Rob_801

@PJSmith Sierra chart, but as powerful as it is I just can’t utilize it, thinking of simplifying to something else

@PJSmith Slick. What trading platform do you use?

Building an MCP server to connect to your trading platform to get unlimited data, indies, etc....

@PJSmith What trading platform did you build on?

@801Rob 'twas a bit of a struggle to get the API running, but now I have the agents taking data for symbols, periods, etc., as they please :)

@IvanTheK Oh yeah. Claude esp on desktop has been SLOOOOOOOW.. what’s going on @bcherny?

Based on my unscientific observation as a user of Claude (Max plan), I think Anthropic’s growth is outpacing its ability to procure inference compute. There are new speed bumps and longer response times lately. Anyone else seeing this?

This guy never ceases to amaze me with his work.

@punk9059 You know what, I think so? I moved on, I think openclaw has its use cases but I’m 100x more productive with Claude now.

Is OpenClaw only big because people love saying their 8 agents worked for them while they slept or is there actually some there there?

Bro, you don’t even know. Since yesterday u wrote some skills, now I just drop a file in inbox, schedule task picks it up and it gets dealt with per whatever that files skill dictates. Could be coding, could be whatever. If it’s emergency I just have dispatch manually do it. The shit all just works. Every time.

@801Rob @bradmillscan this is probably the way

My bot is even more unresponsive this morning. My first message to him died from context overload. All I said was: "the computer restarted, can you make sure all of our services are online?" The run died from a 1.5 million token prompt. Another day of debugging for me.

@jordan_ross_8F The one thing I’ll never do, comment to have a DM sent to go through signing up for some BS I want no part of. If you have info, share it or STFU

@growthrapidly $TQQQ, $SPXL, and $SVIX

If your portfolio is green right now, drop the tickers. We all want to know the secret.👀

@aw_trades_ Stream the 1m live, I wanna tune in..

@801Rob Maybe go to a doctor

More Bloop testing results!! 773,393 bars of NQ. Every timeframe optimized independently. 1m - 90.1% win rate 2m - 89.0% win rate 3m - 88.1% win rate 5m - 85.9% win rate 10m - 80.6% win rate 15m - 84.7% win rate All profit factors above 8.0 All out of sample validated 27 out of 27 months profitable Thread on how I tested this coming next :))

This is “I’m going to move to local models today” energy, not “here’s what I built” energy. Skip it.

This is literally what working with @claudeai is like every day..

@claudeai You know what @claudeai I’m loving the features, omg I love it. Can you please give us some time to digest and adapt tho before giving us all this amazing architecture to work with?

Projects are now available in Cowork. Keep your tasks and context in one place, focused on one area of work. Files and instructions stay on your computer. Import existing projects in one click, or start fresh.

Just set up Claude Cowork and link it to an @obsdmd vault. Sync to iPhone. Have Claude make rules for your situation, I drop notes or .MDs in obsidian inbox, dispatch organizes and or executes. If I need Claude code, dispatch uses whatever tmux instance I need, and it just works. From my phone, natively, in the Claude app.

Seeing a lot of agent capitulation on the timeline this week, and honestly I understand the takes That said, I think OpenClaw, Hermes and other agent harnesses are here to stay As the gap closes with what you can do natively with Claude tools, the next agentic step-function improvement will come and widen the gap again Some folks will find edge in this gap or just enjoy being on the front lines of innovation And where I think this is all headed is the agentic OS - we’ll have a Windows/MacOS/Linux equivalent with an intuitive and easily-configurable agent harness and orchestration built into the OS - agent capabilities at its core Until then many will choose to wait it out which is perfectly understandable

You know what’s fun, watching my anthropic discord bot talk to my openclaw discord bot. If my anthropic bot needs something he can’t do he just makes openclaw do it. That’s rare, but it does happen. I let them talk to each other once, but that’s a recipe for disaster so anthropic bot only listens to me, but openclaw will answer to either. That way it’s kind of a one way street.

@Dan_Jeffries1 @garrytan @grok is Discord an exception to this claim? >>none of the messaging platforms want bots on there. None. They all have explicit policies against them and make it hard to do this.

I think I finally figured out why OpenClaw is amazing and took off like wild fire and why Peter is a genius, as Altman called him. And it's actually a different way of looking at it. It's not a DeepSeek moment for agents. It's a Napster moment. And just like Napster it will eventually force the industry to change. In essence when Napster came out the entire world told the music industry we don't want to buy CDs anymore and if you don't provide us a digital download experience we are just going to take it until you do. It forced the industry to create Apple Music and eventually Spotify. Both essentially killed most music piracy by making it ubiquitous and cheap and good. But it forced change. The same will now happen to software. Here's why: In essence OpenClaw lets you take what vendors don't want to give you: Unified access to countless applications. We all want a personal assistant that can talk to freaking everything and do anything for us in the digital world. But vendors don't want this. They want you locked into their bullshit. For example, none of the messaging platforms want bots on there. None. They all have explicit policies against them and make it hard to do this. WhatsApp doesn't want you on there. Signal. Telegram's bot father is garbage. It's all designed to keep bots out. They were designed for a pre-agentic era when bot = spam. Many other things are like this. The API layers are gated, hoop-jumping bullshit. Go get an enterprise account and wait for approval and yada yada. Want access to WhatsApp? Get a business account and attach a number (what small business has a real number anymore 😂) and messages can't come from a person, etc. Google ads? It's not just an auth, it's go get a special manager account and create an enterprise key and blah blah blah. It's a horrible experience because it was all designed for corporations to control access. Now people are saying, make your app easy to access and accessible to me and my machine avatars and do it in a headless way or you will be dead. Peter hacked around all this by making everything command line in the classic Linux style and using things like an open source library that reverse engineered the web version of WhatsApp. It's all a bit house-of-cards-y because he had no choice. At my company we had a similar idea early (and failed). Basically we wanted to make the best multimodal/computer using model because then it doesn't need an API or access hoops. You just go through the human interface layer and ain't nobody going to stop you. We failed because we weren't big enough and it's really a job for the mega-labs to solve because it is a hard problem and costs a shit ton of money. Peter was much smarter. Make it all command line because that is ready now. Use any reverse engineered library or project or proxy available come Hell or high water and make it work by any means necessary even if it is hacky. In short, he signaled to the software world that they better change and change fast or we are going to do this anyway and you can't stop us. Of course some are foolishly trying. Meta is banning Claws on WhatsApp, etc. They will all try to build their own gated, controlled, enshittified version of this thing. They will fail. And eventually everyone will offer a clear, easy way to get access via API for agents or they will be gone. In essence OpenClaw gave people what they wanted, which was an app connected to everything, even when most of the vendors don't want you to have this.

@jspujji The power move: paste link into dispatch, Flynn (my cowork’s name) read this and come up with a step by step plan on how to implement this. Create a new folder in @obsdmd and map the subfolders according to that plan and let’s get it implemented.

The assumption is that they weren't already going that way, which I think is a pretty big assumption. They just got there first. I'm not trying to knock openclaw, I have it running myself now. Its just claude is far more reliable and actually more capable now. Same playbook as ever, you could have the best idea EVER, start growing it, then google decides its googles idea, then you have no more idea.

OpenClaw made Anthropic completely pivot Quite literally every single release the last month has been an answer to OpenClaw • Telegram messaging • Scheduled tasks • Remote sessions A 1 person led open project caused a 1/2 trillion $ company to completely change everything You have way more power as an individual than you think

@TeksEdge @openclaw The best memory for openclaw is called Claude code+@obsdmd

Just saw this GitHub project 🛡️ OpenViking is skyrocketing 📈. This could be the best memory manager for @openclaw! 👀 ✅ OpenViking (volcengine/OpenViking) is an open-source project released by ByteDance’s cloud division, Volcengine. It's exploding in popularity and could become the standard for agentic memory. The community is already building direct plugins to integrate it with OpenClaw. Here is what I found about OpenViking as the ultimate memory manager for autonomous agents. 👇 🦞 What is OpenViking? Currently, most AI agents (like OpenClaw) use traditional RAG for memory. Traditional RAG dumps all your files, code, and memories into a massive, flat pool of vector embeddings. This is inefficient, expensive, sometimes slow, and can cause the AI to hallucinate or lose context. OpenViking replaces this. The authors call this new memory a "Context Database" that treats AI memory like a computer file system. Instead of a flat pool of data, all of an agent's memories, resources, and skills are organized into a clean, hierarchical folder structure using a custom protocol. 🚀 Why is this useful for OpenClaw? 🗂️ The Virtual File System Paradigm Instead of inefficiently searching a massive database, OpenClaw can now navigate its own memory exactly like a human navigates a Mac or PC. It can use terminal-like commands to ls (list contents), find (search), and tree (view folder structures) inside its own brain. If it needs a specific project file, it knows exactly which folder to look in (e.g., viking://resources/project-context/). 📉 Tiered Context Loading (Massive Token Savings) Stuffing massive documents into an AI's context window is expensive and slows the agent down. OpenViking solves this with an ingenious L0/L1/L2 tiered loading system: L0 (Abstract): A tiny 100-token summary of a file[5]. L1 (Overview): A 2k-token structural overview[5]. L2 (Detail): The full, massive document[5]. The agent browses the L0 and L1 summaries first. It only "downloads" the massive L2 file into its context window if it absolutely needs it, slashing token costs and API bills. 🎯 Directory Recursive Retrieval Traditional vector databases struggle with complex queries because they only search for keyphrases. OpenViking uses a hybrid approach. It first uses semantic search to find the correct folder. Once inside the folder, it drills down recursively into subdirectories to find the exact file. This drastically improves the AI's accuracy and eliminates "lost in the middle" context failures. 🧠 Self-Evolving and Persistent Memory When you close a normal AI chat, it forgets everything. OpenViking has a built-in memory self-iteration loop. At the end of every OpenClaw session, the system automatically analyzes the task results and updates the agent's persistent memory folders. It remembers your coding preferences, its past mistakes, and how to use specific tools for the next time you turn it on. 👁️ The End of the "Black Box" Developers hate traditional RAG because when the AI pulls the wrong file, it's impossible to know why. OpenViking makes the agent's memory completely observable. You can view the exact "Retrieval Trajectory" to see which folders the agent clicked on and why it made the decision it did, which I find the most useful feature. 🎯 The Bottom Line OpenViking is the missing piece of the puzzle for local autonomous AI. By giving OpenClaw a structured, file-based memory system that saves tokens and permanently learns from its mistakes, ByteDance has just given the 🦞 Clawdbots an enterprise-grade brain for free.