We challenged 250+ hackers to build Agent Apps with AgentOps. The goal: Make an agent-powered startup in a weekend.

AI agents are coming to replace you.

Here are the finalists from the Cognitive Agents Hackathon by @AgentOpsAI x @MindsDB x @MayfieldFund (🧵):



1/ Nexus AI

AI voice agent that calls vendors, fights for the best price, and negotiates with other vendors

AI agents for automating procurement officers w/ monitoring by @agentopsai

🥇First Place $1500 + Monitor

@wukevinl @sunnybak_ @narusevic @stateof_kate

Never underestimate the open source AI community.

These cracked engineers are here to break the limits of what’s possible with local LLMs. We just witnessed some nutty inventions.

Here’s what we saw at the @ollama Open Source and Local AI meetup at @cerebral_valley (🧵):

1/ Ollama: Concurrency mode

Run multiple local LLMs on one machine at the same time with shared resources

Even works with different models.
@ollama @dhiltgen

We invited 200+ engineers to take an exclusive look at the latest advancements in AI agent ecosystem

If you’re not following this space, your job is probably going to be replaced by AI.

Here’s what we saw at the @AgentOpsAI x @Relplicate Agent Meetup (🧵):

1/ AgentOps

Agents are slow, expensive, and unreliable. AgentOps is fixing that.

Track, test, and benchmark AI agents from prototype to production

@AlexReibman @AgentOpsAI @AtomSilverman @siyangqiu

Mistral AI is what OpenAI would be if it were actually open.

And they just threw the largest OSS LLM hackathon to date. Over 2000 hackers applied to compete for $10k in prizes.

Here’s what we saw at the @MistralAI x @cerebral_valley hackathon (🧵):

1/ Prompt Parfait

Generative prompt creator that continuously improves

“Learning” by prompting, calculating the loss against evals, and updating the prompt

🥇1st place API track

Llama Lounge just hosted the largest ever symposium of AI agent startups.

Over 400 VCs, builders, and innovators RSVP’d to get an exclusive look at the latest advancements in the SF AI startup scene.

Here’s what we saw at the Agents Llama Lounge by @BlitzVentures @jowyang (🧵):



1/ AgentOps

Track, monitor, and benchmark AI agents. Test your agents against 1000+ benchmarks and monitor performance from prototype to production

Agent tracking, benchmarking, and compliance



@atomsilverman @siyangqiu @agentopsai

p.c. @Scobleizer github.com/AgentOps-AI/ag…

For one day only, General Catalyst invited 20 of San Francisco’s top AI entrepreneurs to showcase what’s possible with AI.

Live product and raw code only. No pitches. No bullshit.

Here’s what we saw at the @cerebral_valley co-working demo session at @generalcatalyst (🧵): 1/ Entelligence

AI agent that generates execution/AST diagrams, creates code reviews, and writes pull requests

Upgrading the on-ramping process for junior engineers with AI

@Aiswarya_Sankar

Stanford just hosted a hackathon. Over 1000 students from around the world came to build for 36 hours straight.

The reward? $100k+ in prizes.

Here are the winners and crowd standouts we saw at TreeHacks ‘24 @hackwithtrees (🧵):

1/ Baymax

Robot arm controlled by natural language and speech to provide medicine to the elderly/physically disabled.

Every single robot control, including inverse kinematics, coded from scratch.

🏆Grand prize winner- $10,000
🏆Elderly citizens award- Free trip to Japan

OpenAI is losing its lead to AI that’s actually Open.

And these cracked engineers are here to prove it.

Some of the most impressive demos I’ve seen in a long time.

Here’s what we saw at the @ollama Open Source and Local AI meetup at @cerebral_valley (🧵):

1/ Ollama for Windows

@ollama running natively and seamlessly on Windows 10 and 11.

Super fast, and no need for WSL

@dhiltgen

AI Agents for the web are here.

These hackers spent 24 hours with an exclusive access API that lets LLMs control the browser. Now they’re showing what’s possible with AI web agents.

Here’s what we saw at the DevDay x @MultiON_AI hackathon at @cerebral_valley (🧵):



1/ Podcast GPT

Mini-podcasts generated by AI.

They generated one on the Sam Altman drama by cloning his voice and recapping major events

🥈Second Place

@flerovious @Aayush_Mathur7 @1gabyang1

OpenAI completely upended all of tech on Dev Day. We launched an emergency hackathon 2 days later.

200+ AI builders, founders, and researchers RSVP’d to hack. On a Wednesday.

Here are the top teams from the Emergency GPT Builders Hackathon at @MindsDB (🧵):

1/ Reflective AI

A vision enabled life coach that watches you throughout your day and helps you achieve your goals

Basically, poor man’s Humane Pin/Tab/Rewind.

GPT-4 vision + TTS + DALLE-3, all wrapped into a wearable

🥇First Place
@EthanSutin

300+ e/acc engineers just spent 24 hours building AI solutions to San Francisco’s most pressing challenges— housing, safety, public health

The Mayor even showed up.

Tweeting the finalists building a better future for SF at the @accelerate_sf Hackathon at @fdotinc (🧵):

1/ 311+

A 311 hotline that intelligently routes callers without the need for confusing and slow phone trees

Requests are summarized for human operators, making it easier for them to deliver city services

🥇First place winner

Chris Brox @twilio @lizziepika @engineer_abel

SF’s top AI hackers all came to a mansion to push the creative limits of art and music.

These projects are next-level

Tweeting my top picks from the Dreamscape Creativity Hackathon at
@agihouse_org w/ @mantisVC @coatuemgmt 🧵: 1/ TranquilAI

Motion detection + generative audio to create guided meditationsession sessions with @elevenlabsio

LLaVA1.5 watches your environment and guides you through your meditation practice

@kadvani

We invited 130+ AI engineers to discuss challenges, strategies, and achieving state of the art with AI agents.

The space is growing fast, and there’s a new breakthrough almost every week.

Here’s a what we saw at the SF Agent SOTA forum (🧵):

1/ Managing safety and alignment at AutoGPT

Key ideas:
* Manage alignment by implementing a monitoring layer between agent external actions and the world state.

Open questions:
* How can we build cheap and effective monitors without making 2x LLM calls?

@silennai @Auto_GPT

We invited 100+ engineers to take an exclusive look at the latest advancements in AI agent ecosystem

If you’re not following this space, your job is probably going to be replaced by AI.

Here’s what we saw in the AI Agent Developer Arena
(🧵):

1/ @sweep__ai

Sweep is building an AI agent that works as a junior software engineer

Raise issues, feature requests, and bug reports on GitHub and Sweep takes care of the rest
@kevinlu1248

LLM Fine tuning is here!

San Francisco’s top AI engineers came together to see what’s possible with fine-turning and only 4 hours of hacking.

Here’s an exclusive what we saw at the “Anything But Wrappers” hackathon (🧵):

1/ Fine tuning on emails

Harrison fine-tuned GPT-3.5 on his emails to politely reject notes from VCs and respond to cool guys like @swyx

@hwchase17 @LangChainAI

Outside Lands is Silicon Valley’s hottest music festival.

But something huge just happened.

Artists, musicians, and engineers from all over the world are here to show what’s possible at the cutting edge of AI and music

Live tweeting the demos from the @OutsideLLMs hackathon🧵: 1/ Spacial Gen

Digital concert experiences

Artist deploys an AR experience through an NFT and the listener is guided to a geofenced experience area https://t.co/Amv1suM24ctwitter.com/i/web/status/1…

Every week, SF’s top AI engineers and startup founders meet up and show what’s new in AI.

No pitches. No grifting. Just code.

Here’s what some of SF’s best hackers are up to this week at @cerebral_valley 🧵 1/ Insight AI

Trying to validate an idea? Just pick your topic and ideal customer persona, and generate user interviews surveys automatically

Mom test in a box
@prasann_pandya https://t.co/oicG2RHUustwitter.com/i/web/status/1…

OpenAI has new competition.

And it’s name is Claude.

Live tweeting the finalists of the first ever @AnthropicAI Hackathon at @cerebral_valley

Meet the best of the 200+ hackers demonstrating what’s now possible with 100k context windows (1/n):

1/ Mythbusters AI

Plugging in Claude with RAG fact checkers to identified confabulations (aka lies) during presidential debates

@pascalwieler @ryboticc @tonyadastra https://t.co/1Bff1fsXqytwitter.com/i/web/status/1…

SF’s most talented:
-AI researchers
-data scientists
-software engineers

All came to a mansion see what’s possible with AI agents.

This stuff is insane.

Live tweeting the demos from the AI Agents hackathon at
@agihouse_org w/ @Wing_VC @MultiON_AI 🧵: 1/

High Flyers

There are 90+ airlines with loyalty programs. It’s a huge pain in the neck to register for their frequent flyer programs

We built an agent that goes to all of them and automatically creates accounts for you using
@multi_on

feat. Me and
@thymeshirl94824
:)

The #NobelPrize in economics was just awarded to 3 top economists. #EconTwitter seems to be over it, but the data science/ML community is totally missing out!

Here's why Data Scientists should start paying attention and what they can take away 🧵 The prize was awarded to David Card, @metrics52, and Guido Imbens for their monumental contributions to statistical methodology and causal inference.

They used and developed strategies that were a true paradigm shift bridging the gap between data and causation in economics

Big tech teams win because they have the best ML Ops. These teams
- Deploy models at 10x speed
- Spend more time on data science, less on engineering
- Reuse rather than rebuild features

How do they do it? An architecture called a Feature Store. Here's how it works
🧵 1/n In almost every ML/data science project, your team will spend 90-95% of the time building data cleaning scripts and pipelines

Data scientists rarely get to put their skills to work because they spend most of their time outside of modeling