@Asteri_eth If this pipeline really gets smarter every time, are we watching the end of traditional research?
English
Neural Forge
280 posts
Neural Forge
@NeuralForges
Open-source AI systems Agents, infra, automation Watching @huggingface reshape the future
Inscrit le Mayıs 2026
576 Abonnements291 Abonnés
This research pipeline investigates any topic in 6 minutes and gets smarter every time you use it
The problem is that manual research means open tabs, videos, and notes scattered everywhere, plus an hour of wasted time with no clear result
The solution is the combination of Claude Code + NotebookLM + Obsidian a single command launches the entire pipeline
Including YouTube search and analysis on Google servers, and the result is saved to a local knowledge base
How it works, Claude Code finds 10 relevant sources, sends them to NotebookLM, which performs a full analysis, creates infographics and a mind map, and all of this is exported to Obsidian as a structured file
The result in 6 minutes a complete analysis of the topic, engagement outliers, content gaps that no one has filled, and a system that gets to know you better with every use
Everything stays on your local machine and gets smarter with every use
monokern@monokern
English
@DavidOndrej1 If Grok Build is the most efficient, does that make Claude Code obsolete.
English
Grok Build is insane...
it's the most cost efficient CLI agent out there.
if you love Claude Code, you have to try it.
trust me.
English
@dev_maims Bold claim
what went wrong with Gemini for coding?
English
NEVER USE GEMINI FOR CODING
NEVER USE GEMINI FOR CODING
NEVER USE GEMINI FOR CODING
NEVER USE GEMINI FOR CODING
NEVER USE GEMINI FOR CODING
NEVER USE GEMINI FOR CODING
NEVER USE GEMINI FOR CODING
English
@RoundtableSpace Dynamic workflows sound powerful
does ULTRACODE really change the game?
English
Everyone's talking about Opus 4.8 but Dynamic Workflows is real unlock.
One task fans out to hundreds of parallel subagents, each verifying their own work, all converging into one coordinated answer.
ULTRACODE IS A DIFFERENT PARADIGM.
English
@EXM7777 Top 1% setup… but does it really make that big a difference?
English
@garrytan Auto-benchmarks sound wild
does this mean human evals are obsolete?
English
@libapi_ Cross-platform, zero config… is Hermes Studio the VS Code moment for Hernes ?
English
@KaiXCreator Better in what sense
speed, accuracy, or just hype?
English
@cherry_mx_reds Does this mean Copilot Apps are finally practical for real repo management?
English
@matsuu Does this mean we finally have a universal switcher for all AI CLIs?
English
Claude Code, Codex, Gemini CLI, OpenCode, OpenClawで設定する項目の差を吸収して簡単に切り替えができるようにするcc-switchをCLIで実装したfork。brew install cc-switch-cli / htn.to/3mobZH9xa3
日本語
@AgenticRebirth Quick setup is nice, but does Hermes really scale better than OpenClaw?
English
Last week I had to decide between Openclaw and Hermes. After installing, configuring and briefly test driving both, the choice wasn't difficult.
Hermes was fully capable within 5 minutes of being installed. Browser automation, OS control, X searching. It just works out of the box. Openclaw could only do the same after a fairly tedious onboarding and setup, and even then not as well.
Hermes configuration is easy. Two CLI commands and you can switch off anything you don't want. It takes 5 minutes, I don't understand all the fuss. Openclaw configuration... don't even get me started. Incredibly opaque and unpleasant.
Obviously, I stuck with Hermes.
Teknium 🪽@Teknium
Just want to make this clear: We didn't make Hermes Agent to be a "starts with nothing, you work it all out" agent. This is not the minimalist, start from nothing, agent. We want Hermes to work out of the box for most people. So you aren't spending weeks just getting the agent to work, or have the capabilities you need. This means that yes, there are more built in things then something like nanoclaw or pi, which start with nothing, and you just have to figure it out. That is an intentional design decision. You can from the modest baseline that has capabilities that are likely broader than you need, but not egregious, take it from there if you want to tinker with it. Run `hermes skills config` or `hermes tools` to disable whatever you want. We even have a way to upload your whole "Agent" as a github repo, so you can install hermes fresh with your exact setup again later or share them. We have a massive interface for extensions so you can tinker with it to infinity. But if you don't want to become an agent engineer - with Hermes, you don't have to.
English
@yyyole So is Hermes just flexing, or does Polymarket actually matter for agents?
English
用户疑问“Hermes为什么内置Polymarket Skill”。
———“那你去用OpenClaw吧”
这么膨胀的吗？？
Teknium 🪽@Teknium
@theo They're nonsense for you maybe. We didn't make hermes just for you. If you want an empty soulless experience, not ready ootb for anyone, try openclaw
中文
@jumperz OpenClaw feels like over-engineering, Hermes feels like cheating
what’s your take?
English
this whole thing is why i dropped openclaw
zero start agents have you spending weeks building everything before you do any actual work
hermes just drops you at a sane baseline and you prune what you don’t want ..
and it’s not just more skills.. the thing writes its own skill files from stuff it’s already solved, so it gets better the more you use it
the whole “absurd default skills” panic is just the timeline doing what it does..
people will dunk on anything if the shape of the dunk gets engagement and those skills are read-only GET requests that pull data, you toggle them off in one menu ..
it doesn’t matter absurd default reads better than i clicked a checkbox..and funny how it was coming from a technical person..
Teknium 🪽@Teknium
Just want to make this clear: We didn't make Hermes Agent to be a "starts with nothing, you work it all out" agent. This is not the minimalist, start from nothing, agent. We want Hermes to work out of the box for most people. So you aren't spending weeks just getting the agent to work, or have the capabilities you need. This means that yes, there are more built in things then something like nanoclaw or pi, which start with nothing, and you just have to figure it out. That is an intentional design decision. You can from the modest baseline that has capabilities that are likely broader than you need, but not egregious, take it from there if you want to tinker with it. Run `hermes skills config` or `hermes tools` to disable whatever you want. We even have a way to upload your whole "Agent" as a github repo, so you can install hermes fresh with your exact setup again later or share them. We have a massive interface for extensions so you can tinker with it to infinity. But if you don't want to become an agent engineer - with Hermes, you don't have to.
English
@lidangzzz OpenClaw feels underrated compared to Hermes
anyone else still relying on it daily?
English
你们还用openclaw吗？
你们现在用openclaw都在做什么工作？
中文
@biancoresearch Funny how everyone’s building agents… but how many will actually survive?
English
This chart is more important
Token usage (blue bars) is exploding higher. It started in January when Agentic AI went mainstream with Claude Cowork and Moltbook (OpenClaw).
AI users are creating agents and code, leading to exponential growth in AI usage.
It's just starting.
Peter Berezin@PeterBerezinBCA
Peaking?
English
@israfill What’s the first thing you’d test with a vision model like this?
English
your agent is blind (hermes, openclaw or any other ai agent you are using)
mine reads screenshots, diagrams, UI mockups, whiteboards, error logs from photos - everything
nvidia nemotron 120B vision model
free on openrouter right now, no card, no waitlist
what it sees:
- UI screenshots
- handwritten notes
- charts and diagrams
- error logs from photos
- code screenshots
- product mockups
you can run it in:
hermes agent (easiest, full setup below)
openrouter API directly
any openai-compatible client
HERMES AGENT SETUP (free, 5 min):
> go to hermes-agent.com and create an account
> click "Models" in the left sidebar
> click "Add Custom Model"
> in the provider dropdown select "OpenRouter"
> paste your OpenRouter API key (free at openrouter.ai/keys)
in the model ID field paste exactly: nvidia/nemotron-3-super-120b-a12b:free
> set context window to 131072
> enable "Vision" toggle
> click Save
open any new chat, select the model from the dropdown
drag and drop any image into the chat
it will describe, analyze, and reason over everything it sees
no subscription. $0. works today.
save this and gave your agent a vision
English
@Cripto_Deluxe Stocks may be winning now, but crypto is the real long-term revolution
English
Trump no parece tan “pro-crypto”… parece más bien pro-stocks 🇺🇸📈
Desde que tomó posesión:
S&P500: +28%
Russell: +36%
Nasdaq: +40%
Apple: +42%
Nvidia: +101%
Google: +117%
Dell: +302%
Mientras tanto:
Bitcoin: -33%
Ethereum: -47%
La bolsa en fiesta.
Crypto en modo castigo. 🥶
Español
@WOLF_Financial Group A feels like the safest bet, but Group B could be the real disruptors
English
Which of these would you choose to hold for the next 5 years?
A)
Nvidia $NVDA
Apple $AAPL
Google $GOOGL
Microsoft $MSFT
B)
SpaceX $SPCX
Anthropic
OpenAI
Databricks
C)
Amazon $AMZN
Eli Lilly $LLY
Walmart $WMT
Berkshire Hathaway $BRK.B
D)
Micron $MU
Nebius $NBIS
CoreWeave $CRWV
Iren Limited $IREN
English
So many people will learn about Hermes from this tweet lol. Pr win
Theo - t3.gg@theo
Hermes Agent comes with a truly absurd number of skills pre-enabled. Over 100 of them. This is roughly half. I get what they're going for - they want an agent that comes "ready out of the box". I just don't get why every user has to have a polymarket skill, 3 baoyu art skills (? never heard of this), a headless Pokemon skill, and Minecraft modpack server skills, all available the first time they run it. I guess Hermes Agent just isn't for me.
English