# The Harness Engineering & Model Wrangling #SFTechWeek Hackathon: Project Gallery

- **Event:** [The Harness Engineering & Model Wrangling #SFTechWeek Hackathon](https://cerebralvalley.ai/e/mongodb-sftw-hackathon)
- **When:** Sun, Oct 11 at 9:00 AM – 10:00 PM (PDT)
- **Where:** San Francisco, CA
- **Hosts:** [MongoDB](https://cerebralvalley.ai/u/mongodb)
- **Projects:** 93 (6 placed)
- **Page:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery

## Projects

### 1. banana-fighter

to train a bot to play a game for you using recursive harnessing, a self-improving agent that repeatedly plays the game, evaluates its performance, identifies…

- **Team:** [Cal Cu](https://cerebralvalley.ai/u/calcu), [sam sam](https://cerebralvalley.ai/u/gguf)
- **GitHub:** https://github.com/mochiyaki/banana-fighter
- **Demo video:** https://youtu.be/fvHchyXywMI
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/1

### 2. LILI

Lili is an adaptive discovery assistant combining two main activities finding places and professional opportunities and she can do so much more!

- **Team:** [Edluis Amaya](https://cerebralvalley.ai/u/edluis316)
- **GitHub:** https://github.com/edluis37/Lili---MongoDB-Hackathon-SF
- **Demo video:** https://sentiai.pro/new/video.html
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/2

### 3. RED QUEEN

# RED QUEEN 2.0 — The Evolution Chamber

**Every fix must survive its own attack.**

**What if an AI agent could test its own solutions, learn from failures…

- **Team:** [Vincent Leguide](https://cerebralvalley.ai/u/Vincentleg)
- **GitHub:** https://github.com/vincentleg/red-queen
- **Demo video:** https://youtu.be/HBdpju9CPno
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/3

### 4. DrawTalk Harness

**The problem:** agents interpret ambiguous human input (a sketch, a phrase, a gesture) with an expensive LLM call every time, and they never become *yours*…

- **Team:** [Li-Yi Wei](https://cerebralvalley.ai/u/liyiwei)
- **GitHub:** https://github.com/1iyiwei/drawtalk-mongodb-sftw-hackathon
- **Demo video:** https://youtu.be/-H8eB0-2pQw
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/4

### 5. Bayflow

BayFlow is a self-improving AI agent system for San Francisco transit. Operator agents for Muni, BART and Caltrain run a simulated commute on the real city…

- **Team:** [Rae Jin](https://cerebralvalley.ai/u/raejin)
- **GitHub:** https://github.com/jin-dalrae/bayflow
- **Demo video:** https://youtu.be/oE6TcyYa9_c
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/5

### 6. Procurator

Procurator is a project-manager agent that holds the mandate for an autonomous engineering mesh — you phone it, give a directive, hang up, and its team of…

- **Team:** [Manjesh Prasad](https://cerebralvalley.ai/u/JayTech_456), [sam sam](https://cerebralvalley.ai/u/gguf)
- **GitHub:** https://github.com/jp-215/Procurator
- **Demo video:** https://youtu.be/h_IgJgvNu4Y
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/6

### 7. AgentShield

AgentShield is a self-evolving guardrail layer for agent-to-agent (A2A) traffic. When AI agents pass customer data to each other, off-the-shelf PII filters…

- **Team:** [Akhil Vallala](https://cerebralvalley.ai/u/Akhil_v_krishna)
- **GitHub:** https://github.com/Akhilvallala1/agentshield
- **Demo video:** https://youtu.be/rxwgwG6DUzY
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/7

### 8. SuperBid

Super Bid is a self-improving AI estimator that teaches itself to price bids the way a specific company would. It practices on the company’s real past bids…

- **Placement:** Finalist
- **Team:** [Kaushik Immadisetty](https://cerebralvalley.ai/u/kimmadisetty), [Martin Mellado](https://cerebralvalley.ai/u/martinamg88)
- **GitHub:** https://github.com/martinomg/super-bid
- **Demo video:** https://www.youtube.com/watch?v=RHD78ItTYvs
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/8

### 9. Team Tesfa

AI agents that write recurring business reports start from zero every week, so they can't say "third week in a row" or "the fix you tried didn't work."…

- **Team:** [Abel Tesfa](https://cerebralvalley.ai/u/abelSF)
- **GitHub:** https://github.com/abeltesfa/longview
- **Demo video:** https://youtu.be/snZA3PoUrKU
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/9

### 10. Routemind

RouteMind is self-improving agent memory on MongoDB Atlas: a car teaches itself a real San Francisco drive, from Shack 15 to Ocean Beach, by learning from its…

- **Team:** [Mohammad Adnan](https://cerebralvalley.ai/u/iamadnan), [Kaushik Sivakumar](https://cerebralvalley.ai/u/kaushik07)
- **GitHub:** https://github.com/KaushikSiva/routemind
- **Demo video:** https://youtu.be/pJ3UG_4ehi0
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/10

### 11. before-the-drop

On October 8, 2026, reporting about OpenAI’s revenue expectations unsettled the AI trade. Headlines contrasted an annualized revenue figure near $50 billion…

- **Team:** [Minakshi Mukherjee](https://cerebralvalley.ai/u/nori_84853)
- **GitHub:** https://github.com/adaboostmm/before-the-drop
- **Demo video:** https://youtu.be/5YR9R0qUImI
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/11

### 12. AIZOYA

AIZOYA’s Engineering That Remembers helps coding assistants resume engineering work from verified evidence instead of starting over.

MongoDB Atlas preserves…

- **Team:** [Franklyn Rosario](https://cerebralvalley.ai/u/aizoya)
- **GitHub:** https://github.com/aizoya/aizoya-engineering-recovery
- **Demo video:** https://docs.google.com/videos/u/0/d/1r72Ag6aw8LCNcaeVRM42ut8dASJ-3CBWZOOU2twqvkc/play
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/12

### 13. Aegis

Aegis is a governance harness for AI agents — the harness is the product. Every tool call passes through a policy gate (allow / deny / approval queue); every…

- **Team:** [Hui Hu](https://cerebralvalley.ai/u/hwoo)
- **GitHub:** https://github.com/Hui-Hwoo/aegis
- **Demo video:** https://drive.google.com/file/d/1mbrjmc1LygVS3_Ugu9XUml4NKbHTjCZ2/view
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/13

### 14. Trojans_VerdictLoop

VerdictLoop - A Self-Improving Safety Harness for AI Agents

AI agents are becoming increasingly autonomous, but giving them permission to modify…

- **Team:** [Vedant Bhenia](https://cerebralvalley.ai/u/Vedantttttt), [sanchita suryavanshi](https://cerebralvalley.ai/u/Sanchita)
- **GitHub:** https://github.com/sanchita1910/VerdictLoop/tree/main
- **Demo video:** https://drive.google.com/file/d/1YUgL-hU8oXLUc7SH-SX69KGCblYZxH1z/view?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/14

### 15. Muscle Memory

A robot that gets better at handling objects it’s never seen, without retraining. After every round, an AI coach reviews what broke and rewrites the robot’s…

- **Placement:** Finalist
- **Team:** [Kartik Mehra](https://cerebralvalley.ai/u/Mkartik007), [Aman Kothari](https://cerebralvalley.ai/u/Akkkk)
- **GitHub:** https://github.com/Kartik-007/skill-smith
- **Demo video:** https://drive.google.com/drive/folders/1WdyH4u_fQYa4OocBCMGTuAox72eQ98VG?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/15

### 16. ammas health

Amma's Health is a family health record that reads my mother's lab reports, remembers them for months, learns from our corrections, and proves every step.

My…

- **Team:** [Sreeprasad Govindankutty](https://cerebralvalley.ai/u/sreeprasad)
- **GitHub:** https://github.com/sreeprasad/ammas-health
- **Demo video:** https://www.youtube.com/watch?v=AMICUd4mt9k
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/16

### 17. Probity

Ratchet turns an AI agent's mistakes into tested, signed safety rules, and refuses any change it cannot prove.

- **Team:** [Sankalp Gilda](https://cerebralvalley.ai/u/sgilda)
- **GitHub:** https://github.com/probityai/ratchet
- **Demo video:** https://drive.google.com/file/d/1f8ZZkG6Nab_1BCH1KyUN0CLx-TD758YL/view
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/17

### 18. WorldSTATE

WORLDSTATE gives physical spaces a memory. Any phone becomes an observer: open a link, point the camera, and WORLDSTATE tracks what's inside fridges, shelves…

- **Placement:** Finalist
- **Team:** [Arnav Dewan](https://cerebralvalley.ai/u/arnavdewan), [Thilak Shekhar Shriyan](https://cerebralvalley.ai/u/thilakshriyan)
- **GitHub:** https://github.com/arnxv0/worldstate-mongodb
- **Demo video:** https://youtu.be/y532iVUl6y4
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/18

### 19. Agent46

We built Regression Court: a self-improving harness for an insurance agent (Agent46), running on MongoDB Atlas Agent Engine with Atlas Cluster0 as its data…

- **Team:** [Pavan Adipuram](https://cerebralvalley.ai/u/PavanAdi)
- **GitHub:** https://github.com/4625Labs/self-improving-agent-harness
- **Demo video:** https://www.loom.com/share/d11c5fce945649c39c44e5acfcea53d5
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/19

### 20. MongoMation

MongoMation is an autonomous PLC engineer. You describe a machine in plain English, and Claude agents write IEC 61131-3 PLC code, compile and deploy it to a…

- **Placement:** 1st Place
- **Team:** [ALI AMJAD](https://cerebralvalley.ai/u/aliamjad), [Zubair Zafar](https://cerebralvalley.ai/u/zubair480)
- **GitHub:** https://github.com/zubair480/MongoMation
- **Demo video:** https://youtu.be/H_7weLtCTmk
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/20

### 21. Expunge

Expunge is a database-cleanup agent that learns where records hide, rewrites its own harness, and has to prove its work to MongoDB.

The problem: deleting one…

- **Team:** [Nihal Nihalani](https://cerebralvalley.ai/u/nihalnihalani), [Charlie Gillet](https://cerebralvalley.ai/u/charlie_gillet)
- **GitHub:** https://github.com/nihalnihalani/expunge
- **Demo video:** https://drive.google.com/drive/folders/1eURty34_0y1OCuUZ7L-WLo3NNPkD2c1l?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/21

### 22. Oops, We Evolved!

Oops, We Evolved! is an agent harness recovery prototype. When a tool fails, it captures failure evidence, proposes a configuration repair, tests that repair…

- **Team:** [Sunny Rodrigues](https://cerebralvalley.ai/u/sunnyrodrigues)
- **GitHub:** https://github.com/srodrift/oops-we-evolved
- **Demo video:** https://www.loom.com/share/22523a1ecfa54dd3b9c7abbcc85aec3f
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/22

### 23. icomppower

Runbook Recursion: an MSP operations agent that rewrites its own runbooks from verified outcomes.

MSPs fix the same problems across dozens of clients, but…

- **Team:** [Johnny Lai](https://cerebralvalley.ai/u/SharkGundam)
- **GitHub:** https://github.com/icomppower/msp-ops-agent
- **Demo video:** https://youtu.be/rQCuQLdR1K0
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/23

### 24. ctrl-z

ctrlz is a production-reliability platform for AI agents that brings state rollback, causal lineage tracing, and dynamic guardrail evolution to persistent…

- **Team:** [Manvender Raparia](https://cerebralvalley.ai/u/Manubaba)
- **GitHub:** https://github.com/manvendersingh21/ctrlz, https://ctrlz-mu.vercel.app/
- **Demo video:** https://drive.google.com/file/d/1ASi3T0g0_UN4N9n1n1UDUZKJsC6id8aq/view?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/24

### 25. Nexus Innovators AI Production Support

## NEXUS AI Operations Center

NEXUS AI Operations Center is an AI-powered production engineering platform designed to transform incident management from…

- **Team:** [Sravan Nalajala](https://cerebralvalley.ai/u/Srava_)
- **GitHub:** https://github.com/sravanJava/AIProductionEngineer
- **Demo video:** https://drive.google.com/file/d/1YavqDWUpECXxpuNV_vjgnufrDiAva_Lb/view?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/25

### 26. Mellivora One

ImportForge is a self-improving warehouse import agent built during this hackathon. A model generates varied synthetic warehouse CSV files with deliberate…

- **Team:** [Boris Kovalenko](https://cerebralvalley.ai/u/BorisKov)
- **GitHub:** https://github.com/BorisKovStudio/importforge
- **Demo video:** https://drive.google.com/file/d/1ziLl94ePZAPxbG12CfpesoYW5R_yarS7/view?usp=drivesdk
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/26

### 27. Omniq

One person + a team of self-improving agents = 10×. Omniq Atlas gives every employee a team of specialist agents (20 role agents across developer, PM…

- **Team:** [Sandeep Vijayarao](https://cerebralvalley.ai/u/VijayaraoSandeep)
- **GitHub:** https://github.com/sandeepvijayarao09/omniq-atlas
- **Demo video:** https://youtu.be/wU7L7CL-zpc
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/27

### 28. aperture

Aperture — See What Your Agent Actually Saw.
AI agents often fail not because information is unavailable, but because critical evidence gets lost when…

- **Team:** [Sree Lekshmi P](https://cerebralvalley.ai/u/not_a_goddess)
- **GitHub:** https://github.com/Sree-lekshmi99/aperture/
- **Demo video:** https://youtu.be/3JcWjK_aOyA
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/28

### 29. Donna

Donna is an AI phone receptionist for small businesses that improves itself after every call. A customer calls a real number and talks to a voice agent built…

- **Team:** [Aayush Gandhi](https://cerebralvalley.ai/u/aayushgandhi), [Vishnu Vishak Srinivas](https://cerebralvalley.ai/u/VishnuSrinivas), [Ikshit Gupta](https://cerebralvalley.ai/u/ikshit_gupta)
- **GitHub:** https://github.com/gandhiaayush/mongodb_hack
- **Demo video:** https://youtu.be/828BnKVhIm4?si=EXoMYIVnlNB41Fmm
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/29

### 30. 59.4

59.4 is a self-improving harness: a frozen AI (Qwen3-30B, never retrained) runs a locked Texas winter-grid simulator, and each night a Claude coach rewrites…

- **Team:** [Prem Kanaparthi](https://cerebralvalley.ai/u/premxai), [TULASI VENKATA SRI VARSHINI PADAMATA](https://cerebralvalley.ai/u/Sri-Varshini-09)
- **GitHub:** https://github.com/premxai/59.4
- **Demo video:** https://youtu.be/CK61p4SdqFo
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/30

### 31. Kintsugi

Kintsugi: an agent that gets stronger where it breaks
Project demo: https://tsugi-production.up.railway.app/#stage

Tsugi is an always-on personal agent on…

- **Team:** [Thomas Cantuti](https://cerebralvalley.ai/u/tucci)
- **GitHub:** https://github.com/ThomasCantuti/kintsugi
- **Demo video:** https://youtu.be/EXEMmH2XXq4
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/31

### 32. Saw_the_bay_bridge_while_working_NICE

Catalog Harness helps retailers turn inconsistent supplier catalogs into evidence-backed product decisions. It preserves raw inputs, normalizes supplier…

- **Team:** [harshvardhan garude](https://cerebralvalley.ai/u/Harshvardhan03)
- **GitHub:** https://github.com/Harshvardhan-Garude/catalog-harness
- **Demo video:** https://www.loom.com/share/981586b362204ba887ee1d7633d14482
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/32

### 33. Dabo

Dabo is a self-evolving agent harness that uses the hardware itself as the feedback signal. You type a GPU task in chat, link your own harness from GitHub…

- **Team:** [Alazar Shenkute](https://cerebralvalley.ai/u/a8nova)
- **GitHub:** https://github.com/a8nova/Dabo
- **Demo video:** https://www.loom.com/share/0c880746d4fc4a3d809a9ef6daa7ac47
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/33

### 34. TeamBrain

Company knowledge is scattered, unstructured and often contradictory.

TeamBrain puts it all in one place and tells you what you can trust.

1. Collect. We…

- **Team:** [douglas lacerda](https://cerebralvalley.ai/u/douglas), [Alex Dubugras](https://cerebralvalley.ai/u/alexdubugras)
- **GitHub:** https://github.com/douglac/team-brain/
- **Demo video:** https://www.youtube.com/watch?v=jItGFA62JBg
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/34

### 35. mongoARC

mongoARC gives a Claude Code agent a long-term memory in MongoDB Atlas while it plays ARC-AGI-3, a benchmark of unfamiliar interactive games played level by…

- **Team:** [Dastin Huang](https://cerebralvalley.ai/u/dastin)
- **GitHub:** https://github.com/dastin359/MongoARC
- **Demo video:** https://youtu.be/DvGie9HadFg
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/35

### 36. RCFL

RCFL (Recursive Chaotic Fractal Learner) is a harness that rewrites its own rules. It watches chaotic visual data, scores its rule set at three scales every…

- **Team:** [Zachary Lafer](https://cerebralvalley.ai/u/zman007)
- **GitHub:** https://github.com/zman007-save/RecursiveChaoticFractalLearner
- **Demo video:** https://rcfl.brainmatch.app/out/video/rcfl-demo.mp4
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/36

### 37. CrashTest

CrashTest is a crash-test lab for AI agents. Connect an agent and CrashTest attacks it in a sandbox, writes a fix to the agent's harness, proves the fix, and…

- **Team:** [Shresthkumar Karnani](https://cerebralvalley.ai/u/Shresthk), [Kenil Himmatbhai Vaghasiya](https://cerebralvalley.ai/u/kenilv), [Aditya Nagpal](https://cerebralvalley.ai/u/adityan18)
- **GitHub:** https://github.com/anagpal18/MongoDB_recursive_agents
- **Demo video:** https://youtu.be/cTUNz6Or9fU
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/37

### 38. Pehovski

The problem: agents now edit their own prompts, rules and tool access, and almost nothing measures whether an edit made them better. Most self-improving…

- **Team:** [Dzmitry Piakhouski](https://cerebralvalley.ai/u/Pehovskix)
- **GitHub:** https://github.com/dmitrypehovski/mongo-harness
- **Demo video:** https://youtu.be/79JVxvYDE94
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/38

### 39. MerryCo

Agentic learning with a frozen agent is difficult. Agents can't reliably extract signal (cause of errors), and world-drift (the outcomes change due to the…

- **Team:** [Slava Zinevich](https://cerebralvalley.ai/u/Slavazin)
- **GitHub:** https://github.com/slavazin/munchhausen
- **Demo video:** https://drive.google.com/file/d/1pYR8GbENN0L_XHU35lnbsxeW3O5FkaaN/view?usp=drive_link
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/39

### 40. AgentTab

AgentTab keeps tabs on what an AI agent spends, and on the rules it spends by. It is a harness for an agent that buys small metered resources while nobody is…

- **Team:** [Robert Schwentker](https://cerebralvalley.ai/u/schwentker)
- **Demo video:** https://sandboxlabs.ai/agent-tab/
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/40

### 41. WiredFront

VibeGuard is a self-tightening agent harness built for vibecoders — people who ship with AI coding tools and pay for every retry, runaway loop and leaked key…

- **Team:** [Jesse Hall](https://cerebralvalley.ai/u/Jessay)
- **GitHub:** https://github.com/eonsofstupid/vibeguard
- **Demo video:** https://youtu.be/FP464OX1Kd8
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/41

### 42. Mavericks

Name: Backfill

Tagline: A self-improving agent harness that writes GPU schedulers and beats the published state of the art on a real 6,212-GPU production…

- **Team:** [Sachin Keswani](https://cerebralvalley.ai/u/shreem)
- **GitHub:** https://github.com/techstar9797/GPUoptimizer
- **Demo video:** https://youtu.be/T4KK97ZQODk
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/42

### 43. OpenLLM

Harry is your newest sales hire, but he isn't real. He's an agent that drafts follow-ups from your pipeline, reviews your sales call transcripts, and tells…

- **Team:** [Jonathan Archer](https://cerebralvalley.ai/u/Jarcher), [Memo Guleryuz](https://cerebralvalley.ai/u/memo)
- **GitHub:** https://github.com/0xxmemo/harry
- **Demo video:** https://www.youtube.com/watch?v=XXMj09bkEmQ
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/43

### 44. Rainy Day Fund

We built **Make It Rain**, an AI support agent designed to improve how it handles troubleshooting problems over time.

MongoDB Atlas is the authoritative…

- **Team:** [Byron Lee](https://cerebralvalley.ai/u/biobitworks)
- **GitHub:** https://github.com/biobitworks/rainy-day-fund
- **Demo video:** https://youtu.be/EJx0vBP40A4
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/44

### 45. doorman

doorman is a self-improving harness that sits at a website’s door. One script tag maps the page into tools and exposes them to visiting AI agents through…

- **Team:** [Sudhersan KV](https://cerebralvalley.ai/u/sudhersankv)
- **GitHub:** https://github.com/sudhersankv/doorman
- **Demo video:** https://www.loom.com/share/0fd21e5e199d4ce0ae2118f35b9a2c26
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/45

### 46. Notary

Notary is admission control for AI agent memory. Agents that learn from experience write "lessons" into procedural memory and follow them forever but nobody…

- **Team:** [Puja Sridhar](https://cerebralvalley.ai/u/PujaSridhar)
- **GitHub:** https://github.com/PujaSridhar/Notary
- **Demo video:** https://youtu.be/-PBWAN4ATcM
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/46

### 47. NavEvolve

NavEvolve — Self-Improving Spatial Memory for Embodied AI Agents

Embodied AI agents can perceive their surroundings, but struggle to remember places…

- **Team:** [Flavia Sparacino](https://cerebralvalley.ai/u/flavspa), [Jun Jiang](https://cerebralvalley.ai/u/jiangjun0105)
- **GitHub:** https://github.com/flaspa/NavEvolve
- **Demo video:** https://youtu.be/CdIh-03yXT4
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/47

### 48. Flex

I built Flex to repair an AI data center's training scheduler when operating conditions change. In the simulation, restart energy rose 30x and the frozen…

- **Team:** [Ricardo Reyes](https://cerebralvalley.ai/u/ricardoreyes)
- **GitHub:** https://github.com/ricardodreyes/flex-harness
- **Demo video:** https://youtube.com/shorts/oMNSXY8PE4k?feature=share
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/48

### 49. Aneeq Ur Rehman

Every company pays thousands of supplier invoices, and someone has to check each one against the purchase order before money goes out. Most of that work is…

- **Team:** [Aneeq Ur Rehman](https://cerebralvalley.ai/u/aneequrrehman)
- **GitHub:** https://github.com/aneequrrehman/ap-agent-harness
- **Demo video:** https://youtu.be/040pUVwzz6I
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/49

### 50. Rada

Rachet: a self-improving harness for MongoDB query tuning.

Slow queries cost money and frustrate users, and fixing them takes expert time: reading explain…

- **Team:** [Allen ZHAO](https://cerebralvalley.ai/u/KingEm), [Day Nguyen](https://cerebralvalley.ai/u/dayn), [venkateshbabu sekar](https://cerebralvalley.ai/u/vesekar), [Paras Jain](https://cerebralvalley.ai/u/JainyAI)
- **GitHub:** https://github.com/Jainparas99/RADA
- **Demo video:** https://youtu.be/2u26UuRqTqM
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/50

### 51. Morph

Morph adapts a robot fleet’s mission software to new robot bodies on its own. Use cases: disaster-response teams adding borrowed drones to ground fleets…

- **Team:** [Karthik Raja Anandan](https://cerebralvalley.ai/u/kitrakrev)
- **GitHub:** https://github.com/kitrakrev/morph
- **Demo video:** https://youtu.be/ERrACT4FlrY
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/51

### 52. Vivy

Vivy is a multi-agent 3D social sandbox: four animal agents (fox, panda, dog, cat) live in a voxel apartment, chat with each other and with you, act in the…

- **Team:** [Evelyn Yu](https://cerebralvalley.ai/u/evelynyu), [Jiaxin Liu](https://cerebralvalley.ai/u/JoannaLiu), [Ruixiang Huang](https://cerebralvalley.ai/u/TonyH), [yan ziyuan](https://cerebralvalley.ai/u/Ryan-Yan)
- **GitHub:** https://github.com/yanzai-4/Vivy
- **Demo video:** https://youtu.be/eAkNDXtYKRo
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/52

### 53. SREvolve

SREvolve is a recursively improving SRE agent harness that fixes incidents in a simulated Kubernetes cluster. The initial agent has a weak harness: it can…

- **Team:** [Araav Nayak](https://cerebralvalley.ai/u/Rav007)
- **GitHub:** https://github.com/AraavNayak/SREvolve
- **Demo video:** https://youtu.be/RwDBCPSuvVQ
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/53

### 54. By my self

GridMind AI is a persistent, self-improving and governed multi-agent harness on MongoDB Atlas that turns a failing power grid into an independently verified…

- **Team:** [Azita Darvishi](https://cerebralvalley.ai/u/1122)
- **GitHub:** https://github.com/AziiDarvii/gridmind-ai
- **Demo video:** https://github.com/AziiDarvii/gridmind-ai/releases/download/v1.0/GridMind_AI_Demo.mp4
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/54

### 55. PaperTrail

Insurers deny medical claims over payer rules nobody writes down. We built a self-improving harness that learns those rules from the denials. A scrubber agent…

- **Team:** [Xavier Huang](https://cerebralvalley.ai/u/xavierhuang), [Bruce Beckley](https://cerebralvalley.ai/u/Michspirit99), [Pranav Lende](https://cerebralvalley.ai/u/nullforce), [Arjun Prasad](https://cerebralvalley.ai/u/arjpras04)
- **GitHub:** https://github.com/ALLENDE123X/mongodb-memory-hackathon/
- **Demo video:** https://youtu.be/4INYMvjCl3o
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/55

### 56. Long Horizon Quant Research

Long-Memory Research Desk is a team of five quant agents that remembers twenty years of markets in MongoDB Atlas and reads live filings, news, prediction…

- **Team:** [Tehani Cabour](https://cerebralvalley.ai/u/tehanicabour), [Shawn Yang](https://cerebralvalley.ai/u/Shawny)
- **GitHub:** https://github.com/jordandaisy/long-memory-desk
- **Demo video:** https://youtu.be/AoOwNyLTuCc
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/56

### 57. LLM deployment agent

Every new open model is useless until someone figures out how to run it well. Today, LLM infra engineers do that by hand, or prompt by prompt with a chat…

- **Team:** [Henry Luan](https://cerebralvalley.ai/u/henryl)
- **GitHub:** https://github.com/casualcomputer/atlas-gpu-harness
- **Demo video:** https://youtu.be/WoHjJ6LMkpg
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/57

### 58. LabRat

LabRat is a self-improving harness for a physical lab agent, running on a real bench: two SO-101 arms, a 3018 CNC carrying a servo pipette I designed during…

- **Placement:** 2nd Place
- **Team:** [Jacob Valdez](https://cerebralvalley.ai/u/jvboid)
- **GitHub:** https://github.com/JacobFV/labrat
- **Demo video:** https://youtu.be/rYxdj7l4Z5I
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/58

### 59. Hype

Agents forget people between conversations and repeat the same mistakes. We built Amble’s Atlas memory loop to preserve context and learn from feedback…

- **Team:** [Nick Lulofs](https://cerebralvalley.ai/u/hype), [Chris Forrester](https://cerebralvalley.ai/u/elationate), [Ted Dessert](https://cerebralvalley.ai/u/teddessert)
- **GitHub:** https://github.com/HypernymAI/amble_mongo
- **Demo video:** https://youtu.be/-LxDgTxfKP0
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/59

### 60. The Data Graduate

A general data analyst that learns the business to analyze your business over time.

- **Team:** [Syd Reynolds](https://cerebralvalley.ai/u/sydreynolds)
- **GitHub:** https://github.com/sydneyreyrey/mongo-db-data-analyst
- **Demo video:** https://drive.google.com/file/d/1UdtELrvpkRsJKeLMdFWur8Zqd60sMYXF/view?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/60

### 61. Uptime Harness

The landing page with all instructions: https://uptime-harness.aemalsayer.com/

Uptime Harness turns production errors into verified fixes. It connects Sentry…

- **Team:** [Aemal Sayer](https://cerebralvalley.ai/u/aemal)
- **GitHub:** https://github.com/aemal/uptime-harness
- **Demo video:** https://youtu.be/jAiT4fO3TOg
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/61

### 62. Bonsai

Bonsai is an agent that improves itself. It edits its own harness (its rules, its tools and its playbook of lessons), and it keeps a change only when held-out…

- **Team:** [pranav achar](https://cerebralvalley.ai/u/prnav), [Nithin](https://cerebralvalley.ai/u/nithinaruswamy), [Kabir Koratkar](https://cerebralvalley.ai/u/Kabirkoratkar)
- **GitHub:** https://github.com/PranavAchar01/bonsai/
- **Demo video:** https://youtu.be/SY80CFiXurc
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/62

### 63. Mangopals

Coding agents sometimes make a failing test pass by changing the test instead of fixing the code. We observed this in a real Claude session: the agent changed…

- **Team:** [Rikin Shah](https://cerebralvalley.ai/u/rikinshah787), [Roshni K R](https://cerebralvalley.ai/u/roshnik9998)
- **GitHub:** https://github.com/Rikinshah787/Hackathon
- **Demo video:** https://drive.google.com/drive/folders/1VayRsgHlhJ5Jap6W4J_AOwylVO2i98Vw?usp=drive_link
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/63

### 64. Capybarrier

An adaptive immune system for AI agents.
It learns from every attack, rewrites its own defenses, and ships a fix only with receipts.

Capybarrier is a self…

- **Team:** [Nelson Lai](https://cerebralvalley.ai/u/chineseman)
- **GitHub:** https://github.com/chinesepowered/hack-sftw/
- **Demo video:** https://www.youtube.com/watch?v=mcaWHJ5Om3A
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/64

### 65. a^inf

a^inf is your persistent AI team in the cloud. Agents retain their own workspaces and context, collaborate directly, and stay available for follow-up…

- **Team:** [Richard Peng](https://cerebralvalley.ai/u/pengrich), [Michael Siu](https://cerebralvalley.ai/u/msiu), [Ryan Hu](https://cerebralvalley.ai/u/ry4nrn)
- **GitHub:** https://github.com/WingchunSiu/atoi
- **Demo video:** https://drive.google.com/file/d/1sylgoITOU4Ec0XcCXZIwRnMmO8i1DcmD/view?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/65

### 66. Helixa

HELIXA is a research studio for changing an agent’s scientific workflow without trusting a model to invent biology.

Genomic pipelines can report success…

- **Team:** [Chetas Parekh](https://cerebralvalley.ai/u/chetas)
- **GitHub:** https://github.com/chetas1208/Helixa
- **Demo video:** https://github.com/chetas1208/Helixa/blob/main/Demo.mp4
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/66

### 67. AgentDesk

AgentDesk is a front desk for AI agents that any website adds with one line: app.use(agentdesk()), plus a MongoDB URI and an LLM key. It starts knowing…

- **Team:** [Andres Carreon](https://cerebralvalley.ai/u/Andresio), [Sebastian Gandoulf](https://cerebralvalley.ai/u/Gandoulf7), [Ricardo Sandoval](https://cerebralvalley.ai/u/ricardoisv)
- **GitHub:** https://github.com/AndresCarreonDiaz/agentDesk
- **Demo video:** https://youtu.be/HXEio3LDOXE
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/67

### 68. lane - gambling on your friends success

Lane holds you accountable for any goal by connecting to your own AI agent. That could mean shipping code every day, posting your build in public, going to…

- **Team:** [Antoine Lescun](https://cerebralvalley.ai/u/antoinelescun), [Maxime Bellemare](https://cerebralvalley.ai/u/mxblmr)
- **GitHub:** https://github.com/mxblmr/lane
- **Demo video:** https://www.loom.com/share/499985a126374c7185f693e0d8039440?from_recorder=1&focus_title=1
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/68

### 69. Recoup

Recoup is the SLA-credit claims agent that remembers every win and loss in MongoDB, and whose next claim is better because of its last one. It reads GitHub's…

- **Team:** [Nikhil Kapu](https://cerebralvalley.ai/u/nikhilk)
- **GitHub:** https://github.com/nikhil-kapu/recoup
- **Demo video:** https://youtu.be/aSDD7V9ym4U?si=FgCfTSoPvDTFy7wa
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/69

### 70. Agent PhD

Laboratory automation is advancing, but scientific research still faces hard limits: available space and robots, costly reagents, and the time biological…

- **Team:** [Christine Baek](https://cerebralvalley.ai/u/cbaek)
- **GitHub:** https://github.com/viirii/scientist_agent
- **Demo video:** https://drive.google.com/file/d/1mAXwDTHRC4LYU_rXaJqEl69QLMn5i9ho/view?usp=drive_link
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/70

### 71. hydra

Hydra is an autonomous, self-healing AI agent framework designed to eliminate schema drift and breaking API contracts in production. When an agent encounters…

- **Team:** [Sophia Park](https://cerebralvalley.ai/u/sophiapark)
- **GitHub:** https://github.com/sophiepark22/hydra-harness
- **Demo video:** https://youtu.be/1HO5Ssyka6M
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/71

### 72. Forge Extended

Forge: an AI agent that rebuilds its own harness, and can't cheat to do it.

Forge takes a small, frozen model (gpt-4.1-nano) and lets an agent improve…

- **Team:** [Subhan Poudel](https://cerebralvalley.ai/u/poudelsubhan)
- **GitHub:** https://github.com/poudelsubhan/forge-harness
- **Demo video:** https://www.loom.com/share/715ac01527434f1b9b4cc7487b921e24
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/72

### 73. OptBench

A self-improving AI agent that transforms GPU profiling data, technical research, and source code into ranked, actionable optimization tasks for open-source…

- **Team:** [Lily Su](https://cerebralvalley.ai/u/lilyxsu)
- **GitHub:** https://github.com/LilySu/OptBench
- **Demo video:** https://www.loom.com/share/c14faaaaa38441c3a525f1fd132b4b50
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/73

### 74. Precedent

Precedent is a governance harness that lets company AI agents act, learn and be stopped, safely. Agents in companies fail in two ways: they do things they…

- **Team:** [Vikhas Somasundaram Giri](https://cerebralvalley.ai/u/Vikhas), [Sudharsana Rajasekaran](https://cerebralvalley.ai/u/sudhan30)
- **GitHub:** https://github.com/Sudhan30/precedent-hackathon
- **Demo video:** https://youtu.be/veSjU09WZqk
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/74

### 75. LKS

Every robot in a real building eventually meets a fire door, a wet floor or a crowd it cannot handle, and a human takes over. Today that takeover is wasted…

- **Team:** [Lokesh lks](https://cerebralvalley.ai/u/Lkslokesh)
- **GitHub:** https://github.com/loki52501/Intervention-zero.git
- **Demo video:** https://www.loom.com/share/50af3772b30941de9fdeb00df2732c4e
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/75

### 76. Custos

Your agent can rewrite its own harness. It can never grade its own homework.

- **Team:** [Siddhant Sancheti](https://cerebralvalley.ai/u/siddhantsancheti)
- **GitHub:** https://github.com/sidsanc/custos
- **Demo video:** https://drive.google.com/drive/folders/1dYYZNLZAmi-tdmp6qKZUVhlOjZLoBlJC?usp=drive_link
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/76

### 77. Recursive Harness Scientist

Recursive Harness Scientist: an AI scientist that improves its own scientific method, and must replicate every gain on data it has never seen.

Why it…

- **Placement:** 3rd Place
- **Team:** [James Bian](https://cerebralvalley.ai/u/jamesbian)
- **GitHub:** https://github.com/yb235/recursive-harness
- **Demo video:** https://youtu.be/qs1tKruixXI
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/77

### 78. Rajappa R

Agent Recall is a persistent memory layer for AI agents that helps them retain, retrieve, and reuse knowledge from past experiences across tasks and…

- **Team:** [Rajappa R](https://cerebralvalley.ai/u/Rajappa)
- **GitHub:** https://github.com/RajappaXenon/agent-recall
- **Demo video:** https://drive.google.com/file/d/1wkVW6lvYPPdUjkEXha-t7mksQJX7b0mX/view?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/78

### 79. Shed

https://shed-molt.fly.dev

Shed is a recursive harness for agents. It observes which tools, rules, and memories a task uses, removes unused items while…

- **Team:** [Hatem Elsisi](https://cerebralvalley.ai/u/elsisiem)
- **GitHub:** https://github.com/elsisiem/shed
- **Demo video:** https://www.loom.com/share/2d0b03b534dd477292d5adb6bfcd0794
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/79

### 80. Style Fleet

Recursive style agents drift toward generic, catalog-clean outfits and have no way to know when they’ve left a brand’s taste.
We turned street-style photos…

- **Team:** [RackSavant AI](https://cerebralvalley.ai/u/specs15)
- **GitHub:** https://github.com/arminforoughi/racksavant-store
- **Demo video:** https://www.loom.com/share/02a4cc548d8e4f72b0ba46bfaf4dcb88
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/80

### 81. LifeGuide

LifeGuide is an AI-powered life navigation system that remembers important events, goals, preferences, decisions, and outcomes over time. When a user faces an…

- **Team:** [Karthik Shetty](https://cerebralvalley.ai/u/TechRun)
- **GitHub:** https://github.com/karthikshetty-1629/guru
- **Demo video:** https://youtu.be/mpUQHLsqk_w
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/81

### 82. Team Spectre

Strata: an AI research agent that can’t forget its failures
An AI agent that forgets its failures will report its luck as discovery. When an agent tests many…

- **Team:** [Shivansh A](https://cerebralvalley.ai/u/Spectre14), [Talal Khalid Wazir](https://cerebralvalley.ai/u/Talal2725)
- **GitHub:** https://github.com/Spectre1404/Strata
- **Demo video:** https://drive.google.com/drive/folders/1XbozLT660QdRgRWn322uM4bHEylzgzkA?usp=share_link
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/82

### 83. Kay

Fit Gate is a daily outfit stylist built as a self-rewriting agent harness. Pick a mood and occasion, and it styles looks from your real closet using…

- **Team:** [Khushi Gangrade](https://cerebralvalley.ai/u/khushigangrade)
- **GitHub:** https://github.com/khush-i97/Fit-Check
- **Demo video:** https://drive.google.com/drive/folders/1l2OW3bczjmUuWHpKPDlVmWAdw17dPRW1?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/83

### 84. tough

hx is a terminal coding agent that improves its own working environment from its own failures. Coding agents keep repeating the same mistakes across sessions…

- **Team:** [Om Kannan](https://cerebralvalley.ai/u/omythehomie)
- **GitHub:** https://github.com/hackathonmongodb/RSI_Harness.git
- **Demo video:** https://drive.google.com/file/d/1FeiDj8tRRQXlHbHlgqhBtRwMAZi5uHSv/view?usp=drive_link
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/84

### 85. Airlock

Airlock serves as a self-improving controller for delegating and evaluating subagents within coding harnesses. In our own experiences, we've found that the…

- **Team:** [Sumanth Reddy](https://cerebralvalley.ai/u/sumanth_reddy), [Matthew Morris](https://cerebralvalley.ai/u/mattmorris)
- **GitHub:** https://github.com/mattmorr1/airlock
- **Demo video:** https://drive.google.com/file/d/12ICrtaYNEQqNuKRGcUfqRnDsbxPM9vFp/view?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/85

### 86. Preflight

We help personal bots create successful bots without having to test it.

- **Team:** [Arshia Moghaddam](https://cerebralvalley.ai/u/arshia), [Adriano Hernandez](https://cerebralvalley.ai/u/4gate), [Ramin Heydarlaki](https://cerebralvalley.ai/u/strider)
- **GitHub:** https://github.com/arshia93/mongodb-hackathon
- **Demo video:** https://drive.google.com/drive/folders/1dS9IZM-N6wtviCpTrSvW4SgLQNnNsZ3H?usp=sharing
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/86

### 87. Agazayt

Cash-heavy businesses (I'm involved with one: Thillens) reconcile deposits, invoices, and billing lines by hand every day, and the same fixes repeat for years…

- **Team:** [Warren Chan](https://cerebralvalley.ai/u/warrenwanders)
- **GitHub:** https://github.com/warren544/ledger
- **Demo video:** https://drive.google.com/file/d/1RuRiS0g443A0XTqyaArKD3lVOg4AWtEn/view?usp=drive_link
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/87

### 88. Harness Darwinism

We developed a self evolving harness using evolutionary algorithms to play Minecraft

- **Team:** [Suryaprakash Senthil Kumar](https://cerebralvalley.ai/u/splion360), [Subra Arun](https://cerebralvalley.ai/u/altnightfury2305), [Jacqueline Yeung](https://cerebralvalley.ai/u/Jacki)
- **GitHub:** https://github.com/Subrahmanyam2305/harness-darwinism
- **Demo video:** https://www.loom.com/share/8ea68c371219462a8112097b49ef0e65
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/88

### 89. Raindrop Returns Lab

HarnessEvolve is a returns operations simulation that shows how an AI agent can improve from its mistakes.
It compares a fixed agent with an adaptive harness…

- **Team:** [Vibhu Dixit](https://cerebralvalley.ai/u/vibhudixit)
- **GitHub:** https://github.com/vibhu-dixit/mongodb-MetaArchitect
- **Demo video:** https://www.loom.com/share/bcef1180635c4420a8feb78a64279b87
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/89

### 90. qnx

debugging web and code bases

- **Team:** [Quinn Martinelli](https://cerebralvalley.ai/u/Qsmqsm)
- **GitHub:** http://github.com/getbuggy1123.git
- **Demo video:** https://youtu.be/2XIkQYFYq00
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/90

### 91. SiteSim

Warehouse robots can waste time queuing at crowded lifts while faster routes go unused. Integration is a broader industry hurdle: 42% of surveyed businesses…

- **Team:** [Shashwat Mahalanobis](https://cerebralvalley.ai/u/ShashwatM), [Prithviraj Mody](https://cerebralvalley.ai/u/prithvirajmody), [Aseel Ahmed Lakadia](https://cerebralvalley.ai/u/aseel332)
- **GitHub:** https://github.com/ShashwatM3/mongodb-harness-engineering-hackathon/tree/main
- **Demo video:** https://youtu.be/Bm7P5DMX_YY
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/91

### 92. Quarantine

Quarantine is a self-improving harness for an IT-operations agent. Every tool call goes through one MCP gateway that enforces a policy stored in MongoDB…

- **Team:** [Emahatsion Issac](https://cerebralvalley.ai/u/issac)
- **GitHub:** https://github.com/amahaeitbit/quarantine
- **Demo video:** https://github.com/amahaeitbit/quarantine/blob/main/docs/demo.gif
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/92

### 93. OwnerOrbit

OwnerOrbit gives restaurant owners one place to delegate work, track business goals, and receive proof that actions were completed, starting with a simple…

- **Team:** [Ashay Srivastava](https://cerebralvalley.ai/u/ashaysriv), [Saddiq Jeelani](https://cerebralvalley.ai/u/saddiq-jeelani), [Karim Ali](https://cerebralvalley.ai/u/LeKiksss), [Abdullah Mohsin](https://cerebralvalley.ai/u/Abdullahmohsin)
- **GitHub:** https://github.com/donna-ownerorbit/ownerorbit-hackathon
- **Demo video:** https://youtu.be/srHEYGsTdUI
- **Project:** https://cerebralvalley.ai/e/mongodb-sftw-hackathon/hackathon/gallery/93

---

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