azerx.eth ₿ ŁⓂ️🕸️🔺

@AnthropicAI @StainlessAPI And please make a proper linux app!

@AnthropicAI @StainlessAPI How do i select this "menu" to vote? i did it once but can't remember it :( even your claude is clueless :)

Anthropic is acquiring @stainlessapi, an SDK and MCP server platform that has powered every Anthropic SDK since the earliest days of our API. Read more: anthropic.com/news/anthropic…

Electric surfboards are about to make jet skis look ancient. Silent, fast, and way too fun.

@Teknium I think i found it, posted a comment in there if i now went to the right place , its called "Feedback on The Kanan System", is that it? Thanks again!

@azerX Ping me and I'll show you the thread its hard to show off unless I know who you are to tag you there

The Hermes Agent Kanban just got a big automation upgrade. Drop one prompt into the triage, and the orchestrator agent can take it from there - decomposing it into all the subtasks necessary and automatically assigning agent profiles that fit the specialization needed. You can also now add descriptions for each agent profile, to better assist the orchestrator in determining what tasks should go to which profile! Docs: hermes-agent.nousresearch.com/docs/user-guid… PR: github.com/NousResearch/h…

@SabriMjd @mackysy @Teknium Thank you.

@azerX @mackysy @Teknium github.com/Sabrimjd/Herme… here it is it is the obsidian-xl in this case

OpenClaw 2026.5.18 is live 🤖 xAI/Grok OAuth + sidecar auth fixes 🎙️ Realtime Android Talk Mode 💬 Telegram media + forum-topic delivery fixes 🪟 Browser dialogs visible + answerable A week of polish, plumbing, and fewer papercuts. github.com/openclaw/openc…

@LeoDuquesnel @cursor_ai Agree, even gpt.5.5 has 272k limit. Not sure how yours show 1m ? But agree, that is to low.

@cursor_ai That's great but the 200k context window is still kind of a blocker for me :/

Introducing Composer 2.5, our most powerful model yet. It's more intelligent, better at sustained work on long-running tasks, and more reliable at following complex instructions. For the next week, we’re doubling the included usage of the model.

@SabriMjd @mackysy @Teknium This looks actually good. Please do share if you can.

@mackysy @azerX @Teknium it's more than just a theme issue it's UX wise having the output in a side bar with is bad UX. added a theme it's better but still not very good

@ThisAndDhat @Teknium I love the tui for the most part but yeah for some work you need proper web. Actually creating a proper control center inspired for the this video :) youtube.com/watch?v=ZjHwlk…

@azerX @Teknium The themes are all terrible. A great product this Hermes but the ui is just unusable for me. Well I sent Hermes to create a more readable theme. After 150 rounds it came back with a theme not much better. Thats where I uninstalled it but later gave Hermes a new try.

@elga_toloko @Teknium yes but it breaks some things and each update ... It needs to rework under the hood for themes. The fonts are all over the place in each part of the webpage.

@azerX @Teknium This is solved with a few CSS lines. I guess you can PR.

@Teknium Will join the fun when i find it :) please share which channel, cant seem to find it. ps. made myself a Hermes Release Radar in community project ;) love the hermes community so want to contribute.

@azerX Join the discord, we have a thread going for all the improvements the community wants to see that Ive been feeding into issues and PRs discord.gg/NousResearch

A glaringly obvious double-standard

Exactly! They provide some eye candy while significantly increasing the token burn rate. I never hit the usage limit until this week; it feels like they’ve downgraded the service under the hood without any transparency. I refuse to pay more than $100, which is already pushing it. ChatGPT has never cut me off, even on lower tiers, so I’ve upgraded to their $100 plan instead of throwing more money at Claude. I’m incredibly disappointed with Anthropic’s decision to continuously squeeze the user base. Removing OAuth usage from agents like Hermes is just another major letdown!

@ClaudeDevs Doesn’t work for me, didn’t get the extra 50%. Im on Max. I’m still at 100% so switched to codex until it resets. And I’m really liking GPT-5.5; it doesn’t need skills to work right.

Claude Code weekly limits are increasing 50%, now through July 13. Live now for all Pro, Max, Team, and seat-based Enterprise users.

Every time you guys make a post about "news", its a downgrade in some hidden shape or form. I actually went from max 20x and game the extra 100$ to chatgpt and soon will move fully if the new model is better for coding. Just not letting us use our paid subscription for Openclaw/Hermes and forcing API is a huge let down. I pay for the amount of usage and how i decide to use it should be up to me as a user! Very disappointed with Anthropic right now.

Starting June 15, paid Claude plans can claim a dedicated monthly credit for programmatic usage. The credit covers usage of: - Claude Agent SDK - claude -p - Claude Code GitHub Actions - Third-party apps built on the Agent SDK

@ClaudeDevs Framing this as a free credit instead of a regression for users is wild. Now I have to make the Claude Code experience on T3 Code significantly worse in order to keep using the 25x subsidization provided on a Claude Code subscription. x.com/theo/status/20…

Dash joins Southeast Asia Blockchain Week 🇹🇭 as a community partner (@SEABWofficial) May 21–22 • Bangkok Hosted by @0xShardLab & @hashed_official On the ground supporting side events & connecting with the SEA ecosystem. Represented by the relaunched Thailand Hub.

@ClaudeDevs its down :)

/radio

@benson_sharks @ClaudeDevs 😂🤣

The one thing thats just awful is the webUI. I think more people would use hermes if the WebUI was more appealing. the TUI people are the 1% of users. To reach the masses you need a proper UI. I think Hermes works much better then Openclaw right now, more stable and working but the interface for things like kanban and copy/paste, attach images you need a proper UI. I hope this can be in the focus soon. And sorry to sound negative, i love and appreciate the hard work. I just want more people to get onboard and use this great platform!

Your Hermes Agent can now build full videos with the official HyperFrames skill by @HeyGen HyperFrames videos are HTML-native, so your agent has total control over the final output Video made entirely by Hermes using the HyperFrames skill