Asim Shrestha
@asimdotshrestha
Followers
12,030
Following
730
Media
88
Statuses
428
Cofounder, @ReworkdAI YC S23. Working on multi-modal agents
San Francisco
Joined December 2016
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
Bridgerton
• 418173 Tweets
Colin
• 126727 Tweets
billie
• 97405 Tweets
Penelope
• 81361 Tweets
Xavi
• 61449 Tweets
Bobby
• 51302 Tweets
つばさの党
• 46045 Tweets
Gabigol
• 44367 Tweets
La Modelo
• 40661 Tweets
Botafogo
• 39755 Tweets
Fever
• 35016 Tweets
Marcelo
• 31509 Tweets
Cerro
• 29835 Tweets
iMessage
• 27671 Tweets
優三さん
• 19267 Tweets
ひーくん
• 19056 Tweets
SIEMPRE QUE LO BESO
• 17488 Tweets
#MAZZEL
• 14028 Tweets
代表ら逮捕
• 11681 Tweets
#911onABC
• 11629 Tweets
#あさイチ
• 11593 Tweets
Another night of merging straight to main
Not a real CTO until you raw dog the prod db at 12:00AM
19
20
487
18
19
962
Not a real CTO until you raw dog the prod db at 12:00AM
19
20
487
The
#AgentGPT
team and I are launching our Beta V2.0 🌟
Its been so awesome to see all of the community support, we've recently just surpassed 15k stars on GitHub.
20
30
241
#AgentGPT
just hit 10,000 stars 🌟
Its been a wild ride this week watching all of our metrics double nearly every day. We've been hard at work with the following:
- Scaling our infra to 100k DAU without breaking our bank
- Local OpenAI account runs
- UI improvements like a view
29
19
190
Find the repo for all of this here:
6
23
173
Built using
@nextjs
with the
@t3dotgg
stack,
@LangChainAI
,
#GPT3
and
Established from ideas by
#BabyAGI
from
@yoheinakajima
and
#AutoGPT
from
@SigGravitas
5
7
146
Appreciate everyone checking this out! So sick just watching the metrics go up
9
3
119
It works through using models to generate a task list and then iteratively executes tasks, evaluating whether or not tasks are completed or require further sub-actions.
In the future, we'll have long term memory via
@pinecone
and give models the ability to query the web
10
4
115
Super excited to announce
@ReworkdAI
has raised a $1.25M pre-seed ⚡️
We're incredibly lucky to be backed by both
@ycombinator
and
@PanacheVC
in this round
20
6
116
⚡️ Chat with your AI Agents with
@LangChainAI
and
#AgentGPT
in our v0.9.5 release!
Guide agents by transforming and updating results at any point of execution. Heres an example of chatting against an agent that created a travel itinerary ✈️
6
13
98
⚡️
@perplexity_ai
has some of the smoothest text streaming out of all LLM apps
As a weekend hack, I recreated it with the
@vercel
AI SDK and
@nextjs
. Try it for free with
#GPT4
at
7
13
98
Of course its a bit limited in terms of capability at the moment but we're working to metaphorically give AgentGPT arms / legs / and eyes.
You'll soon be able to browse the web, deploy software, and so much more
5
3
82
#AgentGPT
recently hit 20k stars on GitHub 🚀
Its been an incredible ride watching this project grow. A big shoutout to everyone that's helped contribute the past few weeks
14
3
82
#AgentGPT
just got tool support in our beta 0.5.0 release 🚀
Watch as your agents search the web 🌐, generate images 🎨, and write code 💻
Heres a demo of an agent attempting to design a platformer game 🎮
9
11
79
Super exited to share we're joining AI Grant's third batch! 🎉
12
1
68
Real time streaming in
#AgentGPT
's beta 0.6.0 🙏
Watch your agents thought process take place in realtime at ⌨️
3
13
60
Wow, analytics sky rocketed overnight 🚀🤯, welcome everyone checking in!
2
3
53
My welcome to YC moment was doing an informal talk during the batch retreat and seeing none other than
@garrytan
himself listening in the audience
Just the other day he did an interview with
@lulumeservey
and talked about our story
4
5
55
#AgentGPT
just hit 20,000 members on our Discord channel ⭐
With this, we're launching Beta 0.4.0 of the platform! Check out the full release notes here:
6
10
56
Update: We're hitting scale limits on both Vercel and OpenAI. We've just added the ability to use your own API key on the platform. Unfortunately, this will be a requirement just until we can get scaling sorted out!
10
1
53
Really excited to see where this goes, shoutout to the folks that helped build this
@SrijanSubedii
and Adam@
1
1
49
⚡️ AI agents supercharged with your data ⚡️
Introducing Vector databases with
#AgentGPT
's Beta 0.7.0 release thanks to
@LangChainAI
. Currently using
@weaviate_io
by default but we're exploring providers!
1
11
48
@OpenAI
bill thus far, thank god they made gpt-3-turbo 10x cheaper. Wonder what the bill would look like for gpt-4
7
2
43
Been a while but excited to show off a small AgentGPT 1.0 update ✨
Features:
- A freshly redesigned theme 🚀
- Updated agent handling with a focus on search 🌍
-
@try_sid
for personalized context and queries 🦥
- Increased usage limits 📈
Try it at
4
5
42
When we first launched AgentGPT, I had to beg
@OpenAI
to raise our rate limits everyday to meet increasing demands
They eventually got us to shut up by giving us an absurd limit 😂
4
0
40
Feedback has been immensely positive, thank you to everyone that's reached out ♥ Now that we've alleviated our infra worries, our team will be focusing on the following in the coming weeks:
- Web browsing
- Connection to productivity tools
- Multi agent support
- User accounts
3
1
34
Not gonna lie, ended up subscribing to Twitter blue in hopes of increasing outreach. Twitter has ended up being the best referrer by far, cheers
@elonmusk
2
1
31
If you'd like to help contribute, discuss plans / features, or would otherwise just like to stay up to date with progress, head over to our discord server @
1
4
27
Before / after of my girlfriend visiting for a week ✨
1
1
29
Also actively looking for contributors to the project:
Added a bunch of tickets for whoever wants to get started, your help is very much appreciated
4
5
27
So dope getting support from Vercel
New AI templates available on Vercel:
◆ AgentGPT with Langchain:
◆ OpenAI Doc Search:
◆ AI Code Translator:
◆ Chatbot UI:
5
43
257
8
2
26
Currently investigating issues where the agent gets stuck thinking, added a note to restart if its taking to long
3
2
26
Quick break from our questionable development practices
0
1
25
Among the features is the ability to save and share runs (that have concluded), here's an example:
AgentGPT 🤖
Assemble, configure, and deploy autonomous AI Agents in your browser.
agentgpt.reworkd.ai
2
2
23
Excited to share the start of Bananalyzer 🍌
A simple first start to our AI Agent evaluation library for web tasks. We're aiming for a rich suite of repeatable web tests for any agent.
Read more here:
4
5
23
Welp pretty much hit the OpenAI limit 😅 Using a key from a new account now to serve the traffic
1
1
19
Had a blast speaking at the
@github
office last night for the Microsoft YC kickoff
Shoutout
@bwinterrose
for inviting us out 🔥
2
1
19
WLB ✅
sometimes after a late night grind sesh, standup turns into liedown 😤
0
0
40
1
0
17
Fun times
@MomenticAI
@ReworkdAI
- web data extraction using multi-modal agents. many use-cases including data ingestion, relevant to chroma. seems like their agents work!
1
3
20
2
0
17
😅 Note to self: secure all APIs with GPT4 access
Someone took the golden opportunity to just throw arbitrary calls to the demo's backend
⚡️
@perplexity_ai
has some of the smoothest text streaming out of all LLM apps
As a weekend hack, I recreated it with the
@vercel
AI SDK and
@nextjs
. Try it for free with
#GPT4
at
7
13
98
9
1
16
Finally, we've added some web searching capabilities. This is however in limited preview so expect it to be unavailable, but get a lot better shortly. Here's a sneak peek
2
0
14
@LOFI911
Hey unfortunately just a limitation of OpenAI throttling our server. The project is completely open source so if you want, you can get it running locally (for free) and use your own key.
Our infra bill is projected to be incredibly high so we can't have huge runs on our own key
2
0
14
Announcing
#AgentGPT
's 0.9.0 release with an awesome open source spotlight from
@DecibelVC
and
@chakrabartis
1
0
13
With that being said, we're still proudly open source and you're free to run locally for free! (Though we do need to do some work to fix up local setup)
Heres our GitHub release notes:
3
0
11
Helping onboard a new engineer with dependency issues
A quick google search led me the the answer on GitHub which I apparently wrote last month 😆
1
0
12
We're also launching a pro subscription with access to GPT-4 to finally help cover our OpenAI bill 😅
Use code TWITTER25 for 25% off! (Only available for the first 100 users)
Of course AgentGPT is still very much in beta. We have a lot planned and your support means a lot.
3
0
10
Companies you didn't know were
@ycombinator
a 🧵
1.
@9GAG
👀
They we're founded in 08 and joined YC in S12. A large part of early meme culture- wasted a lot of hours here during high school but feels largely forgotten now
3
1
11
We've also added the ability to pause / resume execution so you don't get lost in the run 🤖
1
0
11
@SagoLabCom
This was actually originally the idea the team and I explored. The space is definitely saturated and we ended up wanting to solve more ambiguous problems that would be hard to map into a structured flow
1
0
9
Big fan of
@shuding_
's globe library
Redid AgentGPT's home page with it last weekend and it looks ✨
1
0
10
@dory111111
@yoheinakajima
@streamlit
Amazing stuff! I recently did something similar but hosted in its own web app
0
0
11
If you want to help us ship fast, we're hiring
0
1
9
@natfriedman
Not looking to raise but we just open sourced our eval library for agents in web tasks:
Very early stage though
0
0
8
Making LLMs return YAML responses is super nice for UX 🙏
Unlike JSON, their intermediate representations are easily parsable during streaming. The same request with JSON would typically force users to wait for the entire duration of the call to complete
2
1
9
@mr_8_bit
24 year old recent-ish grad here. I'd say if you just build cool enough stuff the companies worth pouring your life force into will come to you
Wouldn't focus on LC that much. In terms of prioritization, just depends on what you want to optimize for. Feels like finding balance
2
0
8
@ronawang
While it shouldn’t be looked at as a status symbol, I’d still recommend it to any young first time founders
Valuation at that early a stage (perhaps in general) has no bearing on the success of your company. The mentorship and network effects of YC however can actually make a
0
0
8
The TLDR:
- Fully migrated our backend to
@FastAPI
💻
- Image generation via
@replicatehq
🎨
- Tool support ⚒️
- Subscriptions launched ✨
- Minor visual updates 🔥
1
0
7
@chipro
We're essentially working on no 4.
Systems to extract structured web data at scale with LLMs. We work with companies today to help them collect foundational data for data constrained product offerings
0
0
8
@Suhail
We did. Previously a single user could cost us up to $40 a day if they hit our site's limits but we were ok with just eating the cost
@perplexity_ai
and
@phindsearch
definitely have too
1
0
7
For our full list of changes, check out the release notes below:
1
1
6
If you also want merge access, please apply here ➡️
0
0
6
In San Fran right now - there is an obscene number of "Cracking the coding interview"s on marketplace
1
0
7
@emollick
Hmm this site doesn't seem outside the realm of what AutoGPT could have done last year
2
0
7
Thanks for tuning in! Check out the full release notes on GitHub!
0
0
6
@DYtweetshere
@scale_AI
@evanon0ping
@theappletucker
Congrats on 1st place! I certainly think LLMs are going to completely disrupt the software engineering flow.
Security for a backend as malleable as what's proposed would be a bit concerning though given how much power this gives to agents performing prompt injection.
0
0
6
@Scobleizer
@ycombinator
Perhaps an outlier, we actually owe a lot of our initial traction (and even getting into YC) to twitter
Welcome to YC,
@SrijanSubedii
,
@asimdotshrestha
, and
@ReworkdAI
!
Reworkd AI (YC S23) allows companies to automate core business workflows with the help of AI Agents, all while integrating seamlessly with their existing tech stack.
4
8
52
2
0
6
Finally, mark your calendars because we have a have a big announcement coming in two weeks (and a new product) 🚨
1
0
6
Beyond that, this week has been mostly exploratory. We have a lot planned out now and its all public on our new roadmap page 🚀
Check it out below:
1
0
6
It's still in its early stages - we're starting by using Vector search to filter out repetitive tasks 🗑️
However, you'll soon be able to create agents with context over whatever data you want 🗄️
1
0
5
My girlfriend has something like a 95%+ win rate in scrabble
Because of this, last Christmas I made an app where she could play against the best scrabble player she knows (herself). Try it at
1
2
5
⚡️
@perplexity_ai
has some of the smoothest text streaming out of all LLM apps
As a weekend hack, I recreated it with the
@vercel
AI SDK and
@nextjs
. Try it for free with
#GPT4
at
7
13
98
0
0
5
We're also doing some work on a super secret landing page in the background 🤫 Stay tuned for more 🔥
1
0
5
Why is ChatGPT4 taking like 5 minutes for a basic completion
5
0
5
Finally, the full release notes below
0
1
4