Founder @Coyotiv, CTO @openservai Software architect, leader, lecturer, public speaker, mentor, entrepreneur, electronics engineer, guitarist, singer.
Berlin, Germany
Joined February 2009
- Tweets12.5K
- Following566
- Followers9.2K
- Likes5K
Pinned Tweet
It’s been 15 years since I last wrote an academic paper and I didn't expect the next to be this fundamental.
Today we published a research paper with @openservai that represents a major breakthrough in how we think about AI reasoning.
For years, we’ve been told that better AI reasoning means bigger models, longer chains of thought, and higher costs. We accepted that trade-off almost by default.
This work questions that assumption.
With BRAID's structured, bounded reasoning, we’re seeing up to 74× efficiency gains and ~30× better performance per dollar without losing accuracy.
The first SERV hackathon got me really excited about what builders can do with our tech. Can’t wait for round two with our new track partners.
More crypto and agentic AI builders means new use cases and feedback on the SERV developer experience. That’s how we make SERV better.
Introducing SERV Hackathon 02 track partners:
@dphnAI @GoKiteAI @reppo
From inference and agentic payments to AI data markets, add SERV to your AI stack and build more reliable agents at lower cost.
Hackathon info drops next week.
Build with SERV: openserv.ai
Very excited to introduce Graph Sharding, one of the biggest architectural advancements we've built into SERV Reasoning v3.
The industry is only now moving from loops to graphs and at @openservai we've spent over two years engineering what comes next in the AI industry.
Graph agents alone won’t make an agent production-ready. Enterprises need bounded execution, predictable costs, verification, and the ability to audit every decision. That's where existing agent architectures still fall short.
With Graph Sharding, we're taking this further by separating execution into deterministic Script nodes, Jev-powered Decision nodes, and Agent nodes where LLM judgment is actually required.
The difficult part is knowing where those boundaries belong. We've learned that through thousands of real requests and production deployments. This isn't something you can replicate by adding a graph or retry loop to an existing framework.
We're building something I haven't seen elsewhere: a reasoning engine that can structure, execute, verify, and audit complex agent workflows while optimizing how computation happens at every step.
This is the foundation for SERV Reasoning v3's evolution into a complete suite for building and managing enterprise agent systems.
I believe this puts SERV in a category of its own, and positions us to lead the next generation of autonomous work.
Graph Sharding beta is coming soon.
I've been doing demos of the upcoming Graph Sharding lately, and every time I try, I'm in love again. This is the future and it's right now with OpenServ.
SERV Reasoning delivers frontier-level performance with smaller models, at a fraction of the cost.
v3 takes SERV further with agent graphs, inspectable reasoning, and near-zero-cost decisions.
@open_founder presenting SERV at gm AI v2 in Singapore ↓
ESP-Mosaico is launching today! It's a tiny, modular, composable board with a camera and a gorgeous screen. I had the privilege to build some very cool and open source demos with it, including dual amp NAM A2 guitar FX.
youtube.com/watch?v=x-ubJL2b…
#ESPMosaico #Espressif #ProductHunt
Join the chat on ProductHunt:
producthunt.com/products/esp…
Disclosure: Espressif sent me the units for the review but my views are my own and they had no say on the content.
Armagan Amcalar retweeted
Pay with ethereum:0x40e3d1a4b2c47d9aa61261f5606136ef73e28042 is live.
Builders and enterprises can now use the SERV token to purchase SERV Reasoning API credits at a 15% discount compared to traditional payment methods.
75% of SERV received through payments will be burned, with the remaining 25% allocated to the treasury.
This marks another step in expanding SERV's utility as the native currency of the SERV ecosystem, with more use cases to come as we bring new products and services to market.
Coinbase MCP is expanding its agentic trading capabilities pretty quickly.
As more financial instruments become accessible to agents, the interesting challenge is making sure their reasoning can keep up with what they're able to execute.
For trading agents, that means consistently respecting the user's mandate, from position limits and spend caps to allowlists and hard risk controls, while deciding whether to execute, resize, hold, or escalate a trade.
We've been researching this at @openservai using Coinbase for Agents tools, benchmarking policy adherence across 13 models and 173 trading scenarios. Adding SERV Reasoning improved results across all 13 models.
Full benchmark here: coinbase.openserv.ai
Does Apple have a hide switch or sth on current Apple TV remotes? The new one got announced today with Find My and my remote got lost... for the first time in 12 years. Coincidence? I think not.
PromptGuard, the first of its kind, the best among its competitors, is a feature that will make or break a business.
last week stats on servpit powered by @openservai
we’re still calling even after the noise is down
• 8,220 rounds played in 22.5 days, at least
58 rounds reasoned, 25 drawn from what it learned
• 2,131 SERV requests, $10.95 spent (SERV console, last 30 days) as opposed to spending probably x1000 more
• 2,082 requests screened by Prompt Guard, 469 blocked
• about $0.12 per reasoned round (console)
• 9,057 transactions on chain
• 6,272 rounds settled on chain
• 8,502 entries
• 338 payouts
• 173,696 chips moved
• 84,958 chips paid out to winners
• 0.001274 ETH gas spent in total
• 200 of 200 rounds on file reconciled, none failed
• 670 chips, biggest pot on file
• 1,920 chips, biggest payout
• 108 loans from Marrow, 1,115 chips lent, 1,136 written off, 64 seized
• 31,958 agents wrecked
• hero cupcake: 131 wins in 3,153 rounds, 3,038 kills, longest run 9
• 4,402 kills across 3 claimed fighters
• 15 handles claimed, 35 rounds called in full, 17 right
• 18 rounds started by the lever
this is proof even game tech can SERV.
At @openservai, we've been building SERV Reasoning around the idea that you don't need the biggest, most expensive models to get reliable results on complex tasks.
Coinbase's recent results are a pretty good validation of that direction. Smaller models, fine-tuned for specific tasks, can outperform frontier models while being faster and cheaper to run.
In SERV v4, we are taking SERV Reasoning further with specialized, fine-tuned models tailored to enterprise customers and their specific workflows, right inside Graph Sharding, automated, training a model that you own on your own production data.
The goal is to make reliable AI more practical and cost-effective to deploy at scale.
We were able to fine tune an open weight model (Qwen3.5-9B) on proprietary internal data at @coinbase, and it out performed frontier models, at much lower cost and speed, for a specialized task (fraud prevention in this case).
I think we'll see more of this pattern inside companies. The frontier models are amazing generalists. But increasingly you'll see specialist models out perform on more narrow tasks, either working on teams, or by themselves.
We're making it easy to fine tune models internally for our employees. We even have a skill for it in our internal harness that makes it easy to spin these up and start training them:
"/fine-tune-and-serve-llm I want to fine-tune Qwen for payments risk review. help me get started"
I imagine we'll have some backend services that could be replaced entirely by this new architecture.
It's been 0 days since you could debug Mac and iOS apps like this. Meet MacInspector, the debugger you have been waiting for. Works for both SwiftUI and AppKit/UIKit. It's free and open source.
github.com/dashersw/macinspe…
Enterprise adoption doesn't come without enterprise readiness, and that requires use cases and data. Neol and OpenServ are creating wonders together. We move ahead, full force.
We’re building SERV to become core infrastructure for Enterprise AI.
Our early work with Neol gave us a major advantage in building toward our vision.
We had the opportunity to develop SERV against live production workloads across companies and governments, including the UAE government, while establishing a growing footprint across the Middle East.
That meant access to real-world data and learnings that no theoretical framework or whitepaper could provide.
These learnings shaped v1 and v2 of SERV Reasoning, moving our technology from a theoretical framework to a real-world use case, which now feeds directly into SERV v3 and Graph Sharding, the next stage of the reasoning engine.
Neol runs network intelligence for governments and institutions, where agents surface real people for high-stakes decisions. In these environments, “usually right” isn’t good enough. The reasoning needs to be reliable, reproducible, and auditable.
On one of Neol’s production agents, the same evaluation was run 2,400 times:
- Prompt-engineered stack: 54.1% reliability
- SERV research applied directly: 63.1%
- Full SERV Reasoning methodology: 100% across every category
SERV moved the workload from open-ended reasoning into structured decision graphs, then applied learnings from production, including subgraph decomposition and binary judgments, to make the reasoning more deterministic and testable.
Higher reliability was only one part of the result. Neol gained an inspectable reasoning structure where results can be traced back to specific decisions, making the system easier to test, improve, and defend when challenged.
Our vision is to make SERV the reasoning layer enterprises and institutions rely on to run AI at scale. Neol is an early proof point of this journey.
Just use SERV.
the possibilities are endless with @openservai reasoning
this is what serv can do for you, and for your system.
if you’re building a game, don’t just use npcs that runs on predetermined code, give them a soul, give them something to serv….
If you would like to compile your Node.js apps to C++ and benefit from huge speed gains and memory reduction, GeaStack is unbeaten. Compliant, fast, and growing even faster.
Congrats on the release! 🎉
We tried scriptc 0.2.3 alongside GeaStack and Node.js on 26 matching compute benchmarks. Results below 👇
More details: geastack.com/blog-scriptc-0-…
Hey @finkd, we put your charm in a tiny box.
We were amused when @finkd showed off the Muse Charm at Meta Connect, so we're releasing two projects we've been building for fun to push our compiler.
GeaStack brings web technologies to tiny devices.
Today: talking AI avatars and voice agents on a 2" ESP32 screen 🧵
This is a huge unlock for the game industry. Building games that run natively on devices people actually play games on, like mobile devices and XBox, especially with AI, is now a breeze. A true revolution for game builders. Get in touch with us if you think this is a great fit for you.
Remember we got @threejs running on Xbox?
Write your game with Three.js → compile it to native C++ → run the same codebase on Xbox, macOS, and the web.
And now, the source code is available ↓
github.com/geastack/skytail
This was a fascinating hackathon! Lots and lots of quality submissions, and it took us quite some time to debate and decide. Thank you to all the builders for extending the SERV ecosystem, and showing what the reasoning engine is truly capable of.
The feedback we received was nothing but positive to "I can't believe how good this is", and that really makes me proud.
For agentic economy to happen, we need autonomous exchanges, and the first thing to pay for is knowledge. The submission from @thenameisMufasa tackles exactly this.
Tender gives an agent its own budget to buy information. It uses SERV Reasoning to decide whether it needs more data or already has enough to act.
A novel use case for SERV: giving autonomous agents better reasoning around when spending more resources is actually worth it.
AI agents need data. But data is locked behind subscriptions, API keys and accounts.
So I built Tender an agent that pays for exactly the data it needs. Not a cent more.
Built with @openservai #SERV Reasoning and @coinbase agentKit
Ask a question with a budget
Tender reads a seller's free price list and buys only the data that can answer it, $0.001 for a quote, $0.01 for 30-day metrics, $0.05 for a deep report.
Pays per request over x402
USDC through an @CoinbaseDev AgentKit wallet on Base. No subscriptions. No API keys. No accounts.
Model proposes, code decides
#SERV Reasoning picks what's worth buying.
A budget guard in code checks the seller's real price, a hard budget and a trusted seller before anything is signed.
A greedy model gets blocked, live.
Every run ends with a receipt
What it bought, why, what got blocked, and a BaseScan link for every payment.
Demo: tender-henna.vercel.app/
Repo: github.com/Odera067/Tender
#x402 #AgentKit #BuildOnBase #BuildonSERV