@dappnode

Run Private AI agents 24/7 to increase your daily productivity. Earn rewards running your web3 node at home. Zero hassle, it just works https://nitter.cf/t.co/PXEiFrEo9S

 Cryptovalley-Zug (Switzerland)
dappnode.com
Joined February 2018
  • Tweets3.9K
  • Following1.3K
  • Followers16.1K
Don't have a nexus account yet? nexus.dappnode.com

Dappnode Nexus — Private AI Gateway for Builders

Access private and confidential AI models through one unified, OpenAI-compatible API. Your prompts and data stay yours.

nexus.dappnode.com
2
213
Qwen 3.8 27B is the model that packs the highest intelligence per size It's fast, smart, and very good with agentic tasks It can handle pretty much everything you throw at him And it's also Free🤑 for a limited time in Nexus right now ⚡️Go squeeze every prompt from it! 🥵
1
5
1
11
1,584
Replying to @raopreetam_ @d_gusakov @Heracles1337 @ethereum
a few minutes installing dappnode and you get a bunch of neat stuff packaged with it! UI, Tailscale/Wireguard for remote access, a UI for validator keys and a bunch of neat packages in the Dappstore!
1
65
Replying to @CryptoChrisG
Easy! Give OpenClaw or Hermes (both available in Dappnode) your problem and ask them to query you on what your preferences are, what would you like, etc. If you use Nexus as the model provider, you keep your personal info private from any profiling company 🕵️ If some of the class info is in PDF, feed it to it, if it's behind password... again, feel free to give it your account details because... the filesystem is yours and only yours and the model provider can't read your password!
1
47
Replying to @CryptoChrisG
Upper class for you, ser. Jk aside, wdym class selection?
1
1
58
If you are not running your own agent you are behind "But it's too complicated" In 1:47 seconds you can have it running on your Dappnode Get your agent, fully private & self-sovereign Comment 👇which thing you'd die to automate in your life and we'll make a video of how
3
2
2
17
1,615
I almost missed the IMHO most catastrophic @ledger vulnerability: h/t @Fatalmeh who brought it onto my feed
TestMachine
@testmachine_ai
Aug 22
🚨Every Ledger running the Ethereum app is vulnerable to signature substitution A malicious dApp with WebHID access could race an APDU during your transaction review and swap the tx being signed while the device still shows the original Here's what you need to know:
9
20
2
201
78,198
Every EVM developer should have a local archive @ethereum node and never trust RPC providers or spend money on RPC subscriptions. I run archive Reth + Prysm on my @dappnode, and it works like a charm. 4TB SSD is more than enough
14
10
5
75
7,655
Every home validator is one more vote for a resilient, censorship-resistant Ethereum. Thank you for funding that.
78
Indirectly, we dropped Smooth's fee from 7% to 5%, so solo stakers keep more of their rewards. Solo staking must stay viable (and that includes rewarding them over centralized players)
1
74
But what if your hardware IS able to run models? We released the Local AI Toolkit (one-click install of Ollama, OpenWebUI, Hermes Agent, OpenClaw, n8n... and growing!)
1
32
That assistant runs on Nexus (nexus.dappnode.com): private AI inference with TEE-attested models with proofs. We built Nexus so if your hardware isn't able to run able models, you can have the next best thing: cryptographically verifiable private inference.

Dappnode Nexus — Private AI Gateway for Builders

Access private and confidential AI models through one unified, OpenAI-compatible API. Your prompts and data stay yours.

nexus.dappnode.com
1
24
Running your own validator can be hard. When it breaks at 3am, people give up or worse... move to a custodial service! So we Nexus Chat in DAppManager reads your logs, debugs, explains. Easier troubleshooting = more home validators = a validator set no one can capture.
1
1
23
So, what did we do with the money? Spolier alert: lots of AI to make your validators safer.
1
1
128
First, thank you also to all the matching fund providers. Matching came from @TheDAOfund @quantstamp @wintermute_t @osec_io @Certora @sigp_io @CertiK @chain_security. Security teams funding security 🤝
1
3
276
Thank you❤️ TheDAO Fund's Ethereum Security round on Giveth sent Dappnode 5.6343 ETH: 1.2227 from the community, 4.4116 matched. Here's how that money becomes Ethereum security: easier home staking → more solo validators → a more decentralized, safer Ethereum.
2
4
15
841
kinda crazy my @dappnode video from 2023 is still one of my top performers on youtube youtu.be/VR_aZXtX3r4?si=2wlT…

a noob sets up an ethereum full node | dappnode plug-and-play guide

tl;dr: wow, i didn't realize it would be that easy to setup an ethe...

youtube.com
1
1
5
281
Replying to @haochizzle
Maybe you should do one on how to run Agents on Dappnode now!
16
The guys from @exolabs , which we have used extensively in @dappnode, dropped local.ai. For virality, they let you claim your name already. local.ai/lanski/invite

local.ai — Independent Local AI Benchmarks

Independent benchmarks comparing AI model intelligence, speed, energy use, and hardware across Apple silicon and NVIDIA GPUs.

local.ai
2
11
736
Testing on Dappnodes
Syzygy Research
@syzygyeng
Aug 3
Today, we're introducing Mach-1 Additive, a 35 billion parameter model that can inference without ever multiplying by a weight. At 1.7 bits per weight, Mach-1 recovers 95% of the performance of the original full precision model, Qwen 3.6 35b, across 12 agentic and reasoning benchmarks, while being 10x smaller. At 7GB, Mach-1 comfortably fits on consumer laptops with speeds of up to 120 tokens per second, making local inference not just feasible but useful. Unlike algorithms like BitNet, our approach requires minimal retraining, under 15 GPU hours, making it scalable to massive LLMs. Over the coming weeks, we will be announcing and serving models of up to 3 trillion parameters compressed using our algorithm. For now, you can visit our website to play with Mach-1 directly in your browser, or download our desktop app. We couldn't be more excited to launch Mach-1. We're looking forward to an energy efficient future for AI, powered by scaled intelligence density.
1
2
661
Load more