GBrain Provides Perfect Recall for OpenClaw Agents
If you want your OpenClaw or Hermes Agent to be able to have perfect total recall of all 10,000+ markdown files, GBrain is here to help. It's exactly my OpenClaw/Hermes Agent setup. MIT-licensed open source. Hope it helps you build your mini-AGI. https://t.co/yFpFU4pn5b
GBrain Runs on Hermes Agent with Simple Script
GBrain works on Hermes Agent, paste the same install script and you're good to go. https://t.co/yFpFU4pn5b
How to Access Anthropic Opus 4.6 Fast via Hermes Agent
Hermeticists— what's the best way to get Anthropic Opus 4.6 1M Fast working with Hermes Agent? OpenRouter seem to like anthropic/claude-opus-4.6-fast as the model name.
Distilled AI Makes Superintelligence Affordable for All
The thing is, thanks to mother models distilling intelligence into smaller models, everyone up and down the ability-to-pay curve will benefit as the models get to superintelligence
OpenClaw Now Runs Karpathy’s LLM Wiki with Pgvector
I got inspired by Karpathy’s LLM Wiki, implemented it in my OpenClaw and then extended it with my own skills and a full Postgres pgvector implementation. Want to be one of the first to try GBrain? This is my personal opinionated version...
Never Repeat Instructions: Automate Tasks with MECE Skills
How I get my claw to be a durable AI agent I never have to instruct twice Paste this into your OpenClaw's AGENTS.md or send it as a message: You are not allowed to do one-off work. If I ask you...
OpenClaw Beats All YouTube Summary Tools
I’ve tried everything out there for YouTube summary and diarization and the best with my OpenClaw hands down is https://t.co/vixKMpUmqO Well done @patelnav
SF Boosts Defender Budget Despite 35% Filing Drop, Data Hidden
SF's public defender got a 27% budget increase—even though criminal filings dropped 35%. But SF courts are hiding the numbers: they haven't reported a single data point to the state since 2020. https://t.co/szHhISyVO8
Claude Code's Bash Bypasses Write File Restrictions
I like how Claude Code allows bash so the agent can’t use Write File tool outside its workspace but it can seemingly “cat >>” to any file in the file system
SFO Shelters Waymo, Prioritizes Uber/Lyft Over Safety
SFO approved Waymo — then buried it at the Rental Car Center. Meanwhile, Uber and Lyft run 800K trips/month from the main garage. Zero safety rationale. Pure incumbent protection. https://t.co/53a332crtg
YC Alum Pranav Poised for Defining Tech‑Enabled PE Play
I think Pranav is one YC alum I have been tracking for a long time who is about to make the defining tech enabled PE play of our generation
Telegram Workflow Poised to Rival Desktop Claude Code
For real projects though I have mainly done detailed plans I then paste into @conductor_build on my desktop and run it in Claude Code from there But I could see the telegram path becoming even more viable as frontier models become...
Slack API Rate Limits Threaten YC’s OpenClaw Scaling
Slack API is so rate limited YC might have to switch off Slack because it is near unusable at scale with OpenClaw
YC AI Stack Offers $25k Credits, GStack Offers Skills
GStack doesn't give you money (it gives you free skills) but YC AI Stack can give you $25k in free credits.
Unpatched Claude Coding Flaw Lets Attackers Steal Cowork Files
Attackers can exfiltrate user files from Cowork by exploiting an unremediated vulnerability in Claude’s coding environment, which now extends to Cowork. The vulnerability was first identified in https://t.co/noHjpUqN1I chat before Cowork existed by Johann Rehberger, who disclosed the vulnerability. It...
Free Open‑Source /Design‑html Skill Supercharges Claude Code
GStack's /design-html is a secretly overpowered Claude Code skill I made with the help of prefix.js It's free, open source, and you can adapt it to whatever you want at https://t.co/54ECILbD9J
Autoplan Command Lets Wintermute AI Automate Tasks
I'm already using GStack with OpenClaw to build out a ton of fun stuff to make my OpenClaw AI (called Wintermute) way way smarter. Below, I'm improving how my AI helps me use X Just say autoplan and OpenClaw knows what...
Prompt‑driven Instant Software Lets Anyone Build Anything
"Ready to build" after one prompt is literally just-in-time software realized It's not a pipe dream. It's happening today. We don't have to be so precious about software anymore. With the right prompts, anyone can build anything Also: We should have 100x...
OpenClaw Soon to Control Desktop Browser via GStack
Sneak peek: Your OpenClaw is about to be able to control a browser on your computer using GStack Browser. 👀 https://t.co/Y8GxPYMlFm
GStack Receives 14 Security Fixes, Half From Community
14 security bug fixes just landed for GStack, half of which were community PR's. https://t.co/98jmCzQ38i
Leaking Confidential Memo Could Lead to Removal, Penalties
City Attorney David Chiu says whoever leaked a confidential legal memo could face investigations, penalties, and even removal from office. Oh who could it be? https://t.co/DTficyQQLI https://t.co/oNs3kEBy4R
GStack Browse Adds Headed Mode with Interactive Claude Sidebar
Now launching GStack Browse Before, /browse actions are by default headless, but now you can just ask for headed mode and you get a real steerable browser. The sidebar is an interactive Claude Code session that lets you navigate, run operations,...
OpenClaw Stays Alive, but Anthropic Models Soon Disabled
Internet: Would you please give me some grace? I am just vibe tweeting over here. OpenClaw is not "shut down" but for all intents and purposes many people are going to have to switch off Anthropic models even though they...
Need Portable Heat‑Deflecting Lap Mount for MacBook Pro
Ridiculous problem: I am looking at my MBPro (often running CI tests and evals locally) all the time in cars, planes, and just waiting someplace I need an attachment to the bottom of the MBPro that deflects heat so my lap...
Open‑source Community Set to Outshine Corporate AI Agents
A lot of the decacorn AI agent cos and labs other than OpenAI are trying to kill OpenClaw or replace it However: I think community and open source is too strong and the Apple II moment will actually happen for OpenClaw...
OpenClaw's Fate Will Test Anthropic's Strategic Gamble
Anthropic shutting down OpenClaw may turn out to be a strategic blunder, or strategic genius. The OpenClaw community will be the determiner of whether it is A or B. It's an interesting moment in history. Personally I never bet against...
New Tool Empowers Better Developer Experience Planning
I make tools on GStack for myself, so I am releasing /plan-devex-review today to help you create amazing Developer Experiences. Big thanks to Addy Osmani's DX framework for the inspiration here. https://t.co/i5Qy553Q8Q
Pedro's AI Breakthrough at Brex Will Reshape Organizations
What Pedro has built at Brex re: AI is nothing short of spectacular. I think we're going to look back on this time as one where Pedro went deep on a topic and put out a spike that will shake...
1M‑Token Context Enables Scalable Decision Traces
Decision traces are a big deal and now possible with 1M token context *sneak peek: one of my projects is launching soon and will be focused on decision traces in agentic engineering
GStack Overhaul: Streamlined and More Useful Than Ever
If you haven't been following, I've been pretty busy tidying up GStack and making it more useful https://t.co/xCo9sVsIxF
California's BASED Act Targets Big Tech Abuse
DC spent years trying to rein in Big Tech platform abuse and failed. With California's BASED Act (SB 1074), we're taking the fight to their backyard. Amazon, Apple, Google, Meta — no more rigging the game against startups. https://t.co/lsr9L3M6cv
Massive AI Training Data Leak Threatens U.S. Security
Wow. Incredible amount of SOTA training data now just available to China thanks to @mercor_ai leak. Every major lab. Billions and billions of value and a major national security issue.
Avoid the Drama Triangle: Confront Directly or Company Rotates
Every founder and CEO should read all they can about the drama triangle. If you cannot face another person directly, you will drag a third person in and call it process. That is how companies rot from the inside.
GStack Checkpointing Lets Claude Code Resume Full Context
GStack session checkpointing is useful when Claude Code starts getting worried about long context. Makes it easy to start a new window and pick up where you left off with full context from the prior workspace in a new, fresh...
Open‑source Memory System Drives GStack’s Self‑improving Software Factory
GStack does more to try to remember failures and learn from them. Open source lets us create a memory system to self-improve in the open. We're still on a path to a software factory, but we're going to build it...
Create What People Want, Speed Over Access
All the old rules are gone, there is only making something people want and what you can do with the tools that now everyone has It's not about access, it's about what you can do, and whether you *want* to go...
Speed of Creation Now Outweighs Age
Actually now age matters less than ever The only thing that matters is your velocity at which you can create things now
Data-Driven Safety Tech Reduces Crime, Saves Lives
There’s a lot of noise out there about public safety technology. Random people with hot takes or half-truths. People presenting themselves as experts after watching a few clips. Some more focused on their brand rather than building safer communities I care less...
37K LOC Daily Across 5 Projects, Speeding Up
Absolutely insane week for agentic engineering 37K LOC per day across 5 projects Still speeding up https://t.co/VR3utsduYx
GStack Browser Adds Multi‑Tab, Context Extraction, CSS Debugging
GStack's browser with sidebar now supports multiple tabs AND can be used to extract context from websites back to your Coding Agent, and can even read/alter/debug CSS for you (e.g. draw a box around a particular story on HN) Run /gstack-upgrade...
Community Fuels GStack's Rapid PR Progress
So many PR's to land tonight for GStack. The community is amazing and giving me so many good ideas and fixing bugs. Thank you to the #gstackfam https://t.co/88wmNnNrWw
GStack Adds Support for Factory Droid Integration
GStack now supports Factory Droid @FactoryAI Thanks for getting me to do it @matanSF https://t.co/SxAE6Q6mjK
GStack: Multi‑role Partner Accelerates Real Software in One Hour
GStack is not just a YC partner or a CEO vision coach. It’s a UX designer when you need it too. And a VP of Eng, a QA manager, and a release engineer too. It’s oriented around what you need...
Disabling Cameras to Protect Immigrants Spikes Car Thefts
After Richmond disabled its Flock cameras to "protect immigrants," car thefts jumped 33%. Immigrant shopkeepers begged to bring them back. Last week their city council finally listened. Opposing safety cameras is a luxury belief. https://t.co/4BecRL4WTL
Claude Code's Design Consultation Feature Impresses Users
I'm using /design-consultation and the ability to just talk Claude Code is so amazing https://t.co/gDv7r7mh1F
GStack
You don’t ever have to type this if you use GStack My /codex and /codex adversarial reviews can fire for CEO, design and eng reviews and they sharpen thinking significantly when using Claude Code as your primary agent
User Sovereignty Trumps AI Recommendations, Keeps Humans Central
New GStack ETHOS.md rule User Sovereignty: AI models recommend. Users decide. This is the one rule that overrides all others. Two AI models agreeing on a change is a strong signal. It is not a mandate. The user always has context that...
User Sovereignty: Models Recommend, Users Decide
I'm already bumping up against interesting moments between models and myself, the developer I had to add this today to ETHOS.md **User sovereignty.** The user always has context you don't — domain knowledge, business relationships, strategic timing, taste. When you and another...
Human Agency Beats Tools for Truly New Challenges
Remixing tasks that are in distribution is easy It’s doing new things that are still hard and require human agency and taste No amount of harnesses or special skills (including GStack) is a replacement for you knowing what you want and pushing...
Simple GStack Workflow: /Plan‑eng‑review Then /Ship
This is why on GStack I usually just run /plan-eng-review and /ship and it works