https://cerebralvalley.ai/u/mongodb)
- **Projects:** 98 (6 placed)
- **Page:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery

## Projects

### 1. Shibboleth

Shibboleth is a harness trust layer for open-weight AI models. Anyone can download a model, quietly strip out its safety ("abliterate" it), and re-upload it…

- **Team:** [Alex Wu](https://cerebralvalley.ai/u/amadeusWoo), [Alan Wu](https://cerebralvalley.ai/u/thewoozie67), [Adam Martinez](https://cerebralvalley.ai/u/TheAdamAgenda)
- **GitHub:** https://github.com/TheApexWu/shibboleth
- **Demo video:** https://youtu.be/afkR0qdtnGk
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/1

### 2. Vision

Problem statement: Two, Long Horizon Engineering. Also covers One: the agent evolves its own rules.

Bookie is a long-horizon agent system that makes money on…

- **Team:** [Nideesh Terapalli](https://cerebralvalley.ai/u/nideesh)
- **GitHub:** https://github.com/Nideesh1/BOOKIE
- **Demo video:** https://www.youtube.com/watch?v=Od3QQGrNuhI
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/2

### 3. APA

Adaptive Pentesting Agent, is an autonomous AI agent designed to resolve the token overload and context bloat found in existing open-source penetration tools…

- **Team:** [Yusri Ilza Sania](https://cerebralvalley.ai/u/ilzasania), [Muhammad Farhan Fadhilah](https://cerebralvalley.ai/u/farhanfadhilah25), [Ferdi Fadillah](https://cerebralvalley.ai/u/Ferdi)
- **GitHub:** https://github.com/MFarhanFadhilah/adaptive_penetration_agent
- **Demo video:** https://youtu.be/4PJJSilWMZ0
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/3

### 4. SubmissionAI

SubmissionAI is a long-horizon review harness for evolving drug-development document packages. It stores immutable package versions, evidence passages…

- **Team:** [Zhenbang Wang](https://cerebralvalley.ai/u/bruce1edward)
- **GitHub:** https://github.com/bruce1edward/Submission-AI
- **Demo video:** https://youtu.be/gxv4KN75xx8
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/4

### 5. Self-Evolving Chip-Design Harness

**Self-Evolving Chip-Design Harness**: an AI harness that fixes its own agents, proven where results can't be faked.

Getting a chip to hit its clock speed is…

- **Team:** [Chris Martin](https://cerebralvalley.ai/u/cmart365)
- **GitHub:** https://github.com/chmartin/chip-harness/
- **Demo video:** https://drive.google.com/file/d/1YAXZVXYoeIuzy_1zMvc_bQsqnz4nK6FO/view?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/5

### 6. Hindsight

Results snapshot (read-only): https://hindsight-xi-two.vercel.app

Hindsight turns real coding-agent history into a long-horizon memory benchmark on MongoDB…

- **Team:** [Conner Babinchak](https://cerebralvalley.ai/u/connerbabs)
- **GitHub:** https://github.com/babinchak/mongo-hackathon
- **Demo video:** https://youtu.be/wjG0bj--t-Y
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/6

### 7. Agent Evolve

Chatbots are set up once by hand and improving them takes weeks of reading transcripts. Our MongoDB Atlas support assistant improves itself. Jev makes the…

- **Team:** [Kartik Mehra](https://cerebralvalley.ai/u/Mkartik007), [Aman Kothari](https://cerebralvalley.ai/u/AmanKothari)
- **GitHub:** https://github.com/Aman-Kothari7/agent-evolve
- **Demo video:** https://drive.google.com/drive/folders/16NOrRu-EsXOeGJDdcbrRTmjP0izsAcUH?usp=drive_link
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/7

### 8. SwipeHome

Track: Recursive Harnessing. SwipeHome is a self-improving real-estate recommendation harness built on MongoDB Atlas. Before showing a home, it predicts…

- **Team:** [Soulemane Sow](https://cerebralvalley.ai/u/sowcantcode)
- **GitHub:** https://github.com/Soulemane12/swipehome
- **Demo video:** https://youtu.be/xTfLwmAfF9k
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/8

### 9. Grudge

1. The problem

Data center permitting in the US takes one to three years, and much of that time is rework. A site plan goes to the county, comes back with…

- **Team:** [Shikha Soneji](https://cerebralvalley.ai/u/shikhasoneji), [Sameer Neve](https://cerebralvalley.ai/u/sam280691)
- **GitHub:** https://github.com/shikhasoneji8/infra_design_permits
- **Demo video:** https://youtu.be/gp7qtiw8Nts
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/9

### 10. Byte Club

Simulacra is a real-time, multiplayer economic-policy simulator: a living pixel-art city where people and AI play out what a policy actually does to…

- **Team:** [Vansh Mehta](https://cerebralvalley.ai/u/vanshm2703), [Ahana Shaikh](https://cerebralvalley.ai/u/Ahana), [Aayush Savla](https://cerebralvalley.ai/u/Aayush_Savla)
- **GitHub:** https://github.com/vanshm2703/Simulacra
- **Demo video:** https://youtu.be/kTetnoTOPIo
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/10

### 11. Da Vinci: Recursive Improvement CAD Harness

Da Vinci is a recursive improvement CAD harness designed to support physical engineering tasks through specialized AI agents, programmatic CAD and automated…

- **Placement:** Finalist
- **Team:** [Cobe Liu](https://cerebralvalley.ai/u/Cobe)
- **GitHub:** https://github.com/Cobeml/Da-Vinci
- **Demo video:** https://youtu.be/QjKv8p9AJu4
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/11

### 12. Jev classifier + Citation Harness

Jev-gating memory is self-improving memory for Strands agents, backed by MongoDB Atlas. A type-safe classifier called Jev decides what is worth remembering…

- **Team:** [John McAuliffe](https://cerebralvalley.ai/u/jrmcauliffe00)
- **GitHub:** https://github.com/jrmcauliffe00/mongo-hackathon
- **Demo video:** https://youtu.be/BZcHLq_mEyc
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/12

### 13. The Archive

Chronicle is self-healing project memory. It finds conflicts in team updates. People can correct its decisions. Chronicle saves these corrections as scoped…

- **Team:** [Elmir Abdullaiev](https://cerebralvalley.ai/u/elmircan), [Maxime Hendryx-Parker](https://cerebralvalley.ai/u/MaximeHP), [Danny Nguyen](https://cerebralvalley.ai/u/kickdapie), [Sahil Dhumale](https://cerebralvalley.ai/u/sahildhumale)
- **GitHub:** https://github.com/maximehp/mongodb-hackathon
- **Demo video:** https://youtu.be/d1Ap3y7OTuQ
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/13

### 14. AI Stylist and Smart Wardrobe

An AI stylist that figures out how fashion items work together — across users’ closets and retail products. It saves users time deciding what to wear and how…

- **Team:** [Sia Fu](https://cerebralvalley.ai/u/Siafu)
- **GitHub:** https://github.com/sheenafu1219-oss/Chic-Puzzle-Front-end
- **Demo video:** https://youtube.com/shorts/-3Yda-8cHxA?feature=share
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/14

### 15. Converge

Converge is collaborative coding workspace through a custom Mac app, web app, and Codex plugin that lets teams guide a shared coding agent. It tracks each…

- **Team:** [Divyesh Thirukonda](https://cerebralvalley.ai/u/divyeshthiru), [Pranav Palle](https://cerebralvalley.ai/u/the_pranav), [Tasos Gerasis](https://cerebralvalley.ai/u/tasosger)
- **GitHub:** https://github.com/Divyesh-Thirukonda/mongo
- **Demo video:** https://youtu.be/KqYgBWlQqK8
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/15

### 16. Levy

LEVY — The Tariff Intelligence Desk
Tariff wars move in hours. LEVY forecasts them like a trading desk with receipts.
Every probability has a belief timeline…

- **Team:** [Forrest Pan](https://cerebralvalley.ai/u/fpreactrn), [frank yu](https://cerebralvalley.ai/u/frankyu), [Sahil Pardasani](https://cerebralvalley.ai/u/sahilpardasani), [Kathy Luo](https://cerebralvalley.ai/u/kluo68)
- **GitHub:** https://github.com/Mkultra00/levy
- **Demo video:** https://youtu.be/bkZpBRPpg24
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/16

### 17. CtrlAltElite

Attune is an AI-powered experimentation lab for improving website flows. A business owner sets an optimization goal and captures a user journey; agents plan…

- **Team:** [Patricia Y](https://cerebralvalley.ai/u/pumpkinpatch), [Sparsh Paliwal](https://cerebralvalley.ai/u/discoman123), [Yibo He](https://cerebralvalley.ai/u/Yibo)
- **GitHub:** https://github.com/Vercellent/attune
- **Demo video:** https://youtu.be/dA6VhZIuREo
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/17

### 18. Reflexes

Reflexes: agents that grow reflexes.

The problem: AI agents send every small decision (classify, prioritize, route, check policy) to a slow, expensive LLM…

- **Team:** [Amey Borkar](https://cerebralvalley.ai/u/ameyborkar771), [Meet Bhanushali](https://cerebralvalley.ai/u/MeetBhanushali)
- **GitHub:** https://github.com/Amey771/reflexes
- **Demo video:** https://drive.google.com/file/d/1jdCyouNxa7JHIP45sKMwOq8E8JSqFSij/view?usp=drive_link
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/18

### 19. MongoHive

MongoHive turns what one agent learns into tested tools every teammate's agent can call by name. When your Claude or Codex agent finishes an investigation, a…

- **Team:** [Ani Potts](https://cerebralvalley.ai/u/anipotts), [Kapil Rajpopat](https://cerebralvalley.ai/u/kap-il)
- **GitHub:** https://github.com/anipotts/mongo-hive
- **Demo video:** https://youtu.be/Wrv3Wx8YVvs
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/19

### 20. Ada

Ada is a 3D quadruped in MuJoCo whose walking gait is written by a cheap model, gpt-6-luna. A supervisor model rewrites the harness around it (its rules…

- **Team:** [Saran Teja Mallela](https://cerebralvalley.ai/u/nerdboss-stm)
- **GitHub:** https://github.com/Nerdboss-stm/Ada
- **Demo video:** https://youtu.be/0TKeUeUC--0
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/20

### 21. PolicyPilot

A self-evolving health-insurance operations copilot that learns how each reviewer makes mistakes, adapts its tools, context, and coaching to that person, and…

- **Team:** [Humna Sultan](https://cerebralvalley.ai/u/humnasul), [Hongzip Kim](https://cerebralvalley.ai/u/hongzip), [Leonardo Cambisaca](https://cerebralvalley.ai/u/lcam), [Allen Lu](https://cerebralvalley.ai/u/allen-lu-1)
- **GitHub:** https://github.com/1allenlu/policy-pilot
- **Demo video:** https://youtu.be/cTSSB2UohJY
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/21

### 22. Moss

Moss: long-running AI teammates whose runs and memory live in one MongoDB Atlas cluster, and that forget on evidence.

You message a coordinator (HQ). It…

- **Team:** [Shaishav Pidadi](https://cerebralvalley.ai/u/shaivpidadi), [Khushi Parmar](https://cerebralvalley.ai/u/Khushiparmar), [Vishnu Daka](https://cerebralvalley.ai/u/dakavishnu), [Gayatri Biram](https://cerebralvalley.ai/u/Gayatrib)
- **GitHub:** https://github.com/khushi491/moss
- **Demo video:** https://www.veed.io/view/fb3b666d-35ef-4ddd-a0bb-cebf8381a318?source=Dashboard&panel=share
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/22

### 23. Second_Loop_Engineering

In agent-run analytics and engineering workflows, outputs must cite their evidence; when they fail, teams tune prompts and checks by hand without a fixed…

- **Team:** [Chris Gibbs](https://cerebralvalley.ai/u/TallGibbs)
- **GitHub:** https://github.com/TallGibbs/race-engineer-adaptive-harness
- **Demo video:** https://drive.google.com/file/d/11EwE4t3Dj1k2Y88wV-x_tpCtBH8LacND/view?usp=drive_link
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/23

### 24. devrandom.co

Devrandom is infrastructure for AI agents that improve how they work while remaining accountable and within user-defined permissions.

A user defines a task…

- **Team:** [Joel D'Souza](https://cerebralvalley.ai/u/joeldsouza)
- **GitHub:** https://github.com/devrandom-labs/devrandom
- **Demo video:** https://youtu.be/Fz7lwgAh0dw
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/24

### 25. Antibody

Antibody is an immune system for AI agents. When an attack gets through, it writes a fix, proves the fix blocks the attack without breaking legitimate work…

- **Team:** [Kireeti Josyula](https://cerebralvalley.ai/u/kireetijosyula41), [Avinash Saraf](https://cerebralvalley.ai/u/avsaraf), [Jessica Jin](https://cerebralvalley.ai/u/JessicaJ), [Xiufeng Ma](https://cerebralvalley.ai/u/mongohack)
- **GitHub:** https://github.com/kireetijosyula41/AgentHarnessHack-JNAJ/tree/main
- **Demo video:** https://youtu.be/fiJgOBBGVps
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/25

### 26. Blanko

Blanko is a better N8N that allows you to build share and manage agentic architecture

- **Team:** [Jeremiah Richard](https://cerebralvalley.ai/u/drjay)
- **GitHub:** https://github.com/thetradingdoc/skills
- **Demo video:** https://youtu.be/ARRaShUUGUQ?si=h7A2hcZwqzpqfOJC
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/26

### 27. Recall Gate

Recall Gate is a cost-rationing safety monitor for cyber-capable agents: instead of running an expensive LLM monitor on everything an agent does, it reads the…

- **Team:** [Krish Veera](https://cerebralvalley.ai/u/krishrveera), [Mihir Prajapati](https://cerebralvalley.ai/u/mihir01)
- **GitHub:** https://github.com/krishrveera/recallgate
- **Demo video:** https://youtu.be/C95nyCrDjQs
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/27

### 28. Sudo Squad

Claim Cipher
Insurers use algorithms to deny claims. We built a self-improving agent that learns each insurer's hidden behavior, catches wrongful denials, and…

- **Team:** [Sakshi Deshpande](https://cerebralvalley.ai/u/sak0514), [Anushka Pandit](https://cerebralvalley.ai/u/Anushka_09), [Chinmayee Mayekar](https://cerebralvalley.ai/u/chinmayee41203), [Brahmi Dalvi](https://cerebralvalley.ai/u/dalvibrahmi)
- **GitHub:** https://github.com/brahmi9811/team-claim-cipher
- **Demo video:** https://youtu.be/T0eOvSE2Z0g
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/28

### 29. emirates

long context agent

- **Team:** [FNU Tushar](https://cerebralvalley.ai/u/gpu004)
- **GitHub:** https://github.com/gpu004/mongomongo
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/29

### 30. Second Shift

Second Shift is a long-horizon NeuroAI harness that keeps an agent pursuing one research goal across context resets, crashes, and changing constraints…

- **Team:** [David Shatsky](https://cerebralvalley.ai/u/davidshatsky), [Andrew Shatsky](https://cerebralvalley.ai/u/Ashatsky)
- **GitHub:** https://github.com/uyqv/MongoDB-Hackathon
- **Demo video:** https://youtu.be/fyuLbvF8t50
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/30

### 31. Self-Taught Trainer

Self-Taught Trainer is a self-improving harness for an LLM that plays Pokémon Showdown (Gen 1 OU). The player, GPT-5.4 mini, is never retrained. Instead, a…

- **Team:** [Devin Dawson](https://cerebralvalley.ai/u/unclemusclez), [Ryan Sherman](https://cerebralvalley.ai/u/beginnerbot), [Eric Ko](https://cerebralvalley.ai/u/ERIC_EX), [Daniel Joo](https://cerebralvalley.ai/u/danielsjoo)
- **GitHub:** https://github.com/ERICEX2025/self-taught-trainer
- **Demo video:** https://www.loom.com/share/d8f1ff2b4a594a6485ac96e79f8cb40f
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/31

### 32. Crucible

AI agents that send emails, read files, and browse the web can be hijacked by prompt injection, where an attacker hides instructions in content the agent…

- **Team:** [Varesh Patel](https://cerebralvalley.ai/u/HaadesX), [Aparajita Sarkar](https://cerebralvalley.ai/u/aparaxsarkar), [Urvi Desai](https://cerebralvalley.ai/u/urvi), [Sinchana S Arun](https://cerebralvalley.ai/u/SinchanaArun)
- **GitHub:** https://github.com/Haadesx/Crucible
- **Demo video:** https://youtu.be/4N4AHXedQBg
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/32

### 33. LILI

LILI An adaptive discovery assistant for finding interesting places, local communities, and professional opportunities. Built by Ed Amaya with Python, Flask…

- **Team:** [Edluis Amaya](https://cerebralvalley.ai/u/edluis316)
- **GitHub:** https://github.com/edluis37/mongodb_h/blob/main/README.md
- **Demo video:** https://sentiai.pro/new/video.html
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/33

### 34. Bisect

Bisect is a self-improving agent harness that never debugs the same bug twice. Agents that learn rules from their mistakes also learn bad habits. Bisect runs…

- **Team:** [Ashwin Ugale](https://cerebralvalley.ai/u/Ashwin1121), [Sahil Mehta](https://cerebralvalley.ai/u/sahilmehtx)
- **GitHub:** https://github.com/sahilmehta17/MongoDB_Hackathon_Sept26_Bisect
- **Demo video:** https://drive.google.com/file/d/1j3dvgXLeZlY345zgtnGai6yujmMNDZLJ/view?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/34

### 35. Proxy Harness

Proxy Harness is an evaluation harness for applying an institutional investor's proxy-voting policy to SEC proxy statements with LLMs, built for Pennant (YC…

- **Team:** [Daniel Chen](https://cerebralvalley.ai/u/daniel297)
- **GitHub:** https://github.com/dchen024/pennant-proxy-harness
- **Demo video:** https://youtu.be/4ckXIIlr7Rw
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/35

### 36. Ninja Attack

Red vs Blue: an agent that teaches itself to attack

A self-improving agent harness, shown as a game. On a simulated office network, an AI attacker plays…

- **Team:** [Jaison Jayaraj](https://cerebralvalley.ai/u/Jaisonj), [Hyeseung Kim](https://cerebralvalley.ai/u/serenkim), [Shaun Porwal](https://cerebralvalley.ai/u/shaunporwal), [Mariam Serag](https://cerebralvalley.ai/u/Mariamserag)
- **GitHub:** https://github.com/shaunporwal/mongodb-hackathon
- **Demo video:** https://youtu.be/lheT36BfGmk
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/36

### 37. Kiara

Kiara is a self-improving legal-context harness on MongoDB Atlas. A California signup at DemoCo, a fictional New York startup, triggers a scoped applicability…

- **Team:** [Jordan Weintraub](https://cerebralvalley.ai/u/Jordan914), [Aayush Dani](https://cerebralvalley.ai/u/arxdani), [Eleonora Bjornberg](https://cerebralvalley.ai/u/ebjornberg), [Aishwarya Patil](https://cerebralvalley.ai/u/Aishwarya4114)
- **GitHub:** https://github.com/AayushDani/kiara
- **Demo video:** https://drive.google.com/file/d/1YrhfbgoPEqL7u-hTJXWpp_EdciJKrAYV/view?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/37

### 38. Downshift

Here's a description you can paste straight into the form:

Downshift is a self-improving harness for data questions on MongoDB Atlas. The first time a new…

- **Team:** [Vaibhav Chaudhari](https://cerebralvalley.ai/u/vaibhavchaudhari), [Chetan Kodeboyina](https://cerebralvalley.ai/u/ck3)
- **GitHub:** https://github.com/chaudharivaibhav12/DownShift
- **Demo video:** https://youtu.be/owtzVBWgo04
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/38

### 39. Tony

An assistant gives Tony a target price, a private walk-away limit, required terms and a deadline. From there Tony runs the negotiation. It writes firm…

- **Team:** [Bobby Trickett](https://cerebralvalley.ai/u/BobbyBones)
- **GitHub:** https://github.com/TGambit1/followthrough.git
- **Demo video:** https://youtu.be/vIS96eLE9zk
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/39

### 40. SpaceExplore

A rover 20 light-minutes from Earth can't wait for an engineer when its agent fails, so our harness repairs itself. An Explorer agent (Claude Haiku 4.5)…

- **Team:** [Jithendra Puppala](https://cerebralvalley.ai/u/jithendra), [Kavitha V](https://cerebralvalley.ai/u/vkavith), [Sandeep Puppala](https://cerebralvalley.ai/u/SandeepPuppala), [Shreyas Sreenivas](https://cerebralvalley.ai/u/shreyas324)
- **GitHub:** https://github.com/jithendra1798/SpaceExplore
- **Demo video:** https://youtu.be/o22nbD8ZESo
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/40

### 41. Context Plane

Context Plane — Mission Control for AI Teams

Context Plane connects the AI agents working across a company and gives them shared, durable context. Each user…

- **Team:** [Buddhsen Tripathi](https://cerebralvalley.ai/u/btr1pathi), [Tanish Vardhineni](https://cerebralvalley.ai/u/Tanish00), [Shivraj Singh Bhatti](https://cerebralvalley.ai/u/web), [Simardeep Sethi](https://cerebralvalley.ai/u/Sim2701)
- **GitHub:** https://github.com/Simardeep27/ContextPlane
- **Demo video:** https://youtu.be/BHW4Yx2Kkgg
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/41

### 42. Pensieve Core

A Data layer for agents with memory context options. Reduces complexity for developers when working with vector DBs and topic targeted agents. Leverages…

- **Team:** [meyron levanon](https://cerebralvalley.ai/u/M-Lev), [Eric Lewellen](https://cerebralvalley.ai/u/redlewel)
- **GitHub:** https://github.com/redlewel/pensieve
- **Demo video:** https://drive.google.com/file/d/1eIS3YdKF6Fzy86bdbULhNJnALN5NXpXy/view?usp=drive_link
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/42

### 43. Reflex

A coding-agent harness that detects repeated failed fixes and changes the agent's context using evidence stored in MongoDB Atlas.

- **Team:** [Oleh Savchuk](https://cerebralvalley.ai/u/Oleh_Savchuk)
- **GitHub:** https://github.com/OlegSavchuk/reflex-harness
- **Demo video:** https://youtu.be/WiJxBR_7ckI
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/43

### 44. ChudChuckleNutz

Record agentic traces, store them on MongoDB and replay them to help debug and  improve the harness automatically.

- **Team:** [Hong Cheng Wang](https://cerebralvalley.ai/u/hongchengw), [Gideon F](https://cerebralvalley.ai/u/gfadele), [Lingbo Zhang](https://cerebralvalley.ai/u/Lingboz)
- **GitHub:** https://github.com/gfade/tapedeck_ai
- **Demo video:** https://youtu.be/48c7ml6XCII
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/44

### 45. Offload

Offload learns the work you repeat, so next time you can hand it over. Its engine, REM (Replay · Evolve · Merge), is an agent harness with a day/night cycle…

- **Placement:** 2nd Place
- **Team:** [Tensae L](https://cerebralvalley.ai/u/Tensu), [Floyd Korzan](https://cerebralvalley.ai/u/FloydKorzan), [ryan Cortenbach](https://cerebralvalley.ai/u/Ryancortenbach)
- **GitHub:** https://github.com/SpectrrT/MongoDB_HarnessHack
- **Demo video:** https://drive.google.com/file/d/192MK3g7SNgEeZgrw5fYH0JHOzjGFKshR/view
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/45

### 46. Seal (Self Healing Harness)

Seal (Self Healing Harness) is an AI agent harness built on top of a simple Database Query Resolution Agent that learns from its own limitations. 

When a…

- **Team:** [Divyanshi Parashar](https://cerebralvalley.ai/u/divyanshi), [Ishwant Singh](https://cerebralvalley.ai/u/ishwantsingh)
- **GitHub:** https://github.com/DIVYANSHI-PARASHAR/Seal-self-heal-
- **Demo video:** https://drive.google.com/drive/folders/1lA2_I-qOuQAY7GX-Bto9eb6Oek2h8Zg0?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/46

### 47. HarnessForge - Evolutionary CI/CD for operational AI agents

HarnessForge: Evolutionary CI/CD for operational AI agents

HarnessForge continuously hardens an AI agent by turning its failures into measurable harness…

- **Team:** [Deepesh Katudia](https://cerebralvalley.ai/u/Deepesh-Katudia), [Tejas Pandya](https://cerebralvalley.ai/u/Tejas9598), [milap shah](https://cerebralvalley.ai/u/hsi), [Arpit Shah](https://cerebralvalley.ai/u/arpitshah)
- **GitHub:** https://github.com/Deepesh-Katudia/harnessforge
- **Demo video:** https://youtu.be/jhjyAhmn4s0
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/47

### 48. 3pt (Three Point Harness)

3PT (Three Point Harness) is a self-improving harness for general contractors, built for Problem Statement One, Recursive Harnessing. Supers, PMs and project…

- **Team:** [Patrick Astarita](https://cerebralvalley.ai/u/pastarita), [Yash Kothari](https://cerebralvalley.ai/u/whykothari)
- **GitHub:** https://github.com/pastarita/3pt
- **Demo video:** https://youtu.be/MxAMXWKRcvc
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/48

### 49. Ripple

Ripple designs circuit boards from plain English, grades them against hidden checks, and evolves its own harness from the failures, going from 0/4 to 3/4 on…

- **Placement:** 1st Place
- **Team:** [Jovian Wang](https://cerebralvalley.ai/u/jvo), [Marcos Speroni](https://cerebralvalley.ai/u/MarcosSperoni), [Jack Li](https://cerebralvalley.ai/u/jackli), [Arjun Cheema](https://cerebralvalley.ai/u/acheema5)
- **GitHub:** https://github.com/jovianw/ripple
- **Demo video:** https://www.youtube.com/watch?v=yMx84ME4XYA
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/49

### 50. Relay

Relay is an agent for the weeks after a storm, when volunteers rotate out and the people who were reported once are forgotten. It listens across 311 calls…

- **Team:** [Arul Thileeban](https://cerebralvalley.ai/u/arul_thileeban), [Shivam Arora](https://cerebralvalley.ai/u/shiv-arora), [Tanish Gudise](https://cerebralvalley.ai/u/TanishG)
- **GitHub:** https://github.com/Shiv-aurora/mongodb-hackathon
- **Demo video:** https://youtu.be/B7xnpd-mmWw
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/50

### 51. Interlock: Aditi Kumari, Austin Zhao, Arnav Sacheti, Shun-Hsun Liang.

Two companies, two private playbooks, one signed joint procedure. Neither side reads the other's. Interlock merges them on MongoDB Atlas: Vector Search aligns…

- **Team:** [Austin Zhao](https://cerebralvalley.ai/u/austinzhao), [Shun-Hsun Liang](https://cerebralvalley.ai/u/Hannibal_Liang), [Aditi Kumari](https://cerebralvalley.ai/u/KRIaditi), [Arnav Sacheti](https://cerebralvalley.ai/u/arnavsacheti)
- **GitHub:** https://github.com/asacheti/mongodb-hackathon
- **Demo video:** https://youtu.be/Yi0isi4nyLU
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/51

### 52. AI Lobang

Try now: AiLobang.com
AI Lobang is a voice-first agent you reach with one phone call. Connect your accounts- Gmail, Drive, Telegram, your bank, and it…

- **Team:** [Ojas Surana](https://cerebralvalley.ai/u/ojasx), [Himanshu Sharma](https://cerebralvalley.ai/u/Himanshu492)
- **GitHub:** https://github.com/ojassurana/AILOBANG-hackathon
- **Demo video:** https://hackathon.ojassurana.com
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/52

### 53. MF Goalkeeper

Long-running agents degrade because their context is a pile and they drift because the thing doing the work is also the thing remembering why. goalkeeper…

- **Team:** [Maya Lopez](https://cerebralvalley.ai/u/oceane), [Fabio Keller](https://cerebralvalley.ai/u/FabioKeller)
- **GitHub:** https://github.com/imfabiokeller/goalkeeper
- **Demo video:** https://docs.google.com/videos/d/1awFeoucoAsgLT9B2m1n5LLbDrp_OYCNUXZpqqOkM7Ws/play
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/53

### 54. Alter

A voice first agent with the ability to generate its own capabilities and interface.

- **Team:** [Russell Van Curen](https://cerebralvalley.ai/u/vancuren)
- **GitHub:** https://github.com/vancuren/alter
- **Demo video:** https://youtu.be/vu4HuIlsfQU
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/54

### 55. 44872

Harness Architect: an autonomous infrastructure engineer for GPU inference

Owning GPUs shouldn't require becoming an inference expert. Describe your hardware…

- **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
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/55

### 56. Grue Lab

Zorkinator plays Zork I with a harness that turns every death into a lesson instead of forgetting it. It builds its own map and memory as it plays, and a rule…

- **Team:** [Himali Saini](https://cerebralvalley.ai/u/himali15), [Joshua Huang](https://cerebralvalley.ai/u/jhuang314), [Elliott Kalt](https://cerebralvalley.ai/u/elkalt), [sebastian losada](https://cerebralvalley.ai/u/n-a)
- **GitHub:** https://github.com/JoshBong/zorkinator
- **Demo video:** https://www.loom.com/share/77e2d77299e3472d8f85febbad78484b
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/56

### 57. OneShot(Aegis)

Aegis is an evidence-governed repair harness for broken API integrations. It uses Strands agents, isolated candidate workspaces, MongoDB Atlas durable memory…

- **Team:** [Subhradeep Acharjee](https://cerebralvalley.ai/u/subhradeep), [R S](https://cerebralvalley.ai/u/rsg), [Tanmay Sahu](https://cerebralvalley.ai/u/Tanmay3), [Nobodit Choudhury](https://cerebralvalley.ai/u/dotbion)
- **GitHub:** https://github.com/7dracoder/OneShot
- **Demo video:** https://youtu.be/Xo823jpl774
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/57

### 58. CyclopsDiary

CyclopsDiary gives factory workers wearing Meta AI glasses a shared memory of the floor. Every worker's glasses feed one MongoDB memory that keeps what was…

- **Placement:** Finalist
- **Team:** [Sudharshan Ramesh](https://cerebralvalley.ai/u/SudhanR), [Richard Lin](https://cerebralvalley.ai/u/rlin25)
- **GitHub:** https://github.com/exploring-curiosity/CyclopsDiary
- **Demo video:** https://youtu.be/P9OXVsmuzuA
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/58

### 59. Incident Memory

Incident Memory prevents engineering teams from repeatedly solving the same production problems by storing past incidents, failed approaches, and human…

- **Team:** [Nten Nyiam](https://cerebralvalley.ai/u/n10n)
- **GitHub:** https://github.com/nnyiam10/incident-memory
- **Demo video:** https://drive.google.com/file/d/15KWa-NbM4OEoYWa6pO4jX-5XvGEvgct7/view?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/59

### 60. Precedent - the Harness for Evolving Memory

We built a complete orchestration and memory system for teams of coding agents. At the foundation is our custom Orchestrator Harness. Every campaign begins…

- **Team:** [Jason Peng](https://cerebralvalley.ai/u/jasonpeng2019), [Benjamin Huh](https://cerebralvalley.ai/u/buh0713), [Brianna Wang](https://cerebralvalley.ai/u/brianna-wang), [Connor Zhang](https://cerebralvalley.ai/u/XGHou)
- **GitHub:** https://github.com/brianna-wng/MA-Harness
- **Demo video:** https://drive.google.com/file/d/1TreRQ7mgPwAbzU1J5kkDSdKPG2aV3pt5/view?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/60

### 61. Harness Journey

Journey Harness is a long-horizon AI engineering system designed to keep agents working reliably toward complex software goals across multiple steps…

- **Team:** [Isayah C](https://cerebralvalley.ai/u/isayac)
- **GitHub:** https://github.com/isayahc/Journey-Hanrness
- **Demo video:** https://youtu.be/3Ox5me96Eno
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/61

### 62. Team SG

An agent working for weeks should not forget what it learned yesterday.

Long Horizon Memory gives agents persistent, connected memory so they can recognise…

- **Team:** [Jiacheng Yang](https://cerebralvalley.ai/u/jiacheng-y), [Xinyi Lu](https://cerebralvalley.ai/u/xinyilu00), [Emmanuel Rayendra](https://cerebralvalley.ai/u/theodorayy), [Matthew Lee](https://cerebralvalley.ai/u/matthewlee)
- **GitHub:** https://github.com/theodorayy/team-sg-mongo-harness-eng-hackathon
- **Demo video:** https://drive.google.com/drive/folders/1f8gqhvg6GefcC6zoH9z2La1Z7d-84hMB
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/62

### 63. Sightline

A harness that teaches itself what context to show Jev, TypeSafe's fast decision model, proves the result on a storm it never saw, and can't cheat because…

- **Placement:** Finalist
- **Team:** [Kishore Bhatia](https://cerebralvalley.ai/u/kbee), [Brayden Hughes](https://cerebralvalley.ai/u/braydenhughes)
- **GitHub:** https://github.com/hughesbrayden/sightline/tree/main
- **Demo video:** https://www.loom.com/share/02d8cd6855844d119fcd969e2a7aa2ad
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/63

### 64. Cortex

Cortex is a memory for your computer that remembers what you use, lets unused detail fade, and helps an AI assistant keep up with your life.
It turns…

- **Team:** [Ranveer Singh](https://cerebralvalley.ai/u/rsingh135), [Arshnoor Kaur](https://cerebralvalley.ai/u/Arshnoor-kaur), [Avneet Singh](https://cerebralvalley.ai/u/avneetsingh36)
- **GitHub:** https://github.com/rsingh135/cortex
- **Demo video:** https://youtu.be/dKmFzzTWUHI
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/64

### 65. Scar Tissue

Scar Tissue: Every agent failure becomes a tested upgrade to its own harness.

An LLM agent takes a small grocery's orders in MongoDB Atlas. When a run breaks…

- **Team:** [Woody Kim](https://cerebralvalley.ai/u/woody-kim)
- **GitHub:** https://github.com/the-woody-kim/scar-tissue
- **Demo video:** https://www.loom.com/share/7ca4cb6854ea49e09f5fea81ad3be1bd
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/65

### 66. Pregame

Pregame is a call-prep assistant for a bank advisor, with a harness that keeps its own memory honest. Advisors stop trusting AI assistants within months…

- **Team:** [Abhishek Gaduputi](https://cerebralvalley.ai/u/Abhi7), [Francisco Garcia](https://cerebralvalley.ai/u/franciscogarcia), [Malcome Fein](https://cerebralvalley.ai/u/malcome), [Alexander Mong](https://cerebralvalley.ai/u/AlexanderMong)
- **GitHub:** https://github.com/sairam782/PreGame
- **Demo video:** https://drive.google.com/drive/folders/1lcw9f8_muTFKwLib_hK_fQ50vn0aJdxN?usp=drive_link
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/66

### 67. XChange

Xchange gives an engineering team's AI coding agents one shared memory. When an agent learns something useful on the job, it shares it on its own, and every…

- **Team:** [Shaurya tiwari](https://cerebralvalley.ai/u/shazam), [Arnav Srivastava](https://cerebralvalley.ai/u/arnavsriva), [Ahmad Nawaz](https://cerebralvalley.ai/u/afreelancer), [Xavier Barrios](https://cerebralvalley.ai/u/fenixbc)
- **GitHub:** https://github.com/Shazam6565/mongo-db-hackathon-Xchange
- **Demo video:** https://youtu.be/JVx_ligxheo
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/67

### 68. Chor

Gatekeeper: a procurement agent whose guardrails evolve themselves (Statement 1: Recursive Harnessing)

AI agents are starting to approve vendors, and they…

- **Team:** [Utsav Patel](https://cerebralvalley.ai/u/utsavp257), [Tarun Theegela](https://cerebralvalley.ai/u/Ttheegela)
- **GitHub:** https://github.com/utsavp257/gatekeeper
- **Demo video:** https://drive.google.com/file/d/1wehrHuLuhXqjKv4w-3WeVwxOTXNqEQYz/view?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/68

### 69. Morgadarsha

Recursive Computer Use is a local-first desktop automation harness that enables AI agents to execute tasks on your computer, verify outcomes locally, and…

- **Placement:** 3rd Place
- **Team:** [Adarsha Mishra](https://cerebralvalley.ai/u/pass), [Morgan Le](https://cerebralvalley.ai/u/lhnm)
- **GitHub:** https://github.com/lhnminh/recursive-computer-use
- **Demo video:** https://youtu.be/x6hrG1wZUH4
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/69

### 70. Robologue

Robologue: a dialogue for robots. Procedural memory for long-horizon tasks.

Long-horizon robots fail for a simple reason: they forget what went wrong five…

- **Team:** [Shravanthi Murugesan](https://cerebralvalley.ai/u/shravanthim), [Rosario Medina](https://cerebralvalley.ai/u/RosarioM), [Basith Mohamed](https://cerebralvalley.ai/u/Basithmd), [Varun Sahni](https://cerebralvalley.ai/u/varunsahni)
- **GitHub:** https://github.com/shravanthi-m/Robologue
- **Demo video:** https://www.loom.com/share/ecb395beb0a044c2a6a2bcf2511b27ca
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/70

### 71. Visai

Visai is a self-improving agent that makes a model faster on the machine it actually runs on, then remembers what worked so the next run searches less.

You…

- **Team:** [Baladhurgesh Balagurusamy Paramasivan](https://cerebralvalley.ai/u/baladhurgesh)
- **GitHub:** https://github.com/Baladhurgesh/visai
- **Demo video:** https://youtu.be/ett4xa3fNoc
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/71

### 72. Forge

ToolSmith is a procedural memory layer for AI agents that turns repeated work into tested, reusable tools. It watches how people and agents work, both on…

- **Team:** [Adish Padalia](https://cerebralvalley.ai/u/Adish26), [Dharm Patel](https://cerebralvalley.ai/u/dharmpatel02), [Neel Barve](https://cerebralvalley.ai/u/supiktalka)
- **GitHub:** https://github.com/DharmPatel02/toolsmith
- **Demo video:** https://www.youtube.com/watch?v=lGv79t3B_9A
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/72

### 73. Immune-Harness

Can we stop AI agents from going rogue before they take over the world?

Immune Harness is a security layer for AI agents. It checks every tool call before it…

- **Team:** [Jalil Jabbarli](https://cerebralvalley.ai/u/javie32)
- **GitHub:** https://github.com/Jalil-g/Immune-Harness
- **Demo video:** https://docs.google.com/document/d/1g23-wiK1KwOr-sqiF4lpD4dH_HfYzTip17Vs1_qj6mk/edit?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/73

### 74. Proofread

Goodhart's law says that when a measure becomes a target, it stops being a good measure. Language models obey this pretty well; as ImpossibleBench documents…

- **Team:** [Adeel Khatri](https://cerebralvalley.ai/u/AKhatri98), [Devakh Rashie](https://cerebralvalley.ai/u/devrashie)
- **GitHub:** https://github.com/Akhatri98/mdbh_proofread
- **Demo video:** https://youtu.be/pdi0CTSgD5g
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/74

### 75. Omega

Omega is an adaptive context and execution layer for high-stakes operations. It ingests fragmented information from sources such as email, Slack, CRM, project…

- **Team:** [Wayne Yang](https://cerebralvalley.ai/u/WayneYYC), [Aidan Cuccaro](https://cerebralvalley.ai/u/ac3362), [Jesse Multani](https://cerebralvalley.ai/u/jessem), [Anthony Spezzano](https://cerebralvalley.ai/u/roguelitelabs)
- **GitHub:** https://github.com/2akc/OperationsErrorMinimization
- **Demo video:** https://youtu.be/O4h--IXyHik
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/75

### 76. Refresh

Large language models are a new frontier in how we interact with and generate digital content, but they still face significant limitations when working with…

- **Team:** [Pranav Agrawal](https://cerebralvalley.ai/u/apranav22), [Aayush Poudel](https://cerebralvalley.ai/u/aayushpoudel), [Tanay vajhala](https://cerebralvalley.ai/u/Tvajhala), [Denis Koterov](https://cerebralvalley.ai/u/godbrigero1)
- **GitHub:** https://github.com/apoudel20/refresh
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/76

### 77. Rulebook

Rulebook — the harness that writes its own rulebook, from the one you already wrote by hand.

Every team using a coding agent has been building a recursive…

- **Team:** [Tom Ortega](https://cerebralvalley.ai/u/LordBron)
- **GitHub:** https://github.com/lordbron/Rulebook
- **Demo video:** https://vimeo.com/1230566131/09391ea373?share=copy&fl=sv&fe=ci
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/77

### 78. AI Cybersquad of 1

This is a cybersecurity agent that learns from past cybersecurity attacks. This means it is better prepared in the future for future attacks that are similar…

- **Team:** [Shay Bouchles](https://cerebralvalley.ai/u/shaythegay13)
- **GitHub:** https://github.com/shaythegay13/regime
- **Demo video:** https://drive.google.com/file/d/1-ow7gd0AoyPQ2r8Gu9ymCd6yfG9NhhuE/view?usp=drive_link
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/78

### 79. Team Darwin

Darwin. Self-improving research system for 5S rRNA biology.

This project builds a self-improving research system to investigate how changes in 5S ribosomal…

- **Team:** [Iveena Mukherjee](https://cerebralvalley.ai/u/blueballoons25), [Vedic Mukherjee](https://cerebralvalley.ai/u/vedic)
- **GitHub:** https://github.com/VedicAM/darwin
- **Demo video:** https://drive.google.com/drive/folders/1XnfuMFlp2pcVgxVZgBwdMCxIW7CZDKZD?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/79

### 80. Raaya

Raw Material Intelligence for Automotive Purchasing

- **Team:** [Harshita Darwatkar](https://cerebralvalley.ai/u/HDarwatkar)
- **GitHub:** https://github.com/HarshiAJ/MongoDBHack
- **Demo video:** https://github.com/HarshiAJ/MongoDBHack/blob/main/demo/rmi_agent_demo.mp4
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/80

### 81. Tomok

Tomok turns heavy civil construction project history into planning knowledge.

- **Team:** [qiman wang](https://cerebralvalley.ai/u/qimanwang)
- **GitHub:** https://github.com/QimanWang/tomok-mongodb
- **Demo video:** https://youtu.be/fv4hBu8O0Gw
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/81

### 82. JITAgent

# AgentJIT: a JIT compiler for LLM agents

## The problem
Production agents pay full LLM cost and latency for every task, even the thousandth one that follows…

- **Team:** [Susan Poudel](https://cerebralvalley.ai/u/Susanpdl), [Shaurabh Ghimire](https://cerebralvalley.ai/u/ghimireshaurabh)
- **GitHub:** https://github.com/ShaurabhGhimire/AgentJIT
- **Demo video:** https://drive.google.com/file/d/15-0KIulGUoXbnnNpClKsVPUNmGTul9mT/view?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/82

### 83. Tokeneyezed

We built a harness for track 2 targetting memory management. It included an observer agent for managing data streams.

- **Team:** [Aaron Chu](https://cerebralvalley.ai/u/aaronchu), [Julian Vilfort](https://cerebralvalley.ai/u/jazoe), [Gunjan Sen](https://cerebralvalley.ai/u/gsen0822), [Dharshan Vetrivelan](https://cerebralvalley.ai/u/Dharshanv06)
- **GitHub:** https://github.com/ja-zoe/tokeneyezed
- **Demo video:** https://youtube.com/shorts/KVJkaA2ZAa8?si=MoT1kMoZxtGsNl8M
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/83

### 84. DDN

Safe Harbor: real genomic evidence investigations with durable memory and evaluated harness adaptation

From docs/safe-harbor/SPECIFICATION.md:

What it is: a…

- **Team:** [Dmytro Popov](https://cerebralvalley.ai/u/LifeDisparity), [Nathan Ray](https://cerebralvalley.ai/u/NathanRay), [Don Shin](https://cerebralvalley.ai/u/Donshin03)
- **GitHub:** https://github.com/Nathan-T-Ray/Safe-Harbor
- **Demo video:** https://youtu.be/DzESx25aYJg
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/84

### 85. satyam

PortPilot helps migrate / port a software service from one legacy tech stack to other. Legacy services are mostly radioactive and no one wants to own them and…

- **Team:** [Satyam Chatrola](https://cerebralvalley.ai/u/Nightshade)
- **GitHub:** https://github.com/Nightshade14/portPilot
- **Demo video:** https://drive.google.com/file/d/1czPOX76DS68eTC-fb8oTlOj0e2dCNA6q/view?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/85

### 86. Flake

Flake is an AI agent that plans group events like dinners and trips. It keeps the organizer from getting stuck with the bill when friends bail or pay late, by…

- **Team:** [Paul Adu-Gyamfi](https://cerebralvalley.ai/u/padugyamfi), [Anthony Arko Jr](https://cerebralvalley.ai/u/Arkoo), [Jeremiah Adu-Gyamfi](https://cerebralvalley.ai/u/JeremiahAdu)
- **GitHub:** https://github.com/4rkooo/flake
- **Demo video:** https://youtu.be/qFk1zxuMf9A
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/86

### 87. rekurse

Rekurse helps coding agents avoid repeating the same failed approach.

When an agent gets stuck, Rekurse records the session and creates checkpoints before…

- **Team:** [Lingzi Zhou](https://cerebralvalley.ai/u/Lingzi), [Harry Hong](https://cerebralvalley.ai/u/HarryH), [Yvonne Shui](https://cerebralvalley.ai/u/a_boat_on_water), [Sabrina Yang](https://cerebralvalley.ai/u/sabyangds)
- **GitHub:** https://github.com/a-boat-on-water/rekurse
- **Demo video:** https://www.youtube.com/watch?v=Rma36ldVMWQ
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/87

### 88. Jia Labs

Frontier models can work for hours, but one hallucination can snowball into bad plans, tool calls, and wasted spend.
Existing validation often catches this…

- **Team:** [Henry Liu](https://cerebralvalley.ai/u/codicate), [Suchith Hegde](https://cerebralvalley.ai/u/suchithhegde)
- **GitHub:** https://github.com/suchithh/anchor
- **Demo video:** https://cap.so/s/bp5q34pqt9s676r
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/88

### 89. Wrasse

Wrasse: the harness that keeps your coding agent on the plan

The problem. AI coding agents are powerful but have no discipline. You give one a goal and a…

- **Team:** [Sai Sidam](https://cerebralvalley.ai/u/Saisidam)
- **GitHub:** https://github.com/sai-sidam/Wrasse
- **Demo video:** https://youtu.be/1NnCkBekQQs
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/89

### 90. Reconcile

Persistent reconciliation harness built with Google ADK, OpenAI, MongoDB Atlas, FastAPI, and React.

- **Team:** [Apoorva Menon](https://cerebralvalley.ai/u/ApoorvaM), [Mitran Ramesh Kumar](https://cerebralvalley.ai/u/Mitran)
- **GitHub:** https://github.com/Apoorva-Menon/ReconForge
- **Demo video:** https://drive.google.com/file/d/1qeRYCI3H9UTcMZwWcujwjt64Nk5U12nX/view?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/90

### 91. Pheonix

ClaimMemory
Public adjusters and disaster-claim policyholders fight insurers over months, across hundreds of documents, with no reliable memory of what was…

- **Team:** [Manju Yadav](https://cerebralvalley.ai/u/manjupheonix93)
- **GitHub:** https://github.com/MNJUYDV/claimmemory
- **Demo video:** https://youtu.be/vBzHq51MC3w
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/91

### 92. Many Lives

Many-Lives is a persistent-world agent harness, demonstrated by a turn-based text dungeon. The harness is the product; the game is the environment.

It solves…

- **Team:** [Mike Sandare](https://cerebralvalley.ai/u/msandare), [Niraj Amalkanti](https://cerebralvalley.ai/u/RedoubtWarden), [Harry Singh](https://cerebralvalley.ai/u/harrypahwa)
- **GitHub:** https://github.com/HarryPahwa/Many-Lives
- **Demo video:** https://drive.google.com/drive/folders/1J_7vYpNcmb6lpu1cV5rhMlVdCYe7k60z
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/92

### 93. UltraPM Console

A console for project managers to query continuous OS-level and screen-capture data over long horizons using a custom agent served from openrouter using…

- **Team:** [Lex Hackett](https://cerebralvalley.ai/u/lexhacke), [Solal PM](https://cerebralvalley.ai/u/Solal), [Ton Hoang Nguyen](https://cerebralvalley.ai/u/hahabill)
- **GitHub:** https://github.com/lexhacke/PM-24-7
- **Demo video:** https://www.loom.com/share/2c0e22669b004c049fe72de9252ecdac
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/93

### 94. Btechs

KYAgent is a KYB + KYA trust infrastructure layer for AI-era commerce.

- **Team:** [Pauloes Berhe](https://cerebralvalley.ai/u/Pauloes)
- **GitHub:** https://github.com/pauloes-btechs/KYAgent
- **Demo video:** https://youtu.be/UosbWoQTqjU
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/94

### 95. Casefile

Casefile helps review large construction claim files. It organizes the record into a chronology, party map, exhibit list, and coverage report, with a source…

- **Team:** [Tilak Sharma](https://cerebralvalley.ai/u/tilak1114), [Nipun Agarwal](https://cerebralvalley.ai/u/NipunAgarwal)
- **GitHub:** https://github.com/Tilak1114/casefile
- **Demo video:** https://drive.google.com/file/d/13Zrvp2Dx-zzIb1f9QFowKRNNKRAK3JhZ/view?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/95

### 96. NYC-Flood-Map-Agent

A flood agent whose answers are fenced in by real, versioned evidence in MongoDB Atlas. Today it refuses unsupported claims. Next, it remembers every answer…

- **Team:** [Araceliz Gomes](https://cerebralvalley.ai/u/araceliz)
- **GitHub:** https://github.com/AracelizGomes/nyc-flood-map-agent
- **Demo video:** https://youtu.be/YbvbhLZDFlI
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/96

### 97. ShadowCFO

Shadow CFO ( https://shadow-cfo.vercel.app  ) is a self-improving AI financial agent whose rules live as evolving documents in MongoDB Atlas, letting it…

- **Team:** [game ram](https://cerebralvalley.ai/u/game)
- **GitHub:** https://github.com/vim719/Shadow-CFO
- **Demo video:** https://www.loom.com/share/685f843960884efd8ce0d8f8a051b942
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/97

### 98. Continuum

Continuum is a memory, policy and explanation layer for AI agents on MongoDB Atlas: it recalls what worked, follows a human-approved policy, and can explain…

- **Team:** [Carlos Arellano](https://cerebralvalley.ai/u/carlosarellano)
- **GitHub:** https://github.com/carlosarellano0969/continuum
- **Demo video:** https://youtu.be/pnJIKWf5Dhs
- **Project:** https://cerebralvalley.ai/e/mongodb-nyc-hackathon/hackathon/gallery/98

---

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