1M‑token Context Window Runs On
Downloading now... 1M token context window with supposedly usable coding agent capability all on a 128GB Macbook Pro is 🤯 https://t.co/otTL8NZMvV
Leftist Policies, Not Markets, Drive Housing Shortage
NIMBY Leftists never believe that it was their own terrible anti-market policies that created housing shortages. The subsidized demand, the clamped supply, the vilification of landlords and housing builders. Of course they hate the markets. We should vote them all...
Founders Use Humor to Gauge Startup Well‑Being
Hermann Hesse says humor is the escape hatch for people who can’t be saints, won’t be degenerates, and refuse the safe bourgeois script. Feels like most founders I know. Among YC partners, our "canary" on whether we are...
GStack v1.28 Adds Download, Headed Mode, llms.txt
Just dropped GStack v1.28 GStack Browser can now download items, and run in headed configuration mode with anti-bot detection in using Xvfb on headless Linux containers (like your claw/hermes) Added llms.txt so agents of all kinds can use all the skills...
GBrain v0.29 Introduces Salience: Detect Emotional Highlights
GBrain v0.29 and v0.29.1 dropped v0.29 enables salience: what is emotionally charged? what is important to a human being? What jumps out as unusual or interesting or particularly powerful? https://t.co/Nau5TljEFQ
GBrain Outperforms MemPalace on LongMemEval Benchmark
GBrain beats MemPalace on LongMemEval And I published the benchmarks and open source eval repo to prove it https://t.co/UNtSBWMxGa
Adopt Thin Harness, Fat Skills to Cut Bugs
Thin Harness / Fat Skills is actually a powerful mindset shift that helps you reduce your bugs in agentic flows
GBrain Expands to Support Diverse Local and Cloud Topologies
GBrain will soon support multiple topologies 1/ local PGLite 2/ multiple thin-clients (e.g. Hermes Agent works with OpenClaw's hosted GBrain MCP server) 3/ multiple thin-clients WITH local PGLite for code repos (e.g. Claude Code worktrees with code indexing stay local while GBrain plan...
GBrain Outperforms QMD by 8.3× in Benchmark
Nice qmd vs gbrain benchmarking post GBrain won 8.3x on this particular corpus https://t.co/UcXcksygKz https://t.co/k9NQvYhXA2
OpenClaw's Zombie Workers: Is Tini the Fix?
OpenClaw is giving me the craziest zombie worker problem Has anyone solved this properly? Is tini the correct solution? https://t.co/6HqgSTSb7o
GBrain v0.27 Adds Broad Non‑OpenAI Embedding Support
GBrain v0.27 just dropped - as promised, you asked for support for lots of other non-Anthropic and non-OpenAI embeddings and LLM support, so here it is. Multi-modal embeddings and deep photo OCR, description, and EXIF extraction coming shortly after that....
GStack 1.26.3 Integrates GBrain, Boosting Agent Context
GStack v1.26.3 now works with GBrain, which means your coding agent now has much more context than it did before. https://t.co/DB6tQgjIZQ
World‑changing Startups Apply Before They're 100% Ready
Today is the deadline to apply for YC Summer 2026. If you're still hesitating: the companies that change the world don't wait until they're 100% ready. Applying is sometimes literally the first step.
GBrain 0.26.3 Introduces Full OAuth Access Control Panel
GBrain v0.26.3 now has a full MCP oAuth panel that you can use to control which clients (Claude Code, Cowork, ChatGPT or Perplexity Computer) get access to your brain, with full invalidation and logs https://t.co/xJnnGbcUUW
Codex/Goal Shines when Paired with Gstack and Gbrain
Codex/goal is powerful in conjunction with gstack (all my plans and office-hours runs) and gbrain (code search plus context on what I’m trying to build and what I care about broadly)
Android's Work‑Profile Design Flaw Highlights Poor PM Decisions
Whoever at Android forced this mess of how work profiles and personal profiles work together (really they don’t) should have been fired It’s a textbook example of PMs making the wrong call and letting the bad decision fester for years
GBrain 0.25.1 Adds Book‑Mirror: Contextual EPUB Insights
GBrain v0.25.1 now ships with the book-mirror skillpack by default. Yes, you can upload an epub and if your brain is full of knowledge about you, it'll relate each idea to something you are working on, care about, or are...
Neural Nets Solve Programming; Scaling Makes It Viable
Professor Hamming called it: neural nets were the solution to the programming problem. Ilya had to point to scaling for it to work. https://t.co/6FqaXoi5Ct
1 GW Data Center Offers Jobs, Taxes—Seattle Bans It
Per one-gigawatt data center complex: 5,322 permanent jobs, $157M per year in state taxes, $248M per year in local taxes. During construction: $2.67B in combined investment But nobody managed to tell Seattle this, so it's banned. https://t.co/4RQwxdSdKj
Open-Sourcing My Personal AI for Everyone's Future
In the future everyone will have a personal AI This is why I'm open sourcing the code and skills for mine https://t.co/AUubI9ERCj
Smart Defaults and Thin Layers Boost Team Efficiency
The thing that makes ImageNet work turns out to be a powerful idea for how your teams should organize: smart defaults, have thin layers that don’t require every layer to chime in and accumulate noise https://t.co/eCLnCG5btR
GBrain Emerges as Unique Personal AI Category
3 weeks ago GBrain and Mempalace looked kind of similar 3 weeks later, it's pretty clear GBrain is its own category that is ideal for OpenClaw/Hermes personal AI scenarios, not trying to solve needle-in-a-haystack retrieval perfectly only https://t.co/J8klUWy9XB
GBrain v0.23.0 Lets OpenClaw Enrich Shared Knowledge
GBrain v0.23.0 is actually... a quite big deal. Your brain actaully gets enriched from your conversations with OpenClaw now. OpenClaw still has its own separate memory, but the brain's people, companies, and concepts now all benefit from what it learns...
When Luck Fades, Choose Smart, Gritty Action
Almost any decision in business and life can be decided by: 1/ Are we lucky? Great. 2/ Otherwise what is the smart gritty thing to do? Lucky things happen to lucky people. But after that most of the manifold of outcomes...
SFUSD Spends $147K on Biased Curriculum Review
SFUSD paid $147K for an "independent" review of its ethnic studies curriculum that was stacked with insiders, had no passing threshold, and silenced critics. The Board voted to approve it anyway. Litigation incoming. https://t.co/W8pnmgsm1v
Generative AI Defies Skeptics, Explodes in Adoption
In 2024 Ed Zitron said "Generative AI is peaking, if it hasn't already peaked. It cannot do much more than it is currently doing." Since then: costs dropped 1000x, 50%+ of Americans use AI weekly, OpenAI hit $2B/month revenue, and I...
Tech Millionaire Seeks AI Data Center Ban, Hurting SF
Saikat Chakrabarti made his fortune in tech. Now he wants to ban the data centers that power AI in San Francisco, the most important growth industry in the city and the engine of downtown's recovery. That's not regulation. It's a kill...
Build What People Want: YC’s Core Advice
@50cent at Y Combinator we tell people "Make something people want" and this is exactly what you're saying too
AI Generates Personalized Chapter‑by‑Chapter Book Analyses
Here's a fun skill you can teach your OpenClaw/Hermes, just paste it and find a book and it'll give you hours of fun Book Mirror — How It Works What it does: Takes any book + everything the AI knows about the...
AI Boosts Food Supply Through Safer, Efficient Agriculture
Everybody eats. Improving our food supply and safer more efficient agriculture is one of tue most direct ways for AI to help people
Young Founders: Reading Extensively Fuels Success
Haha, uh, I guess one thing I would recommend to young founders is read a lot Like, read *A LOT* just learn about the world. If you like to read it's not a waste of time. It might be the best...
Prioritize What Matters, Skip the Spam
This is awesome Big tip would actually be focus more on notability: don’t eat all spam and forwards. Really focus on what is important to you and 🦞 with that directive can run with it
Three Docs Turn AI Into Your Personalized, Articulate Agent
The secret to an articulate agent like mine isn't one file. It's three: SOUL.md — Who the agent IS. Voice, values, operating principles, what good output looks like, what bad output looks like. Not a system prompt, a constitution. Mine says...
AI-Enhanced Chapter-by-Chapter Reading Boosts Insight
Ok one very wild thing I didn’t expect from having a openclaw with GBrain retrieval is how powerful reading a book chapter by chapter WITH my AI has become. You need the full text. You have the AI parse a...
Combining Graph and Vector Retrieval Boosts Knowledge Wiki
Graph, and vector have to work together to get you better retrieval. I realize this is not rocket surgery or new ground— but for it to work out of box with OpenClaw as a Karpathy knowledge wiki synced off a...
Hybrid Graph-Vector Retrieval Drives 97.9% Recall@5
For GBrain I built a proper eval harness. 145 queries, Opus-generated corpus. The retrieval stack uses graph based, vector based and Grep based strategies in combination. The graph layer is worth +31 points on precision. Vector-only misses 170/261 correct answers...
OpenClaw Enables Contextual Map‑Reduce Queries via GBrain
This is what my OpenClaw does when I ask it questions. It’s amazing how good and useful it is once it has your context and you want to do map reduce type questions like this I’m building all of this...
GBrain v0.22 Launches with Search Fixes and Separate Eval Repo
Releaseing GBrain v0.22 - lots of fixes to search and retireval and a new eval system (gbrain-evals is now a separate repo to prevent checkout bloat) https://t.co/qVAQjQeReV
Control Your Browser Directly with Claude Code
Did you ever want to control your browser side-by-side with Claude Code? Now, with /open-gstack-browser skill and GStack Browser, you can https://t.co/dT0dUd3MhF
GStack v1.13 Enables Cross‑Modal Synthesis with GPT‑5.5
GStack v1.13 shipped - simple feature, I'm spending a lot more time using GPT-5.5 with Conductor and so I realized I sometimes wanted to get Opus 4.7's take on a change before I kept going. Cross-modal synthesis is something I...
New OSS Tool Discovered for E2E Testing Despite Google Lag
Early warning signal for the Google execs who might follow me: Your index doesn't refresh fast enough for github repos, and so I had to use my OpenClaw and Exa to find this new and very powerful OSS for E2E...
Founders Must Distinguish Pilot, Bookings, Revenue Accurately
Here's YC's official advice about being truthful and precise about what is pilot, bookings, revenue and recurring revenue. Founders, particularly first time founders, need to sear this into their brains. Don't mistake one tier for another. Be precise, and always...
Product‑Market Fit Beats Coding: The Real Startup Challenge
Knowing what to build, for who, and how to get them to use it is actually harder
GBrain to Release Over 100 New Skill Packs
GBrain has dozens of skill packs that make functionality out of box and I’m going to add more than 100 in the next few weeks
Enhanced Smoke Tests Ensure OpenClaw Container Recovery
I'm on a GBrain PR-spree tonight, first up smoke test improvements for when your OpenClaw container dies and you want everything to work when it fires up again https://t.co/e2p0f6NVVN
GStack v1.11.0 Atomically Stacks Versions and Changelogs
Quality of life GStack v1.11.0 release /ship now stacks VERSIONs and CHANGELOGs up atomically so you don't have to go through so much BS trying to get 10 PR's ready to go all landed on main It's a good problem to have,...
GBrain to Add Code Chunking, Search, and Claude Integration
This is great feedback, thanks Agrim. I'm going to slim things down... But also I will do a branch where GBrain augments Claude Code too. I'm adding code chunking and code search to GBrain in an upcoming PR in the...
YC Launch Analysis Suggests AGI Already Exists
I asked my OpenClaw to analyze all YC video launches for the last 3 years. I'm not sure how anyone can look at this screenshot and not believe that AGI is already here https://t.co/l1vNNcKTMF
Migration Hardening Essential for Massive Markdown Repositories
Turns out migration hardening matters a lot when you have 50k markdown files in your brain repo https://t.co/kgoCFverRF
Discover GStack: Your Guide to the Platform
If you're wondering what GStack is, here it is https://lnkd.in/gdhKh6Qc