vainess

vai

[vainess @badboymv21]

@Okpara081 Yes 🫣

[Sunrise @sunrisedefi]

$SPCX is now live on @Solana via Sunrise.

The biggest IPO in history priced on Nasdaq this morning.

Issued by @Backpack Securities, $SPCX brings a tokenized SpaceX share onchain, on day one, trading across every Solana wallet and app 24/7.

Own something.

[Liquid AI @liquidai]

Today, we're releasing LFM2.5-8B-A1B, a device-optimized model designed to power real-life applications on phones, laptops, PCs, robots, and fast & lightweight server-side use-cases.

> 8B MoE, 1.5B active
> Expanded 128K context
> LFM2.5 flagship hybrid MoE architecture
> Trained on 38T tokens + large-scale RL
> fast, reliable tool calling, punching above its weight, comparable to models with up to 4x its size
> customizable on a single GPU for any specialized task
> LFM2 open-weight license

🧵

[vainess @badboymv21]

@gregosuri August 15, UTC 07:20,

[Teknium 🪽 @Teknium]

If using a cloud based browser backend in Hermes Agent, it will now auto-detect if you want it to look at or use a locally hosted website and switch to local browser so it can access it.

Hopefully this makes it super convenient for web devs and people needing local services accessible!

`hermes update` and it'll take affect automatically.

PR: https://t.co/o0fKO54HeE

[Dhruv @dhruvtwt_]

Why is no one talking about this?

@nvidia is offering around 80 AI models via hosted APIs absolutely for free.

You get access to MiniMax M2.7, GLM 5.1, Kimi 2.5, DeepSeek 3.2, GPT-OSS-120B, Sarvam-M etc.

This plugs straight into OpenClaude, OpenCode, Zed IDE, Hermes agent and even with Cursor IDE.

Setup:
– Grab API key: https://t.co/Wfdclm0hY2
– base_url = "https://t.co/VOGC10LmGP"
– api_key = "$NVIDIA_API_KEY"
– select model (e.g. minimaxai/minimax-m2.7)

If you’re building or experimenting, this is basically free inference.

Lock in and start building today anon.

Thank me later.

[Teknium 🪽 @Teknium]

Looks like a nice guide!

[Teknium 🪽 @Teknium]

Tip of the day:

Learn about Auxiliary Models and save big money with Hermes Agent!

https://t.co/6M7iYoqEea

[0xJeff @0xJeff]

https://t.co/vujtA3V8Wi

[dodo-reach 🦤 @DODOREACH]

@Teknium @NousResearch hermes-desktop is open-source and 100% native macOS → https://t.co/AZzh4QC2c3

@socialwithaayan @QingQ77 @billtheinvestor @sudoingX @cocktailpeanut @0xsachi

[BruceBlue 🌊 @BruceBlue]

📱Hermes-web-ui 的贴心更新！

🎮最新优化/新增功能：
🔹用户模块（profile），随时切换 multi-agent；
🔹深色主题，对夜猫子网友特别友好；
🔹手机适配，出门/通勤都可以及时抢救和搬砖；
🪆温馨提示：试试单独和赫妹在 Web UI 单独聊天，她的性格可以和你自己配置的 Agent 不一样喔！🥳

👉Github：https://t.co/Ff5PhMvBwO

💾安装即用：
1️⃣复制以下命令：
npm install -g hermes-web-ui
hermes-web-ui start
2️⃣输入 hermes-web-ui start → 浏览器自动打开；

#HermesAgent #AIAgent

[GitTrend @GitTrend0x]

今天 GitHub 被个人到指挥 Agent 军团彻底屠榜了🚀

5 个星标暴增最狠的项目，专业拆解下！

1. NousResearch/hermes-agent

今天还是榜一，自进化 AI agent、通过与用户交互自主创建技能、跨会话记忆建模，实现真正和你一起成长的智能体，彻底解决传统 agent一成不变的痛点

🔗 直达 https://t.co/A0bGcD9p2q

程序员半夜睡一觉起来，agent已经自学了你所有坏习惯，还把昨天的bug修好顺便优化了架构——8301星直接核爆，这哪是助手，分明是你失业的AI分身在卷你自己！🟢

2. multica-ai/multica

解决编码 Agent孤岛作战、无法协同的顽疾，开源托管式多Agent平台，让Agent像真队友一样分配任务、追踪进度、叠加技能，直接变身可管理的企业级生产力军团。

🔗 直达 https://t.co/vHBqUgOHSw

以前一个 Agent干活像独狼，现在multica 直接给它配了整个连队，1626星标暴增，开发者看完直呼：这不就是我梦寐以求的 AI部门吗？

🟢🟢

3. shiyu-coder/Kronos

首个开源金融K线基础模型，通过分层离散tokenization把高噪声 OHLCV 时序数据变成 Transformer 能吃的“语言”，为量化 agent 提供统一预测 backbone

🔗 直达 https://t.co/cgzKAhTq9E

以前quant得熬夜盯盘，现在扔给Kronos 它自己就把45个交易所的K线全吃透了。963星起飞，这不是模型，是给 Agent 军团装上的金融大脑！

🟢🟢🟢

4. alirezarezvani/claude-skills

232+个领域专家级技能包与agent插件，一键武装 Claude Code、Cursor等12款 coding agent，覆盖工程、营销、合规、C-level 等 9大场景，解决通用AI工具什么都会但什么都不精的痛点

🔗 直达 https://t.co/hCp7oB6RFM

以前 agent写代码像实习生，现在直接加载 Startup CTO 人格+POWERFUL 技能包，秒变 C-level 顾问。195星暴增，程序员终于可以指挥一整个 AI 高管团队了！

🟢🟢🟢🟢

5. Tracer-Cloud/opensre

开源 AI SRE agent 工具包，集成40+运维观测工具+真实故障模拟环境，让agent 自主调查并修复生产事故，解决传统 SRE证据碎片化、响应慢的痛点

🔗 直达 https://t.co/GhYHc2zSXl

生产出故障，SRE们还在 Slack里吵，AI agent 已经把日志、指标、trace全拉出来定责修完了。137星起飞，这回真不是人在运维，是agent在 24h 值班！

⚠️⚠️

总结：从自进化个人agent，到19人金融战队、SRE 救火神器、coding高管技能包，再到金融时序大脑全武装。 Agent 军团已全面接管，程序员的下一份工作是指挥官 🚀🤖

[Mayukh Bagchi @MayukhBagchi4]

@Teknium @MiniMax_AI Just shipped a Hermes Agent skill with HuskyLens V2 on a Pi 5 gesture control, face recognition, emotion reading, all local. MiniMax M2.7 as the brain would be wild for this. What's the target hardware?
https://t.co/UuBtK7YIyO

[Joey @aijoey]

Hermes Agent Upgrade Kit.

Skins: https://t.co/hJuER0Db6f
Web UI: https://t.co/b5SxuuRX72
TUI: https://t.co/wT8L7X8BPu

Daily Quote: Hermes Agent does not chase chaos. It brings order to it.

@NousResearch @Teknium

[Teknium 🪽 @Teknium]

Nice guide here:

[Teknium 🪽 @Teknium]

Tip of the day:

If you need help with configs, settings, setup, usage, exploration, tutorials, or development on Hermes Agent, just type /hermes-agent <prompt>

Built in skill that gives your agent all the knowledge of every CLI command, config, resource links, best practices, architecture info, etc

Even shows your agent how to orchestrate other hermes agent instances and profiles!

Give it a try today :)

[Gajesh @gajesh]

9 Macs running right now. 600+ GB unified memory. ~3 TB/s bandwidth. $15k live, another $15k (3x 128GB M5 Max) on the way.

Text, images (FLUX on Metal), speech-to-text. Full stack shipping: coordinator, hardened provider agent, Secure Enclave integration, macOS app, web console.

Paper published. System live. Research preview, rough edges included.

Try it: https://t.co/gOww1LY1NP
Earn from your Mac: https://t.co/fCA7CNyewY
Paper: https://t.co/5qNS8P5H5J

Reply and I'll send you an invite with free credits.

An @eigenlabs research initiative.

[Teknium 🪽 @Teknium]

NEW: Added @OpenRouter's new free stealth model, Elephant-Alpha, to Hermes Agent, which you can now access if you run `hermes update`!

I also had Hermes come up with an agentic benchmark on the fly to test, the results were mixed but about in line with what you'd expect for a 100B model. The model seems OK at most tool use, but expect some hallucinations and it potentially misunderstanding the environment (hermes agent) that it's in!

Enjoy!

PR Link: https://t.co/FNzcD7KNEQ

[SIGKITTEN @SIGKITTEN]

every time i open openclaw/hermes/etc im always like

&gt; i dont even know what i want it to do now

[Kanika @KanikaBK]

🚨 JUST IN: SOMEONE JUST WROTE A WHOLE THE HERMES AGENT MANUAL Nous Research never gave you. 100% FREE.

No experience needed to start. 17 chapters. 80+ tools, skills, plugins, and integration all at one place.

It covers BUILDING A SELF-IMPROVING AGENT from ZERO to ADVANCED.

Here is what is inside.

Everyone knows Hermes Agent blew up. 50K stars, 2.4 million views on the launch tweet, developers ditching everything else to run it. But Nous Research dropped the tool and basically left you to figure it out alone. No beginner guide. No map. Just a GitHub repo and good luck.

It is called the Orange Book. 17 chapters, split into 5 parts. He starts with the concepts so you actually understand what makes Hermes different from every other agent before you touch a single command. Then he walks you through the three layer memory system, how the skill creation loop actually works, and why the agent gets better every single time it runs a task.

- part one kills the anxiety, explains Hermes in plain language before anything else
- part two breaks down the learning loop, memory architecture, and how skills get created automatically
- part three is hands on, installation, first conversation, multi platform setup, customisation
- part four is real world scenarios, knowledge assistant, coding agent, creative work, running multiple agents together
- part five compares Hermes against Claude Code and OpenClaw so you actually know when to use what

Nous Research built the agent. They charged nothing for it. Alchain spent weeks mastering every part of it, wrote a 17 chapter book, and also charged nothing for it.

The tool that taught itself to get smarter now has a guide written by someone who did the same thing.

I still do not understand why this is all free. But here we are.