
ceo+cofounder @nottecore me: https://xitter.cf/t.co/hZ2gHl51BB
Joined March 2024
- Tweets826
- Following907
- Followers1.9K
- Likes2.7K
Heard Lyft drivers complaining they get like $16 for a $40 ride
How hard would it be to collectively build an opensource car sharing app paying drivers 50% more and charges riders 40% less in SF?
ish $25 ride $24 for driver and $1 for service costs (prolly costs are more expensive idk)
We forked BELL and plugged @nottecore browsers
Same personal agents builder. Same iMessage flow. Same Link checkout. Up to 12x cheaper and 8x faster browser sessions for your agents 🖤
Introducing BELL, the complete OSS stack to build your own personal assistant.
@browserbase for browser infra
@eve by Vercel for harness
@thelinqapp for iMessage
@link by Stripe for payments
We're giving it $10,000 to make agentic payments, join the stream to spend our money.
BELL is an open source stack to build your own personal assistant: text it on iMessage, it browses the web and buys things for you.
→ Eve by Vercel runs the agent
→ Linq handles iMessage
→ Link by Stripe handles payments
→ Notte now powers every browser session
→ Stagehand drives the browser pages
An assistant that browses all day shouldn't cost more than you do.
→ $0.01 per browser hour
→ benchmarks on browserarena.ai
→ fork it: github.com/nottelabs/bellsta…
AP retweeted
Replying to @Suhail
I’ve heard several OAI people say there are unfixable bugs in hardware that are exploitable by AI models directly speaking machine code so even if we could solve software that’s not enough. We need defense to move faster than offense if that’s even possible we may just have a new normal that requires adapting to insecure software (bank transfers require going into a branch and taking a dna test 🤣😬)
AP retweeted
Very excited to be part of the @e2b ecosystem ‼️
Two new integrations landed in the E2B Cookbook this week: @veris_ai and @nottecore.
1. Veris
Use Veris with E2B to simulate any system your agent needs to work with, so it can test its work in a stateful and consistent twin of your production environment.
Agents can claim they did things they didn’t. In the cookbook example, the agent creates a Stripe customer in the simulation, and Veris’s receipt confirms the API call actually happened.
Cookbook: github.com/e2b-dev/e2b-cookb…
2. Notte
Use Notte with E2B to give your agents a real browser that can get past bot checks, while the sandbox stays lightweight.
Real sites check for bots, ask for captchas, and want you signed in. Notte handles all three with stealth, residential proxies, captcha solving, and saved logins, so your sandbox stays focused on the agent's code.
Your agent drives the browser from its E2B sandbox with a few CLI commands, and you can watch every session live or step in when it gets stuck.
In the cookbook example, an agent serves an app from its E2B sandbox, then a Notte browser opens it, adds a to-do, and confirms the result.
Cookbook: github.com/e2b-dev/e2b-cookb…
Docs: docs.notte.cc/integrations/e…
Deel released Pangaea "built purposefully towards payroll tasks" that is faster and cheaper than frontier but considerably worse on their own bench. Weird flex for a model specialized on stuff that sounds "critical"
AP retweeted
We shipped 50+ integrations this week.
Claude Agent SDK, 1Password, Pipedream, Replit, E2B, Daytona, Temporal, Stripe, and many more.
All with Notte cloud browsers.
Can we plug @nottecore to @greptile to have our webapps reviewed by an agent like a human integration test?
689 PRs were merged across @nottecore and subrepos since Monday 00:01 as of Friday 18:45. Leaving out the @dependabot bumps, people and agents merged 666 👺














