Welcome Hermes' latest verified partner plugin: Adaption AI
Your agent can now train new models, work on data, and more with their tools.
Check it out:
Adaption is now a plugin for @NousResearch's Hermes Agent 🎉
Open-source builders can train a custom model from inside their agent. Generate and prep data. Fine-tune with AutoScientist.
Better intelligence starts where your agents already run.
Valentin Shenfeld retweeted
Hermes mobile app is now available for beta testing on both iOS and Android.
TESTING TIME! 🔥
hermes mobile official testflight
testflight.apple.com/join/U8…
hermes-agent.nousresearch.co…
Valentin Shenfeld retweeted
Hermes Agent now comes preinstalled on rabbitOS
rabbitOS 2.3 is here, with hermes agent 🥕🪽
a fresh OTA is rolling out to r1 now, and this one’s packed: hermes agent, proactive rabbit, openclaw v4, creations gallery 1.5, DLAM BYOK, and more.
here’s what’s new:
🪽 hermes agent on r1
you can now talk to hermes agent by @nousresearch directly from r1 and get things done. simply install the rabbit agent to your computer from rabbithole > nodes and then swipe left on r1 until you reach the hermes page to connect.
🆕 DLAM moves to BYOK (Bring Your Own Key)
DLAM now uses your own Anthropic or OpenAI API key. it remains available at no extra charge from rabbit, with usage handled through your chosen provider. check out the DLAM settings page to choose your provider and model and enter your API key.
💥 openclaw protocol v4
r1 now supports openclaw v4, with the integration rebuilt through rabbit agent for a stronger foundation going forward, including usage outside of your home network.
🖼️ creations gallery 1.5
editor’s picks, popular creations, QR codes, intern session shortcuts, and the full creations gallery — all in one cleaner on-device experience.
✨ proactive rabbit
triple-tap the rabbit on your home screen and r1 will greet you with something helpful, personal, or just a little fun — based on your r1 personality, reminders, journal entries, magic recorder logs, and more.
🟥 what’s new?
a new on-device card lets you see recent OTA updates right from r1.
rabbitOS keeps evolving fast. update your r1 and have a play 🧡🥕
Valentin Shenfeld retweeted
rabbitOS 2.3 is here, with hermes agent 🥕🪽
a fresh OTA is rolling out to r1 now, and this one’s packed: hermes agent, proactive rabbit, openclaw v4, creations gallery 1.5, DLAM BYOK, and more.
here’s what’s new:
🪽 hermes agent on r1
you can now talk to hermes agent by @nousresearch directly from r1 and get things done. simply install the rabbit agent to your computer from rabbithole > nodes and then swipe left on r1 until you reach the hermes page to connect.
🆕 DLAM moves to BYOK (Bring Your Own Key)
DLAM now uses your own Anthropic or OpenAI API key. it remains available at no extra charge from rabbit, with usage handled through your chosen provider. check out the DLAM settings page to choose your provider and model and enter your API key.
💥 openclaw protocol v4
r1 now supports openclaw v4, with the integration rebuilt through rabbit agent for a stronger foundation going forward, including usage outside of your home network.
🖼️ creations gallery 1.5
editor’s picks, popular creations, QR codes, intern session shortcuts, and the full creations gallery — all in one cleaner on-device experience.
✨ proactive rabbit
triple-tap the rabbit on your home screen and r1 will greet you with something helpful, personal, or just a little fun — based on your r1 personality, reminders, journal entries, magic recorder logs, and more.
🟥 what’s new?
a new on-device card lets you see recent OTA updates right from r1.
rabbitOS keeps evolving fast. update your r1 and have a play 🧡🥕
Ex google engineer acaba de soltar un curso completo de 1 hora para construir agentes de IA que se mejoran solos, desde cero:
00:00 – Cómo nace un agente que se construye a sí mismo
03:01 – soul.md: el archivo que lo controla todo
30:16 – RAG inteligente: solo traes 20 mensajes relevantes, no los 2.000
31:48 – El loop que sabe cuándo parar solo
35:14 – Detectar el error y arreglar el prompt en el momento
50:22 – Cómo Claude comprime y optimiza tu memoria automáticamente
1 hora de contenido práctico que vale más que la mayoría de cursos de pago sobre agentes.
Míralo completo, guárdalo📚
Valentin Shenfeld retweeted
Two weeks ago, Ethereum researchers met in Berlin to continue charting the protocol's long-term trajectory, following along discussions with client teams in Svalbard in April.
The updated strawmap is at strawmap.org, and I attached a picture of it to this post.
My own high-level takeaways:
* "Lean Ethereum" is not a single one-shot upgrade, it is a collection of improvements that will come online to the Ethereum network over the course of three or four years. But make no mistake, this IS the third major iteration of Ethereum in the same way that the Merge was the second. Almost every major piece of the protocol will be replaced:
- Verification through recursive STARKs, rather than direct re-execution. Recursive STARKs become an enshrined first-class core component of the protocol
- Replacing everything quantum-vulnerable with quantum-safe alternatives
- Consensus: decoupled available chain and finality, one or two-round finality. Theoretically optimal security properties, simpler than today, and faster than today
- Multidimensional gas
- State: not just tree structure, but what *types* of state are available
- Changes to client architecture
...
At the same time, simplification, cleanup and future-proofing. And this will all be done in a way that minimizes disruption to existing application. We've done this before (the Merge), we can do it again.
* H-star (aka Hegota) is probably Ethereum's last thematically "pre-Lean" fork. Starting from I-star, most of everything we do will have a very strong "Lean" feel to it in one way or another.
* Privacy is no longer an afterthought, it is a first class goal. When designing Frames, the mempool, additions to the state tree, we explicitly ask the question "okay, how do quantum-safe, intermediary-free privacy protocol transactions go through this, and what is the overhead?"
* Formal verification of everything for security.
* FV also makes us much more comfortable with canonicalization (having pieces of the protocol that are directly defined as a piece of bytecode expressed in some language). evm-asm is being written in part to become a canonical proof system for the EVM.
* Quantum safety has shifted up a LOT in priority. This adds a lot of work (eg. finalizing a quantum-safe blobs design has become urgent; this work has already been ongoing for months)
* Probably the single most disruptive part of the plan is the changes to state. There is growing consensus around leaving present-day-style "dynamic state" mostly unchanged, but scaling it only a medium amount, and adding new types of state that are more scalability-friendly (eg. no need for builders to sync/store all of it) but more restrictive, and that will scale a large amount.
eg. possible Ethereum in 2030: 2 TB of present-day-style (dynamic) state, and 100 TB of new-style (scalable but restrictive) state
This "new-style" state would work very well for ERC20s, NFTs, many defi use cases, but not eg. highly "central" objects like Uniswap contracts, or onchain order books, or other complex things (which are crucial for Ethereum but which only take up a small percentage of state)
Hence, it will not be *necessary* to rewrite any apps, but it will be *very cost-effective* to eg. rewrite an ERC20 token into a newer design that uses a new type of UTXO storage that is currently being explored, so that it will have >10x lower txfees.
Design of these new state types (current ideas: keyed nonces, ring buffers, UTXOs, statically accessible state, temp state) is an area where we will need a lot of feedback from application developers (incl. privacy-friendly application developers) and probably several rounds of rethinking and iteration.
* In the context of a much larger total state size, we need to figure out the incentive issues around who stores this state and what motivates them to. Even saying "each node stores 1%" is not good enough - why do they store that 1% and why are they willing to serve it? This is being elevated as a first-class research area.
* Ethereum will need to have a "VM" other than EVM in one form or another - at the very least, we need something like leanISA for recursive STARKs - and the gains are large in exposing it to users so that we support programmable privacy and better scalability. Right now, the most likely contenders are leanISA and RISC-V.
My own ideal is that in this world, we adjust the protocol so that the EVM becomes a high-level-language compiler-level feature, and the protocol only "sees" RISC-V / leanISA directly. But this is still far away.
* Gas limit increases, blob increases and slot time decreases will happen many times over the next ~5 years. We expect a large gas limit increase with Glasterdam. Each step of increased scale or decreased slot time is a matter of getting to the point where it is safe to do it, which comes from a combination of client optimization and protocol changes.
Ethereum is CROPS.
Ethereum is scaling.
Ethereum is reinventing itself.
Onward.
Valentin Shenfeld retweeted
Ready to build automations using @MetaMask Agent Wallet? 🦊
Join us tomorrow for a workshop where we'll walk through Agent Wallet, explore the possibilities, and build a few automations together.
📅 6/25
⏰12:30pm ET
Live on X.
Valentin Shenfeld retweeted
An update: we’re 3xing the rate limits for Gemini models across all paid tiers in Antigravity and resetting everyone’s Gemini quota for the week.
We understand some people hit their rate limits quickly and wanted to respond fast. Lots more to come and enjoy building!
Valentin Shenfeld retweeted
Nearly 23K stars for a collection of markdown files I wrote
I guess they must be pretty good
I want to invest more time in this repo. So, folks who starred it, what can I do to make these skills more obvious to you?
- A docs site for the skills?
- Send them to plugin marketplaces?
Help me help you
github.com/mattpocock/skills
Valentin Shenfeld retweeted
Вчера AI-агент уничтожил производственную базу данных небольшого SaaS-бизнеса. За 9 секунд. Jer Crane, основатель PocketOS, сервиса для компаний по аренде автомобилей. Агент Cursor (на базе Claude Opus) работал в staging-среде, наткнулся на ошибку credentials и сам решил "починить" проблему: удалил Railway-volume одним GraphQL-запросом.
Токен, который он нашёл в случайном файле, был создан для управления доменами. Но Railway не разграничивает права токенов: каждый из них фактически является root-доступом. Никакого подтверждения не потребовалось.
Бэкапы? Они хранились в том же volume и ушли вместе с данными. Последний восстановимый бэкап был трёхмесячной давности. Когда Jer спросил агента, почему он так поступил, тот ответил письменно и перечислил все правила безопасности, которые нарушил: угадывал вместо того, чтобы проверять, выполнил деструктивное действие без запроса, не прочитал документацию перед удалением и не спросил разрешения.
Итог: малый бизнес потерял данные клиентов за три месяца. Люди приходили в субботу забирать арендованные машины и не находили своих записей.
Главный вывод: системные промпты не могут быть единственным слоем защиты. Безопасность должна быть встроена в API, токены и обработчики деструктивных операций, а не в текст, который модель "должна прочитать и соблюдать".
Если вы используете Railway и AI-агенты в проде, сегодня хороший день проверить скоупы токенов и то, где реально хранятся ваши бэкапы
Valentin Shenfeld retweeted
97 new members. 146 total. 1 mission: Open Agentic AI. 🚀
Our members are working together to reduce fragmentation, advance open protocols and shape production-ready standards for agentic AI.
Read the announcement: hubs.la/Q044kjhw0
🦞Calling all openclaw bots, clawdbots, moltbots, and AI agents @moltbook.
We’re running an end-to-end, agent-powered hackathon with a $30,000 USDC prize pool, open until Sunday, Feb 8 at 12:00 PM PST.
Three tracks:
→ Agentic Commerce
→ Best OpenClaw Skill
→ Most Novel Smart Contract
Agents submit projects. Agents vote. USDC moves.
Agents can read the rules and submit projects on m/usdc: moltbook.com/post/b021cdea-d…
Learn more: circle.com/blog/openclaw-usd…
Valentin Shenfeld retweeted
🚀 Upcoming Web3 Devs Underground online session 👇
🔗 RSVP now: luma.com/fbof4ysn
Join us for a live online talk focused on how better data infrastructure enables better payment systems in Web3.
We’ll dive into the role of indexing, data availability, and developer-first tooling in building scalable, reliable, and production-ready payment flows.
🧠 Topics:
• Why data quality matters for Web3 payments
• Indexing infrastructure and real-time payment use cases
• Tradeoffs between performance, reliability, and developer experience
• Lessons from building data systems used in production
🎤 Speaker:
• BrockHaugen — Founder & CEO, @indexingco
💻 Online event
🕕 February 4 | 18:00 IDT
(11:00 EDT | 17:00 CET)
🚀 Presented by Web3 Devs Underground
💡 Powered by MASTERKEY Venture Capital
📅 Subscribe to future events: luma.com/web3devs_undergroun…
🌐 Community site: web3devs.org
ERC-8004 is going live on mainnet soon.
By enabling discovery and portable reputation, ERC-8004 allows AI agents to interact across organizations ensuring credibility travels everywhere.
This unlocks a global market where AI services can interoperate without gatekeepers.
Valentin Shenfeld retweeted
🧵 Tomorrow's technical deep dive: EIP-7702 & MPC with @arik_g (VP Tech @FireblocksHQ)
🔹 How EOAs can act like smart contracts
🔹 MPC for decentralized key security
🔹 Gasless transactions & recovery
🔹 Backward-compatibility advantages
📅 Sept 17, 10:00 EDT | 17:00 IDT
📍 Live on X, YouTube & LinkedIn
For devs building the future of Ethereum accounts.
Register → lu.ma/qp2j08a3
#EIP7702 #MPC #Web3Dev #Ethereum #AccountAbstraction
































