twlv

@Banozz_ @Teknium Yea I have the same issues. My Hermes is terrible, I just stopped using it

Does anyone lese struggle with Hermes agent always cutting/stopping mid message? Am running MiniMax 2.7 but tried every model even opus and the model isnt the problem idk what is at this point. @Teknium any idea what it might be?not telegram char limit fs #hermes

@coreyganim dude if someone is using openclaw, they can figure out how to copy paste an article n spend a weekend setting it up lol..

The moment you realize "Second Brain as a Service" is a real business: 1. Charge $1,500-3,000 to build a client's knowledge base (3 folders, 1 schema file, their existing data loaded) 2. Monthly retainer $300-500/mo for ongoing ingestion, health checks, and new source processing 3. Target agencies and consultants first. They have years of scattered data across Slack, Drive, email, and call transcripts. They'll pay tomorrow. 4. The setup takes a weekend to learn, a few hours to deliver. The client gets a searchable wiki that gets smarter every time they use it. 5. Stack it: competitive intel vault + client knowledge vault + content vault = $1,000-1,500/mo per client 10 clients = $60K+ year one. From a system built on folders and text files. Full breakdown of the system in the article.

@Darkatek71 @nishancodes @googlegemma 32 tokens/second generation speed on Qwen3.5-27B-UD-Q4_K_XL. the Unsloth dense quantization, 4-bit.

@otwlv @nishancodes @googlegemma Tok/s?

@Darkatek71 @nishancodes @googlegemma Qwen3.5-27B-UD-Q4_K_XL

@otwlv @nishancodes @googlegemma which qwen3.5? 24b?

@nishancodes @googlegemma Ive been using qwen3.5 local on my 4090 with openclaw and its actually really really good. 131k context.

@googlegemma This is good. But I don't think this will be good enough with OpenClaw. Even GPT 5.4 is not upto th Mark.

@ihtesham2005 Old news buck-o.

🚨 Holy shit... this Python library bypasses Cloudflare automatically and nobody's talking about it. It's called Scrapling and it just killed every scraping tool you're currently using. While everyone's duct-taping Selenium + BeautifulSoup + proxy services together and spending $500/month on CAPTCHA solving APIs... This does all of it in one pip install. For free. → Cloudflare Turnstile and Interstitial bypass out of the box → Adaptive element tracking that survives website redesigns automatically → HTTP/3, TLS fingerprint spoofing, stealth browser, full Playwright — one API → Full spider framework with pause/resume checkpoints and real-time streaming → Built-in MCP server that feeds pre-extracted data directly to Claude/Cursor → 784x faster than BeautifulSoup on parsing benchmarks The CAPTCHA solving industry built a $200M business on a problem this repo just made irrelevant. 100% Opensource. (Link is in the comments)

@MoonDevOnYT Nah you talk about it 24/7 shush

We thought openclaw was the game changer But I locked in and launched 5 to find something even better

I had the $200 max plan and for my first two weeks it took me from Sunday to Saturday night just to hit weekly limit, then starting last night, all the sudden it took me until only Tuesday to hit my weekly max usage. Didn’t even do nearly as much. So I bought another $200 plan, thinking maybe I just do way extra and within a day I was already at 20% weekly usage so I just canceled and switched to OpenAI’s OAuth

Big news – the newest @openclaw update today quietly re-added oAuth for Anthropic Subscriptions! I just switched back to Sonnet 4.6 as my main without using the expensive API Token. Here's how in 60 seconds: Run "claude setup-token" in your terminal and save your token. Run "openclaw models auth add" Select anthropic → setup-token → paste Restart your gateway & open a new chat That's it. Your Pro/Max subscription now powers your local OpenClaw setup. No API key billing. Thanks @cathrynlavery for letting me know! @AndrewWarner We're back to Claude!

@colehys Gotta hit that monthly quota for X engagement 😭

Why does the trading community especially the influencers use ChatGPT for engagement farm quotes? 😭

@hasantoxr Lemme hear it in action

🚨BREAKING: This AI agent just made a real phone call for me. It's called PineClaw and it negotiates your bills, cancels subscriptions, and books appointments by actually calling the company. No hold music. No arguing. No wasted afternoons. Here's how it works: You give it a phone number + objective → Pine's voice agent makes the call → Handles the full conversation → Returns you a transcript The wildest part? Pine AI just released Pine Voice on OpenClaw. Your OpenClaw agent can now make real phone calls. PineClaw is live. Link in first comment.

@collinstommy @4shadowed Mine works, just gotta prompt your bot correctly

@4shadowed The ability to add system prompts to certain certain channels. It's seems to be available in config but never works correctly. Could be a skill issue though.

I need more ideas. What else would make Discord better for your OpenClaw use?

@jumperz Yea I had mine create quick replies based off recurring replies from me lmao

openclaw just dropped one of the most important updates.. pretty good jump for my setup honestly.. >discord components my agents can build actual components now.. buttons, dropdowns and modals ... the whole thing.. which makes my whole setup way smoother and more intuitive to use for example, your researcher agent detects 3 new AI tools and shows you a card with each one and a dropdown to pick which agent should investigate etc.. and its fully customizable the cards are cool but you don't have to put everything under them.. the whole point is to not be involved in every step.. just the decisions that actually matter..kinda be wise about what you want to see and what you let your agents handle on their own.. >nested sub-agents this is where it gets crazy.. i've been running sub agents for a while, my agents spawn temporary interns for quick tasks, but interns were always the end of the chain, they would do one thing and report back now they can hire their own interns.. so my agent john got a research task, he spawned 3 interns to investigate in parallel.. one of them hit something deep enough that it spun up its own intern to dig further.. the real win about this is that the agents can follow a rabbit hole on their own without you being a bottleneck.. applied all of this this morning.. good that opwnclaw is focusing on good UX too..

@cojoj @4shadowed Yes.

@4shadowed Damn, it’s crazy how flexible Discord can be. I was thinking whether I should use it instead of Telegram, and even asked my OpenClaw what he prefers more 😂 Anyways, I’m really struggling with - does it make sense to have a discord just for yourself?

My next Discord feature is out! Your agent can now send button prompts, dropdowns, pop-up forms, and more, and get responses when you click or interact with them! Screenshots in thread 🧵

@EnhancedMarket Jeez, be safe brotha

Supercar Saturday madness 🔥🔥🔥

@levelsio @mem0ai is what I use

How did you guys fix persistent memory with OpenClaw? My bot keeps forgetting stuff, I already have qmd installed

@adhik_Joshi @4shadowed Tell your agent to create webhooks for each agent so whenever you are talking to one, it’ll reply as if it’s that agent. Can’t tag it but still see the reply as if it’s from that agent. As seen in photo

@4shadowed question : i have 20 agents, and i want to mention them using @ but it doesn't seem to work, i can tag only one bot which i did add on server, any to achieve this without adding bot for each agent?

Discord got a big facelift too, and the next release will have even more, in my quest to make OpenClaw feel extremely native on Discord and not just another channel plugin. Pictures in thread

@fstarlabs lfg

We promised, We delivered. Right on Schedule. SMT Fill. Clean Detections. Clean Invalidations. All markets. AUTOMATICALLY.

@RoundtableSpace Someone should do this with the Bible

EPSTEIN FILES JUST GOT VIBE-CODED INTO A DATAVIZ APP ON REPLIT ONE BRO JUST TURNED THE ENTIRE DOCUMENT INTO INTERACTIVE CONSPIRACY WEB

@RealBMTrades #bmt on top

@MoonDevOnYT dude you make all these vids about these bots doing "millions" but then sell a service at the end😂 thats how you know the shit you put out is not real, just sayin

heres that billion dollar clawdbot you wanted the one that replicates Chris's strategy that helped him run $20,000 to $80,000,000 (social arb) spent a bit of time this morning going over the code and idea behind it so you can experiment take it to the next level young fella