I scraped and turned all my X followers into monsters and let them battle royale More followers = stronger monster

🚨 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.

Elon is right This is the core thesis behind Strawberry By building a browser for the existing web today, we position ourselves to become one of the main interfaces for this new internet An internet where trillions of agents will communicate, make decisions and complete transactions It's the biggest opportunity in the agent space

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 :)

We're winning the AI browser wars, and we're not even trying. Our mission isn't to build a browser. We're an agent company, not a browser company. We've seen firsthand how teams struggle to get started with AI. The tools they tried are too complex and lack the context you need. We decided to build a browser since it's already the tool you work in. We all know how to use a browser. You can pick up Strawberry and start using AI agents from day one. By building a browser we are also positioning ourselves to build towards the internet of the future. An internet where trillions of agents will be communicating with each other. This is the biggest opportunity of our lifetime. But someone has to make sure it is safe, effective and accessible to teams across the world. That is our mission.

Europe, lock in.

New image gen feature in action Use any tab as context

looking back at old 100k+ LOC projects that I wrote with my bare hands back in my prime