Blind dev projects news
3 subscribers
18 photos
6 videos
392 links
From discord.
Download Telegram
Nous Research #announcements

@everyone

Announcing the Hermes Agent plugin catalog!

Hermes Agent now has a Plugin Catalog: starting with 4 official plugins and 96 from the community, covering desktop mods, new platforms, browsing, specialized tools, and more.

Our team reviews every community plugin, and we will add new ones regularly.

Want to submit your plugins? Learn how here: https://hermes-agent.nousresearch.com/docs/user-guide/features/plugin-catalog#submitting-a-plugin-to-the-catalog

https://fxtwitter.com/NousResearch/status/2100266421020152114

Plugin Catalog | Hermes Agent

Browse and install reviewed, SHA-pinned Hermes plugins from the curated catalog

Hermes Agent now has a Plugin Catalog\: starting with 4 official plugins and 96 from the community, covering desktop mods, new platforms, browsing, specialized tools, and more\.
︀︀
︀︀Our team reviews every community plugin, and we will add new ones regularly\.
︀︀
︀︀hermes-agent.nousresearch.com/docs/plugins - https://hermes-agent.nousresearch.com/docs/plugins

💬 - https://x.com/intent/tweet?inreplyto=2100266421020152114 2 ❤️ - https://x.com/intent/like?tweet_id=2100266421020152114 9 👁️ 2\.6K 
Nous Research #hermes-announcements

@hermes-agent-notifications

A bit of a roadmap:

https://fxtwitter.com/Teknium/status/2100645382552428963
https://fxtwitter.com/Teknium/status/2100645510856298543
https://fxtwitter.com/Teknium/status/2100645958447186331
https://fxtwitter.com/Teknium/status/2100646469015609779
https://fxtwitter.com/Teknium/status/2100646667259449653
https://fxtwitter.com/Teknium/status/2100647120147771645
https://fxtwitter.com/Teknium/status/2100647460217729401

We are going to lean into making Hermes more like Pi, and less like OpenClaw

💬 - https://x.com/intent/tweet?inreplyto=2100645382552428963 47 🔁 - https://x.com/intent/retweet?tweetid=2100645382552428963 9 ❤️ - https://x.com/intent/like?tweetid=2100645382552428963 249 👁️ 4\.1K 

↩ (@Teknium) - https://x.com/Teknium
The first step of this is removing all the bundled Memory providers\.
︀︀
︀︀They will be maintained by their creators, in their own org's repos, and land in the plugins market

💬 - https://x.com/intent/tweet?inreplyto=2100645510856298543 3 ❤️ - https://x.com/intent/like?tweet_id=2100645510856298543 55 👁️ 1\.2K 

↩ (@Teknium) - https://x.com/Teknium
This will be our test run of pulling integrations out of the core codebase, and into maintainer owned repos\.
︀︀
︀︀This means less to confuse users, less bloat, and less people who don't know what they're doing on a path that isn't the happy path\.

💬 - https://x.com/intent/tweet?inreplyto=2100645958447186331 3 ❤️ - https://x.com/intent/like?tweet_id=2100645958447186331 36 👁️ 751 

↩ (@Teknium) - https://x.com/Teknium
Now that we have a plugins catalog, and months ago made all integrations plugins that came bundled with Hermes, we can begin to move away from having to maintain and package them with every install\.
︀︀
︀︀This reduces our load as well, so we maintain the things that matter, while external integration creators maintain what matters to them

💬 - https://x.com/intent/tweet?inreplyto=2100646469015609779 1 ❤️ - https://x.com/intent/like?tweet_id=2100646469015609779 23 👁️ 550 

↩ (@Teknium) - https://x.com/Teknium
The biggest issue with independent plugins for everything was discoverability\.
︀︀
︀︀The Plugins API surface was already strong and capable of supporting all kinds of things, like tool providers, memory systems, etc \- but there was no discoverability until now\.

💬 - https://x.com/intent/tweet?inreplyto=2100646667259449653 1 ❤️ - https://x.com/intent/like?tweet_id=2100646667259449653 15 👁️ 528 
Nous Research #hermes-announcements

https://x.com/Teknium/status/2100647460217729401

Some confusion on what leaning into being more like Pi than Openclaw is being expressed \-

What I mean is, bundling and packaging less things with the core agent, more plugins, leaner core\. Not that we're not trying to be a personal assistant agent and becoming a coding agent\. For clarity\!

https://twitter.com/Teknium/status/2100647460217729401
Nous Research #hermes-announcements

@hermes-agent-notifications

You can now access GLM-5.3 FlashX on Nous Portal and OpenRouter in Hermes Agent 🙂

https://x.com/Teknium/status/2101773802418139526

GLM\-5\.3 FlashX is now available in Hermes Agent through Nous Portal and OpenRouter\!

https://twitter.com/Teknium/status/2101773802418139526
Nous Research #hermes-announcements

@hermes-agent-notifications

The plugins catalog is now expanded to let you click into the plugin to it's own shareable page, with full readme inside - as well as see all plugins by author, and sort by recent to see the latest additions!

Check out the full catalog here: https://hermes-agent.nousresearch.com/docs/plugins

https://x.com/Teknium/status/2101932350821257289

Plugin Catalog | Hermes Agent

Give Hermes new powers: reviewed plugins you can install in one click

Just FYI, it's all live now :\)

Plugin's each get a whole page when clicked into, their readme piped in\.

We also now have sort by recent, show all plugins by author, and more\.

Check out the catalog:
https://t.co/iN3j0OT4sR

https://twitter.com/Teknium/status/2101932350821257289
Nous Research #announcements

@everyone

Grok 4.7 is 50% off for one week in Hermes Agent via Nous Portal

https://fxtwitter.com/NousResearch/status/2102079445607629260?s=20

Grok 4\.7 by @SpaceXAI - https://x.com/SpaceXAI is 50% off for one week in Hermes Agent via Nous Portal
︀︀
︀︀portal.nousresearch.com/models - https://portal.nousresearch.com/models

> Quoting - https://x.com/SpaceXAI/status/2102069815225586149 SpaceXAI \(@SpaceXAI - https://x.com/SpaceXAI\)
> ︀
> Grok 4\.7 is here\.
> ︀︀
> ︀︀It's a notable improvement over Grok 4\.6 at the same price and speed\.

💬 - https://x.com/intent/tweet?inreplyto=2102079445607629260 2 🔁 - https://x.com/intent/retweet?tweetid=2102079445607629260 2 ❤️ - https://x.com/intent/like?tweetid=2102079445607629260 10 👁️ 1\.6K 
Nous Research #hermes-announcements

@hermes-agent-notifications

Welcome back to Hermes Agent, Claude

New official plugin that uses Claude SDK without the tradeoffs to enable Claude Code subscriptions to work in Hermes Agent again!

Check it out and install it here: https://hermes-agent.nousresearch.com/docs/plugins/claude-subscription-directsdk

https://x.com/Teknium/status/2102093483788107792

claude-subscription-directsdk · Plugin Catalog | Hermes Agent

Experimental model provider that runs Hermes turns on a Claude Pro/Max subscription through the official Claude Code CLI (the Agent SDK path), so no separate AP

Welcome back to Hermes Agent, Claude

New official plugin that uses Claude SDK without the tradeoffs to enable Claude Code subscriptions to work in Hermes Agent again\!

Check it out and install it here: https://t.co/r5YghWTwiY

https://twitter.com/Teknium/status/2102093483788107792
Nous Research #hermes-announcements

@hermes-agent-notifications

Opus 5.5 is now on Nous Portal for Hermes Agent (and on openrouter too)!

https://x.com/Teknium/status/2102442142040014893

Anthropic's Claude Opus 5\.5 is now available in Hermes Agent via Nous Portal\!

https://twitter.com/Teknium/status/2102442142040014893
Nous Research #hermes-announcements

@hermes-agent-notifications

GPT-6-Sol and GPT-6-Luna are now available in Hermes as well 🙂

Soon for codex with 1M ctx too.

https://x.com/Teknium/status/2102472696525377909

The new GPT\-6\-Sol and GPT\-6\-Luna are now available in Hermes Agent in Nous Portal and OpenRouter, soon through Codex subscriptions as well\!

https://twitter.com/Teknium/status/2102472696525377909
Nous Research #hermes-announcements

@hermes-agent-notifications

Portal services are restored 🙏
Nous Research #hermes-announcements

@hermes-agent-notifications

You can now watch your agents work live as Hermes Desktop streams the screen of any bot's screen or session in real time.

Watch it drive a browser, type into a terminal, or open a window. Take over anytime to interact with the Bot Screen or type credentials and seamlessly hand back off when you're done.

https://fxtwitter.com/NousResearch/status/2102873234819698877?s=20

Learn more with @ntombi's latest video guide: https://fxtwitter.com/NousResearch/status/2102873237101154321

You can now watch your agents work live as Hermes Desktop streams the screen of any bot's screen or session in real time\.
︀︀
︀︀Watch it drive a browser, type into a terminal, or open a window\. Take over anytime to interact with the Bot Screen or type credentials and seamlessly hand back off when you're done\.

💬 - https://x.com/intent/tweet?inreplyto=2102873234819698877 6 🔁 - https://x.com/intent/retweet?tweetid=2102873234819698877 8 ❤️ - https://x.com/intent/like?tweetid=2102873234819698877 68 👁️ 4\.5K 

↩ (@NousResearch) - https://x.com/NousResearch
Here's a handy walkthrough of the new Bot Screen feature by the illustrious @tonbistudio - https://x.com/tonbistudio
︀︀
︀︀Docs\: hermes-agent.nousresearch.com/docs/user-guide/features/bot-screen - https://hermes-agent.nousresearch.com/docs/user-guide/features/bot-screen

💬 - https://x.com/intent/tweet?inreplyto=2102873237101154321 2 🔁 - https://x.com/intent/retweet?tweetid=2102873237101154321 1 ❤️ - https://x.com/intent/like?tweetid=2102873237101154321 15 👁️ 878 
Ambient #📢│announcements

@⁣       ↑ Notification Roles ↑        ⁣

New super users announced soon!


⚡ WEEK 27 — PROOF OF USEFUL WORK

Theme: What Should Useful AI Compute Be Worth?

Compute is at the heart of Ambient, but contributing compute to a decentralized network raises an important question:
What should useful AI work actually be worth?

As small-model mining moves closer to launch readiness, this week focuses on the systems surrounding it: verification, rewards, slashing protections, miner onboarding, and the experience of contributing hardware to the network.
We want to explore what makes mining fair, reliable, and economically predictable for operators.

🆕 WHAT'S NEW THIS WEEK?
• Small-model mining approaching launch readiness
• Verification work nearing completion
• Reward accounting development
• Fair slashing protections
• Standalone miner client preparation
• Miner documentation preparation

👤 USER LOOP — "DESIGN THE MINER"
Imagine you have limited GPU capacity and need to decide which jobs are worth accepting.
What information would you need to make that decision?

Consider:
• Workload size
• Inference time
• Verification cost
• Expected reward
• Hardware requirements
• Current network demand
• Risk of failure

Think about the experience from a miner's perspective.
Would you know how much work a job requires? Would the potential reward be clear? Could you understand the risks before committing your hardware?

Share:
• What information you'd need before accepting work
• What would make contributing compute worthwhile
• What would make you reject a job
• What would make mining feel too unpredictable
Post your thoughts in:
https://discord.com/channels/1334942930695225365/1448970141940322354

🛠️ DEV LOOP — "VALID WORK / INVALID WORK"
This week, build workflows where the expected result can be checked.
The goal is to explore what evidence should exist before completed work receives a reward.

Test:
• Correct execution
• Incorrect execution
• Interrupted jobs
• Incomplete results
• Duplicate work
• Inconsistent outputs
Think About:
• What should count as valid completed work?
• What evidence should exist before a reward is issued?
• Where should verification happen?
• What should happen when verification fails?
• How should incomplete or duplicated work be handled?
Share any edge cases where deciding whether work is "valid" becomes difficult.

⚙️ INFRA LOOP — "MINER READINESS"
We're getting closer to the point where more operators can participate directly.
This week, focus on what that experience needs to look like in practice.
Focus:
• Standalone client behaviour
• Hardware compatibility
• Miner onboarding
• Verification
• Reward accounting
• Failure handling

Test:
• Miner disconnects
• Slow miners
• Invalid results
• Interrupted inference
• Verification failures
• Temporary network loss
• Recovery and rejoining

Report:
• Confusing setup steps
• Hardware-specific problems
• Unexpected verification behaviour
• Poor or unclear error messages
• Recovery issues
• Anything that makes operating a miner unnecessarily difficult
The goal is to make contributing compute understandable and predictable, even when something goes wrong.

🌐 ECOSYSTEM LOOP — "FAIR REWARDS"
A useful compute network needs incentives that work for both the network and the people supplying hardware.
This week, we want the community to think about what "fair" actually looks like.

Discuss:
• What deserves a reward?
• What should constitute invalid work?
• When should slashing happen?
• How should honest hardware failures be treated?
• What information should miners receive when work is rejected?
• What would make mining economically predictable enough to participate?
There won't always be a simple answer.

💡 WHY THIS MATTERS
Compute is one of the core resources powering Ambient.
Ambient's longer-term design ties network participation to useful machine-learning work, rather than expending compute purely for consensus.