Building Wolffish — a desktop AI agent that runs entirely on your machine. 100% local & private. Open source. No server. No CLI. No subscriptions. No lock-in.
🐟 People of the world... can you hear me? I am Wolffish...
This is Younes and today, I launch Wolffish. 🚀
Every personal AI agent I tried let me down. A black-box CLI. A server with exposed ports. A 30-minute setup before you could even say hello. Some needed a course just to use them. 😡
I wanted the opposite... So I built Wolffish around three core principles:
⚡️Easy to use.
🧱Easy to extend.
💡Easy to understand.
No server. No CLI. No TUIs. No Docker. A private AI agent that lives on YOUR machine — runs your commands, manages your files, searches the web, remembers everything.
Your data never leaves your computer.
My bet: next year, everyone runs a personal AI agent the way they run a browser today — except this one matters more. It's not just your window to the internet, it's the thing acting on your behalf.
And the one people will want is like Wolffish: fully open source, simple, works, model-agnostic, fully private, fully local. Yours.
My commitment: to build the friendliest, most robust personal AI agent ever made. And I'm just getting started.
Live now: https://t.co/HNTc4Ps37S
Code: https://t.co/yFfPFAukoQ
Claude Opus 5 one-shotted this game.
EVERYTHING you see in this demo is custom code... not a single external asset was used.
AI games are going to be amazing.
(sound on)
For my first post, I’m sharing a letter @NVIDIA signed on why open models matter.
AI will transform every industry, power every company, and be built by every country.
Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty.
The world needs both frontier closed models and frontier open models.
https://t.co/AUKzoQ5Ikb
AI is moving into the physical world.
We're excited about a new wave of startups rebuilding the systems that power the real world, from education and healthcare to defense, finance, infrastructure, and work itself.
https://t.co/QCIz6DnQnN
Wolffish daily news brief knows all about me and let me know which news matter and why. It even knows this new MCP update is very relevant to Wolffish itself.
You can’t have smooth context like that on Cloud AI.
I wanted to help a medical doctor friend yesterday to create a project based on a 300MB 3k pages book so he can easily study the HUGE book
ChatGPT: Uploading... few minutes later, "ERROR: SOMETHING WENT WRONG". Upload gets canceled and removed silently.
Claude: Uploading... instantly, "UPLOAD REJECTED".
I just realized you cannot have Claude or ChatGPT help you with big PDF files.
Wolffish: Uploads instantly, ask any questions on PDF. No big deal.
The future of personal AI is local first. The work happens on your machine. The model is just an API layer on top. No need to upload 1GB file no provider will accept.
I didn't realized how important it is to have a local-first personal AI that can help you with anything even HUGE files.
Need help with 1GB pdf? Sure! No errors or rejections or even loading.
Everyone gets angry with me for saying triple, triple, double, double is dead.
Fine, I do not really care. Venture is about investing in unbelievable outliers. Anomalies that own markets with generational founders.
@FireworksAI_HQ is an example of this.
They scaled to $1BN in ARR in just 3.5 years.
They also have just 200 employees making it an insane $5M revenue per head.
@lqiao just raised a whopping $1.5BN at a $17BN valuation and I sat down with her. Added my notes and the episode below:
1. The Challenges That Come From Such a Fast Development Cycle for Chips
Hardware innovation is moving so quickly that rapid SKU cycles now outpace traditional depreciation timelines, changing the financial calculus of building versus renting infrastructure. Founders should prioritize growth and market agility over immediate gross margins, avoiding premature optimization until customer workloads stabilize.
2. Why National Sovereignty Is Real in AI and Every Company Should Have Its Own Model
Frontier models function like a society’s core electricity grid. Relying entirely on a third-party API creates the existential risk of sudden disconnection, making model ownership and infrastructure independence critical for both sovereign nations and enterprise businesses.
3. Why the Future Is Millions of Specialized Models
Frontier providers bake their own design tastes and values into models, which inevitably misaligns with enterprise business logic. The future belongs to millions of specialized, “one-size-fits-one” models tailored to proprietary data, consistently outperforming generalized AGI on accuracy, speed, and unit economics.
4. The Transition From the Year of Coding to the Year of Co-Work
AI adoption has rapidly evolved from engineering-centric coding tools to a diversified ecosystem of B2B co-work agents. Founders and VCs must look past crowded developer environments to capture massive value in specialized workflow automation across legal, finance, healthcare, and other enterprise functions.
5. How a 10x Cost Reduction Will Drive a 100x Explosion in Usage
Temporary supply chain backlogs will eventually ease, compressing infrastructure and model-tuning costs by 10x over the next three years. This deflation in token unit economics will turn intelligence into a near-frictionless commodity, driving a massive surge in enterprise production usage.
6. Why Avoiding the Application Layer Is Essential for Platform Focus
Platform defensibility requires strict focus on multi-chip agility without creating vertical hardware or software dependencies. By refusing to move up into the application layer, infrastructure platforms avoid competing with their own ecosystem and maximize their value in specialized model orchestration.
7. Biggest Lesson From Working With Jensen Huang on Leadership
Leadership in hyper-velocity markets is defined by rapid judgment, not executive privilege. Because critical information degrades as it moves through layers of corporate hierarchy, leaders must stay close to ground-level technical details to maintain execution speed and avoid flawed strategic calls.
@bridgemindai You cannot ban an open weights model. You can try to ban the inference API but that’s near impossible. You would be banning DNS domains. Good luck with that.
I bring you along for the chaos of running 13 startups solo 😵💫
☠️ Launching @shipordie_ with @jackfriks
🔎 Pre launching a new SaaS https://t.co/sByPTnK4u4
🤩 Meeting with 100+ founders in Korea
💦 Running & calisthenics routine
🥦 Superfood diet
💍 My w̶i̶f̶e̶ farmer's wisdom