Gokul Bala

@sudoingX Making content on my Instagram, webinars/walkthroughs, and helping businesses get setup with Hermes, and custom for each business. Generally new to content but we focus on providing useful information instagram.com/gokuls.vision?… @gokulsvision?si=N_SOoO-TwPX9XL_Y" target="_blank" rel="nofollow noopener">youtube.com/@gokulsvision?… @gokulsvision?si=N_SOoO-TwPX9XL_Y" target="_blank" rel="nofollow noopener">youtube.com/@gokulsvision?…

if you're creating video content on local AI or agent frameworks, hermes agent is the #3 fastest growing repo on github right now with 24,000+ stars and the X community just crossed 4,000 builders. i'm actively looking for creators to collab with on hermes agent video content. tutorials, walkthroughs, benchmarks, reactions, whatever format fits your style. i'll push your content to the community and help brainstorm angles that hit. drop your channel or your video below and i'll amplify it to 21K followers and 4,000 hermes builders. if you already have hermes agent content, share it here. let's make open source great again.

@ollama @ollama do these models natively support multi-modal? having trouble enabling vision on ollama cloud.

🦞Ollama's cloud is one of the best places to run OpenClaw. $20 plan is enough for most day to day OpenClaw usage with open models! To make the switch, all you need is to open the terminal and type: ollama launch openclaw Choose a model: kimi-k2.5:cloud glm-5:cloud minimax-m2.7:cloud If you are affected, Ollama welcomes you!! ❤️

OpenClaw: free Mac Mini: $599 Claude Max: $200/mo Keyboard: $25 Monitor: $195 Mouse: $20 having to rebuild your entire agentic stack on a holiday weekend because Anthropic moved the goalposts: priceless

@Utkarsh51557661 @blakeandersonw hes gonna host it for extra $

@blakeandersonw open-source is great, but you still need a way to monetize it. what's your plan for that?

Core is 100% free and open-source (Apache 2.0) All of my important work moving forward will be open-source. I believe this is the future of software development.

We used to be building our startup on Openclaw, but we are planning to change directions to Hermes. Our clients are finding that Openclaw isn’t as reliable. Doesn’t follow outputs consistently and the memory doesn’t help. Gonna hand them Hermes + minimax m2.7 highspeed, curious about their feedback.

what's stopping you from dropping openclaw bloat?

@sodofi_ honestly everyone just opensource your tools, sharing is caring.. i feel like we all have similar needs

what agent tools do people actually use? i feel like ive tried so many and still end up building my own custom thing because everything is mid

This is dope, i love how the calendar is integrated, with both the threads, project managent .. intuitive and simple design. is there a dark mode? wanted to move away from slack anyway. Is there a simple way to connect everyones openclaw agents, like even connect it to the chat section love the product!!!

Introducing core.so (oss apache 2.0) We’re building the future of an AI-native workspace. We rebuilt functionality from Slack, Linear, and Notion. Our vision is simple: centralize context so small teams can work more efficiently with agents.

@internetvin Interested!

I'm thinking about doing an Obsidian, Claude Code, Arena, Figjam meet up at New Stadium in Toronto. Anyone interested?

At that point isn’t it better to get subscriptions of OpenAI, anthropic, minimax, kimi and just rotate. I doubt all of their max subscriptions cost that much in total anyway. And the drop off after opus is so big that, it’s a race for second anyway. So does it matter who the other models are ?

i am now spending $100 every 4 days on tokens this is unsustainable especially because I'm nowhere near where I want to be does anyone have suggestions for self-hosting models? budget 2-4k

@Teknium wait i love this, i've been trying to hack this together for my openclaw for so long. this unlocks how i can actually work with the agent... instead of just whatsapp.

API Server with Responses API Hermes can now act as an OpenAI-compatible backend — any frontend (Open WebUI, LobeChat, LibreChat, ChatBox, etc.) can connect to it. Exposes both /v1/chat/completions and /v1/responses (stateful, with previous_response_id chaining). Full agent stack behind the API: tools, skills, memory, cron.

Hermes Agent v0.4.0 — 300 merged PRs this week. Biggest release we've done. Background self-improvement, OpenAI Responses API endpoint for your agent, new messaging platforms, new providers, MCP server management, and a lot more.

@Haezurath Connections.cx <-- AI social connections done properly.

I’m angeling in a few projects! Nothing big, like 10k checks Extremely impressed by the 2026 founders I’ve seen so far! Drop your project url + I’ll shout out some projects

loyalty has a terrible return on investment. especially when you're the only one investing.

@elliott__potter Hey @elliott__potter !! whats the paid entry tier like? we were actually looking at linq a couple of months ago, but the entry level pricing didn't make sense for us at the time. did it go down at all? We don't have the user base to justify using linq at that price point.

We’ve raised $27M for this moment: starting today, your agent gets an iPhone and can talk like a friend. Texting is the universal interface. Billions of people text every day, but until now, developers have been restricted from building on the most powerful channel to ever exist. Linq is a single API for iMessage, RCS, SMS, voice, and even FaceTime and Find My. Nothing for users to download. Nothing new to learn. We’re already powering @interaction, @pika_labs, @getlindy, @zocomputer, @joindimension, Tomo (and others we can’t name just yet) to bring this new ecosystem to life. Join them, and start building for free in our sandbox, linked below. Or comment and we’ll get you set up.

@sudoingX I'm running it with opus rn, on my claude subscription. its gonna expire soon, is it worth switching to a local model? How big is the drop off? i'm scared to switch to an OSS model, openclaw couldn't handle any model other than opus.

if you're trying to run hermes agent with ollama or lm studio, this is probably why it's not working well. compile llama.cpp from source. run it in server mode. point hermes at localhost:8080. yes, ollama and lm studio let you tweak some settings. but you're still going through their abstraction layer. when something breaks, you're debugging their wrapper on top of llama.cpp instead of just llama.cpp. their defaults aren't built for agent workloads. and when upstream llama.cpp ships a new flag or performance fix, you wait for them to catch up. compile once. you're running the same engine they're wrapping, just without the middleman.

@elijahmuraoka_ @obsdmd didn't even realize haha, with how cheap + how open their licenses are thought they were open

@GokulsVision @obsdmd everyone thinks obsidian is opensource lol... it's not

Imagine this: open-source Notion Full programmatic control over you own docs, data, and context Host, share, and collaborate with your team APIs + SKILL files built in by default Personal software is the future Anyone see anything like this? I need it If not, i’ll build it

Markdowns are the new pdf

@hazan0608 Investors are known to over invest, they are all sheep after all. One person goes in on the deal and then probably an army of VCs went in. The founder probably wouldn’t complain after getting extra $ too

Genuine question, why do recruiting tech platforms raise so much money?

@paraga My Openclaw agent had a hard time getting reliable information specifically for people enrichment, like I want my agent to have ability to do background search’s or like a background historical on people at scale.

Parallel is built for a world where agents are the primary users of the web. Agents can now autonomously pay per API call for web access via Parallel using MPP. parallelmpp.dev

@elijahmuraoka_ @49agents you can just have a shared vault, i had my openclaw agent set one up.

@49agents yeah biggest thing is team access, we have a startup