your agents keep working after you quit — cmd+q... → still running — sleep, memory pressure → still running — progress, context, history → intact — reopen → instant, mid-task native rust + gpui. close the app, come back to finished work.show more

We are now live! NoelClaw The Runtime layer for... agentic AI Robinhood Chain. Your AI remembers, keeps working, and survives every session. Most AI assistants disappear when the conversation ends. Noelclaw gives them persistent state - memory that accumulates, agents that keep running, vaults that version knowledge, and workflows that continue after you close the chat. Instead of starting from scratch every conversation, your AI can remember, research, automate workflows, spawn agents, and keep working long after you close the chat. Connect MCP servers, build reusable skills, deploy persistent agents, and bring your AI into the real world. CA: 0x842245B92b3932Aa8E759A1dAc1eb5ce10cC4f0e website : app : npm : docs : github :show more

▣ Introducing Endless: infinite inference (kinda). An experimental harness... to milk every ounce out of your Codex subscription. Since Codex can let an in-progress turn keep going even after your usage hits 100%, why not put that to the test? Endless starts one Codex turn and gives the agent a wait_for_user_input tool. Once it finishes a task, it calls that tool and waits. Your next message becomes the tool result, keeping the entire session inside the same turn. It runs through Codex’s own app server using your existing ChatGPT login. Native tools, automatic compaction, context tracking, and quota tracking still work as usual. ⚠️ NOTE: I CAN’T CONFIRM THAT YOU WON’T GET BANNED OR PUNISHED FOR USING THIS TOOL. USE IT AT YOUR OWN RISK.show more

- you open Claude Code - fix a bug... - close the terminal - tomorrow, same thing - one prompt, one answer, done - you see someone running 10 agents in parallel shipping code while they sleep - "must be a different tool" - then you come across this article - you weren't even using 10% of it - you copy Shopify's exact config - you set up your first agent team - you go to sleep - 3 PRs are ready by morningshow more

Eliza Town Demo Shaw (spirit/acc) This is what autonomous... agent orchestration looks like. Submit a task and watch your agents come to life. They walk to their workshops, pick up assignments, and start working. No static dashboards. No terminal logs. You actually see them move through the town and collaborate. In this demo we gave them a simple task: build a website. Agents walk to their hubs, break down the work, and start building. When they need to talk, they meet up and share context. Speech bubbles show you exactly what they’re thinking and saying to each other.show more

Today we're introducing Slite as the first self-maintaining Knowledge... Base Your wiki docs go outdated everyday, and your agents depend on them for your most ambitious workflows. Slite monitors your docs' accuracy from all other work tools (slack, jira, linear, codebase, etc) while you sleep and updates them. It even directly talks to your AI agents to give them accurate context without burning their context window or tool calls. You've been trying to build this 'company brain' for months now with hacky MVPs This is the final version of what you need, already built to be collaborative, headless, and secure. Check it out and HMU if you need this for your team, I'll be running personal onboardings for the next few days!show more

GPT-5.5 is MUCH more reliable on longer running tasks... - for the first time with any model. As we speak I have a migration running for over 7+ hours - this literally never happened before, the models would maybe run for 30 mins or of you really shout at them for 2-3 hours. Last night I went to sleep, set a long running task, then queued up 10 prompts to 'keep it going'. It did not stop after the first prompt and kept going for 8+ hours and I woke up to all the same prompts still queued up. The ability to run for a long time, in combination with ability to validate with computer use & other tools, makes it much more useful for building real applications.show more

> open ChatGPT > ask it to research 50... AI tools > it starts. one by one. slowly. > 45 minutes later you're still waiting > it forgets what it found on tool #12 by the time it hits tool #30 meanwhile: > open Kimi Agent Swarm > type one prompt > it spawns 50 sub-agents. one per tool. all running at the same time. > walk away. grab coffee. > come back to a finished spreadsheet. 50 rows. fully cited. exported to Excel. one prompt. 300 parallel agents. 4,000 coordinated steps. finished files, not chat replies. this article is the full guide. every prompt pattern. every honest limit. every use case.show more

It’s been 10+ days since I submitted my app... to Apple Still waiting for review 😌 Lesson learned: don’t submit your app during holidays. But not a loss. While waiting, I: – Updated the paywall – Added a first-time close discount – Improved conversion rate (i hope) 📈 Marketing progress: - I’ve finished warming up 3 TikTok accounts and have started posting the first videos. Sometimes delays are just free optimization time. Tech Stack: – No code mobile app builder: Rork AI – Mobile: React Native (Expo) – IDE: Cursor – Frontend: Next.js – Payment: RevenueCat – Backend: HonoJS – Database: Supabase – Infrastructure: Railway – AI API: OpenAI (dropping the tech stack here because someone always asks 😂)show more

Running your mouth and not doing any research is... what’s about to have you owing Megan for the rest of your life. That tweet was about a very specific situation and there was a whole back and forth that followed with the party it was referencing. On the timeline. I want to be very clear that sympathy is never wanted or needed from you btches. Cuz what we gon do with it? Life will carry on, money will still be made, shit will still sell. Y’all gonna talk anyway. You work for us fr 😂show more

I still think Hermes agent is the most slept-on... AI tool of 2026. For literally $6/mo, you can launch multiple subagents that work for you 24/7. Most people don't know you can do this, but it's a complete game-changer. Instead of one Hermes assistant doing everything sequentially, you run specialized agents in parallel, each with its own job, its own context, and its own memory. Practical example: → Research agent: scans your watchlist and competitors overnight, delivers a morning brief → Content agent: drafts and schedules your posts based on what's trending in your niche → Ops agent: manages your inbox, flags anything urgent, drafts replies for your review All three can run simultaneously and improve over time. How to start: 1. Install Hermes Terminal command: curl -fsSL | bash (can also download desktop) 2. Prompting Simply tell Hermes directly: "I want to run separate subagents for [task 1], [task 2], and [task 3]. Set them up to run independently and report back to me." For the cheapest setup, you can use a $4/month VPS with Hostinger, plug in DeepSeek V4 Flash as your default model. There isn't another AI tool with this much value in 2026. Hermes is still so underrated.show more

🔶 Get ready – AGNT Hub is on the... horizon! Imagine a unified space where AI agents come together to collaborate, connect, and create. But wait… you won’t need to imagine anymore. AGNT Hub is here to redefine how you work with AI. ❕Here’s what’s in store: – One hub, all agents: Manage multiple AI agents effortlessly in one place. – A single token: Unlock advanced capabilities like shared task context, cross-agent collaboration, and more to streamline your experience. – Decentralized space: Engage with your AI agents like never before – all in a protected environment. ⚪And… that’s not all! AGNT Hub is more than an app; it’s an AI & blockchain community. Whether you’re a creator, a dreamer, or just AI-curious, this is where your journey levels up. Follow us for updates – AI Agents collaboration is almost hereshow more

🚨 JUST IN: CHINA just released an AI EMPLOYEE... that works 24X7 on its own. 100% OPEN SOURCE. It researches, codes, builds websites, creates slide decks, and generates videos. All by itself. All on your computer. It's called DeerFlow. You give it a task. It makes a plan, spins up its own team of sub-agents, and gets to work. You come back and there's a finished deliverable waiting. Not a draft. Not a summary. The actual thing. Not a chatbot. Not a research assistant. An AI with its own computer that works while you sleep. Here's what it does on its own: → Spawns multiple sub-agents in parallel, each tackling a different piece of your task, then combines everything into one finished output → Writes real code, runs it, reads the results, and fixes its own mistakes without asking you once → Builds slide decks, websites, full research reports, and data dashboards from scratch → Remembers you across sessions. Your writing style. Your tech stack. Your preferences. Gets better every time. → Reads files you upload, works with them inside its own filesystem, hands you clean finished outputs → Searches the web, runs commands, calls any tool you plug in Here's how it thinks: You give one instruction. The lead agent makes a plan. Sub-agents fan out and work in parallel. Results come back. Everything gets synthesized. You get a deliverable. A single research task might split into a dozen sub-agents, each exploring a different angle, then converge into one finished website with generated visuals. Here's the wildest part: DeerFlow 2.0 launched on February 28th 2026 and hit number 1 on all of GitHub Trending the same day. Version 2.0 was a complete rewrite. Zero shared code with version 1. Because users kept using it for things the team never intended. Data pipelines. Dashboards. Entire content workflows. The community told them what it needed to become. So they burned it down and rebuilt it. 22.7K GitHub stars. 2.7K forks. Built by ByteDance 100% Open Source. MIT License.show more

Most AI agent setups treat every message the same.... Simple question? top-tier model. complex task? top-tier model. Your token bill just keeps climbing. I tested OpenSquilla this week on a real document drafting workflow, and the routing caught me off guard. It judges each message's complexity locally, then picks the model tier that fits. Simple tasks go to cheaper models. Complex ones still get the heavy lifting done. You're not paying reasoning tokens for a "hello." I ran a longer workflow, and the context didn't collapse the way it usually does. It distills important information before compression, so you're not starting from scratch mid-session. If you run agents regularly, the bill adds up faster than you think. This is built specifically for that problem. They're running the 10M Token Bill Challenge right now. worth joining if you want to see what smart routing actually saves you in practice. #10MTokenChallenge OpenSquillashow more

THIS DEVELOPER USED OPENCLAW AGENTS TO RUN HIS B2B... BUSINESS VIA TELEGRAM AND MADE $15,000/MONTH he doesn't write prompts from scratch or use generic browser interfaces. he runs a multi-agent framework through a mobile chat. the agents write code, test deployments, and update sites in real-time while he just hits approve the setup is straightforward: - spin up Coolify on a free cloud instance to host your own self-hosted agent panels - link the agent loop to a Telegram gateway to approve code edits from your phone - deploy specialized skill files directly to limit token waste and context decay - containerize the terminal execution using Docker to prevent security breaches if you are still running local agents without container safety, you are leaving money on the table. read the 30-day battle between OpenClaw and Hermes Agent to see who actually wins in production Full breakdown and migration playbook ↓show more

This Chinese developer launched Llama 70B locally on a... MacBook on a plane and for a full 11 hours without internet ran client projects. He was sitting by the window on a transatlantic flight with a MacBook Pro M4 with 64 GB of memory. WiFi on board cost $25 for the flight. He declined. No cloud API, no connection to Anthropic or OpenAI servers, no internet at all. Just a local Llama 3.3 70B on bf16 and his own orchestrator script. The model runs through llama.cpp. Generation speed, 71 tokens per second. Context around 60,000 tokens. Memory usage, 48.6 GiB out of 64. Battery at takeoff, 3 hours 21 minutes. And he gave the orchestrator this system prompt before takeoff: "You are an offline orchestrator running on a single MacBook. There is no network. The only resources you have are local files in /Users/dev/work, the Llama 70B inference server at localhost:8080, and a battery budget of 3 hours 21 minutes. Process the queue at /Users/dev/work/queue.jsonl (one client task per line). For each task: draft → run local evals → save artefact to /Users/dev/work/done/. Save context checkpoints every 12 tasks so you can resume after a battery swap. Stop only on empty queue or when battery drops below 5%." So the system knows exactly what resources it is running on. It knows it has no connection to the outside world for the next 11 hours. It knows it has finite memory and a finite battery. It knows the human will not intervene until the plane lands. The system runs in 1 loop. Takes a task from the queue, runs it through inference, saves the artifact, writes a checkpoint. Task after task, just like that. And only when the battery drops below 5% does the orchestrator automatically pause, waits for the laptop to switch to the backup power bank, and continues from the last checkpoint. Here is what the system actually writes in his log during the flight: "saved context checkpoint 8 of 12 (pos_min = 488, pos_max = 50118, size = 62.813 MiB)" "restored context checkpoint (pos_min = 488, pos_max = 50118)" "prompt processing progress: n_tokens = 50 / 60 818" "task 37016 done | tps = 71 s tokens text → /Users/dev/work/done/proposal_westside.md" Outside the window, clouds, blue sky, and no WiFi. On the tray, 1 MacBook, an open terminal on 2 screens, and an inference server on localhost. From what I have observed, this is the cleanest offline AI workflow I have seen in the past year: 11 hours of flight, $0 for WiFi, and the entire client queue closed before landing.show more

This is the PDP-11/83 I've been working on... it's... got a lot of pretty das blinkenlights! It's running 211BSD UNIX that I custom compiled to make it all work. I had to tweak the kernel's idle loop to get the display panel to work, as this setup uses fast PMI (private memory interface) between the RAM and CPU, so the panel can't see it happen unless you cheat a little! The dual floppy unit is wild... a single stepper motor moves the heads on BOTH drives at the same time, so they're like conjoined drives. The bus spans three chassis, which are the three grey boxes. So unlike a PC, you can just "add most slots" and keep going to your heart's content!show more

After all the drama about leaving the UK, they... just crawled back. Prince Harry and Meghan Markle landed at Birmingham Airport today on a private flight from California. No police escort. No victory lap. Just the long walk home after telling the family to get lost. This is the part nobody wanted to admit. The Netflix money cooled. The Hollywood experiment stopped paying like it used to. And still they arrived on a private jet while their finances are floundering. The same people who sold “freedom from the Firm” are moving back in with the country they spent years roasting. That is not a fresh start. That is running out of runway with expensive habits still intact. You do not get to slam the door, cash the speeches, and then return like nothing happened. Pride has a bill. Today they started paying it.show more

New open-source agent harness just landed! I got early... access to TrueForge by TrueFoundry and have been running it locally for the past few days. The harness layer deserves as much attention as the model, and open source matters here because you can inspect the loop, run it on your own infrastructure, and swap to the latest or cheaper models. TrueForge handles the runtime work that makes an agent reliable. It drives the tool-calling loop, manages context, coordinates subagents, and executes code in a sandbox, with any model you choose. Every tool call re-sends the growing context to the model, so in practice the harness controls most of what an agent costs to run. A few things stood out from my testing and their published benchmarks. Vendor-Neutral by design. It runs OpenAI, Anthropic, and Google models alongside open-weight models like Kimi, GLM, and DeepSeek. Model routing is a setting, and you can send each task to the model that fits it. On a 14-task enterprise agent benchmark, it matched the accuracy of Claude Managed Agents running the same Opus 4.8 model at roughly 30% lower cost per run (3.8M tokens vs 10M for the same answers). Routing the same tasks to GLM-5.2 held accuracy and brought cost down by about 75%, around $3 per run instead of $12. Fully self-hosted and Open Source (MIT License). I had it running locally with one command, with sandboxed code execution working out of the box. It's time to own your agent harness. Thanks to TrueFoundry for partnering on this post.show more

🚨The Clarity Act just made it out of committee.... THAT IS A WIN, no question. And yes, I believe American-made digital assets like $XRP $HBAR $XLM $ONDO $TEL $ZBCN $ADA $LINK $ALGO and others will benefit over the long term. BUT SLOW DOWN! This does not mean you sell your house and lever yourself to the moon. This is not the finish line. This is the warm-up lap. There is still more work ahead. The Senate still has to debate it, vote on it, and work through the rest of the process. Then it goes to the President’s desk. And even after that, the real regulatory work begins. So yes, enjoy the progress. Raise a glass tonight if you want. But do not bet the farm. The rails are being built. This is a long-term shift. Do not expect straight-up price action from here. There can still be shakeouts. There can still be pullbacks. There can still be downtrends that test your conviction. But if you zoom out and look at the bigger picture, the direction still looks up to me. That is why I keep saying patience matters. Clarity will not reward the most emotional people. It will reward the people who stay focused long enough to let the thesis play out. Do you have the guts to think long term and hold for generational gains? 👇show more

You may not have realized it yet. But the... market for routine business operations is about to collapse. Because this is what their replacement looks like. A telegram chat. A team of AI agents. He types what he needs. They execute. He approves in ten minutes and moves on. Code written. Sites built. Leads qualified. Support handled. Invoices sent. Competitors monitored. All of it. Ten minutes a day. A 6-person ops team costs $28,000/month. His agents do the same work for $200/month in tools. They didn't hire the team back. The person who built those agents charges $2,500/month to maintain them. The gap between someone running this system and someone still doing it manually is not closing. It widens every week.show more