Strawberry (@strawberry) header
Strawberry (@strawberry) profile picture

AI that works alongside you. Strawberry is a browser with built-in AI agents that understand your context, tools and team. Now in beta

Stockholm
Joined July 2024
Photo by Strawberry (@strawberry)Photo by Strawberry (@strawberry)Photo by Strawberry (@strawberry)Photo by Strawberry (@strawberry)Photo by Strawberry (@strawberry)Photo by Strawberry (@strawberry)Photo by Strawberry (@strawberry)Photo by Strawberry (@strawberry)Photo by Strawberry (@strawberry)Photo by Strawberry (@strawberry)
Strawberry is a game-changer for creating content and making better posts. Just tell Strawberry your vision and it will draft posts, generate images, videos, carousels, etc. All in your tone, brand and style. Try for free: strawberrybrowser.com
8
9
1
38
2,953
Strawberry lets you run AI agents around the clock. Describe a workflow once, and your agent runs it every day, every week, or the moment something happens in your apps, like a new email landing in your inbox. We call these Routines
22
1
37
1,126
Some we run ourselves: ▶ Finding warm leads on social media based on who interacted with our posts ▶ Summarising relevant industry news and competitor moves every morning ▶ Keeping our inboxes clean from junk with important emails marked as high priority Setting one up takes one sentence.
2
2
210
My dad is 61 years old and has AI agents working for him 24/7 Strawberry makes running powerful AI agents more accessible than ever, even if you are non-technical You now have no excuse not to start adopting agents 😭 Try for free: strawberrybrowser.com
13
5
71
3,269
The companions got a massive upgrade in version 1.0 🥳 Let's see how yours look! We'll hand out some credits to cool looking ones in the comments! 👇
12
2
1
33
3,334
GPT-6.1 Terra is now available in Strawberry 1.0. It feels amazing. Fast. Smart. Cheap. Try it now.
GPT-6.1 Terra: delivering fast and capable computer use at a lower price. GPT-6.1 Terra understands what’s on screen, takes action across apps, writes naturally, and is a more capable model for your whole workday with the efficiency to take on more of it.
18
7
1
66
9,241
Delete Chrome Delete Granola Delete Claude Strawberry 1.0 is here, the AI browser that saves your team >100h/week
345
290
230
4,504
2,353,773
Arc made browsers interesting again. Whatever browser you use today, there’s a good chance you expect more from it because of Arc. Respect to the team for pushing things forward. o7
🤖 Made with AI
We've decided to sunset Arc on December 22, 2026. That's not an easy sentence to write. We spent years building Arc and celebrating each and every release along the way: we have so much pride and love for what we made alongside the Arc community. Our priority is to deliver best-in-class security for our members. Keeping a browser secure takes constant, dedicated work that is only increasing in the age of AI. Dia was built from the ground up to meet today’s security standards, so that's where our engineering and security teams will focus moving forward. We've worked to make switching to @diabrowser as easy as possible for Arc members. Here's how: · Your passwords, bookmarks, extensions and history come over to Dia seamlessly. · Spaces, Folders, and Tab Groups are in Dia and import over with your data intact. · Dia now surpasses Arc benchmarks in stability, speed, and security. · The browser features you use in Arc are free in Dia, and the AI is optional. Thank you for using Arc, for pushing us to make it better, and for building alongside us. The team that made Arc is the same team behind Dia, and some of our most ambitious work is just ahead. We'd love for you to be there with us when it lands.
19
2
46
1,858
I scraped and turned all my X followers into monsters and let them battle royale More followers = stronger monster
8
5
68
2,790
Sooo, when's Barry's first day on the job?
1
11
27
4,775
🚨 New 3D models for our AI agents - Handmade in Blender - 3D, look 2D-ish with cel shading - Fully customisable (see first comment) Every AI agent deserves a look of its own.
13
4
2
35
4,410
Laurits is 19: He automated 80% of our customer support with agents Entire playbook in the first comment
4
2
1
19
2,822
What happened with @browsercompany? They were so careful about details, and now it's just junk. This bug has lasted for months.
3
1
28
4,441
Some of you have experienced outages and other issues over the past few days. We’re sorry for the disruption. The issues followed major upgrades to the foundations behind chats, cloud sync and using Strawberry across devices. Most are now under control, and we expect Strawberry to be fully stable by the end of this week or early next week. If you’re experiencing a concrete issue, email [email protected]. We’ll look into it and try to resolve it quickly.
3
21
2,870
Build in public, Day 1 V1 of new companion models What do you think?
18
1
1
42
4,101
We just cut Strawberry’s credit use by 70%. Update Strawberry. Your current plan should now last at least twice as long! So, how did Arian and the agent team do it? Three main things: 1️⃣ We reduced edge-case cache misses Prompt caching lets devs reuse parts of a prompt instead of paying to process the same instructions and context again. A complex agent harness creates a large surface area for cache misses. Adding/removing tools, dynamically changes to prompts, memory updates, etc. can all invalidate cached prompts. These edge cases are very hard to discover in in-house evals, so we improved our anonymous telemetry around real-world cache behaviour. We found many common miss patterns, and patched them. With a nice Dash0 dashboard, it is now easy to see which situations cause cache misses. If you are building agents and not measuring cache hit rates, you have to look into this. 2️⃣ We switched our base model to GPT-5.6 Terra In our evals, Terra gives us Opus 4.8-level performance at roughly half the model cost. Its tokenizer is also much more efficient. For the average Strawberry prompt, Terra uses roughly half as many input tokens as Anthropic’s models. Your Strawberry agents now use cheaper input tokens, and fewer of them. 3️⃣ We made our agent harness more context-efficient Agent harnesses can accumulate absurd amounts of input context. Reading a 1,000-row sheet in full can push more than 100,000 input tokens into a single prompt. Our new harness limits large tool results, preserves the useful parts, and lets the agent surgically fetch more context when needed. We improved memory search using the same principle. Strawberry's memory system can contain thousands of memory files covering candidates, meetings, customer interviews, and much more. We now give the agent a better overview of the file tree, helping it search effectively and open only the relevant files. Most agent cost problems are context-engineering problems. Happy Monday :)
21
5
1
69
5,342