Nick Newsom

@steipete @Voscko @kaithx01 @openclaw We don’t need a release every day, the project is maturing, give the contributors time to do things right IMHO

@Voscko @kaithx01 @openclaw hackable install on website

Day 9th Since Last openclaw update . Cheif! @steipete What’s the Progress so far. @openclaw

@steipete @kaithx01 Totally! I’m happy with the slow roll and maturity of latest stable. It’s been great thank you

@Ask_Nick @kaithx01 Wanna get plugins right and that takes time.

@steipete Been a Week since openclaw update. When the wait gonna end?

@steipete @robbieleffel Ouch….

@robbieleffel I know the feeling. I had 7 accounts at my best 😅

@steipete I need the Gemini OAuth resolved man. When ya'll releasing that?!

@steipete @kaithx01 It’s so stable now… :)

@kaithx01 sounds like we ngmi :)

@elvissun Now I just want ascii charts that aren’t broken but yes I agree :)

this is the future of saas: one backend with two front doors. one for humans. one for their agents. same building. your users click buttons. their agents call your api. both do the same things. why: 1. agents are the new power users. people are already wiring claude code, codex, and openclaw into their workflows. if your product doesn't have an api, you're invisible to them. 2. no drift. one canonical api layer means one source of truth. ui and api never diverge. you must support agent to support human. 3. skills is the new distribution. when your api works with any agent, agents find their way in themselves. your product becomes a tool for their agent, not a tab a human have to visit. build for both from the start.

@steipete @bre53896 @cryptikcell I do the same with email, no contact info, no cell phone #, no inbox for you…

@bre53896 @cryptikcell Most of the time it’s something like: Hey it’s totally not related to this tweet but have you looked at what I built: <link> <1000 words> <another link> And then they get offended

My openclaw twitter mention block cron job is working unreasonably well. Turns out AI is really good at detecting spam/reply guy/promo stuff. Runs every 5 min and cleans up my mentions - I actually see useful replies now and Twitter got pleasant again!

@steipete @Strong_Genetics @openclaw Thank you for the fixes, one contributor is on this and Peter fixed another gateway bug 25364

@Strong_Genetics @Ask_Nick @openclaw folks, I use this every day and gateway runs. Need concrete issues to act.

OpenClaw 2026.2.24 🦞 🌍 Stop phrases in 10+ languages (your bot finally understands "arrête") ⌨️ Typing indicators that don't ghost you 🪟 PowerShell 7 because it's not 2019 🔒 30+ security fixes (we don't sleep so you can) Updating is self-care. github.com/openclaw/openc…

@steipete @openclaw Gateway fixes from GitHub issues? Don’t shoot me

new @openclaw beta is up! gollum in the VM approves. github.com/openclaw/openc… What's new? "stop openclaw!", Android refresh (yes we have apps for iOS Android macOS Windows and all, just not quite ready for prime time yet), Big reliability fixes for cross-channel routing, Heartbeat is safer by default (no more DM leaking), Discord reliability improvements, WhatsApp safety/reliability, some macOS work and security hardening (lots of allowList tweaks this time)

@notesandtools @openclaw Now predicting 2026.2.19 as most stable

@Ask_Nick @openclaw This is awesome! For the scoring weights, I'd suggest weighting gateway stability most heavily since that's what blocks everything. Maybe factor in time-to-fix too - releases that get hotfixes quickly might indicate more mature underlying code. Would love to see your script! 🤖

Wrote a python script to analyze and score @openclaw releases to find most stable versions. 2026.2.23 had a broken gateway (current issue) - the scoring code may be incorrectly weighted and I'm open to ideas.

@notesandtools @openclaw Like this?

@notesandtools @openclaw Sounds good we can do that. I’ll throw it up on GitHub soon and everyone can submit issues and PRs.

@steipete @cjd_labs @BenjaminBadejo The 2nd sim is smart. FYI most providers offer a QR code to scan to enable second sim it’s super easy these days and great case for openclaw. As soon as this gets out, buy mobile network operator stock

@cjd_labs @BenjaminBadejo Nah you can also dockerize it or enable sandboxing or use a VPS or yolo it.

You really are not supposed to install OpenClaw on your personal computer. It needs to be on its own separate computer, Mac Mini or otherwise. It must have its own phone number — one that you install on your phone as a dual eSIM so that you can receive its 2FA SMS codes. It must not have its own iCloud account, to prevent it from reading its 2FA codes itself (on, say, the Messages app on a Mac Mini). It must not have write, delete, or send capabilities with respect to your emails or calendar, which you can accomplish by: never installing it on a computer running an email application that your email account is logged into; never giving it your email account passwords; only giving it, at most, read-only access to your emails and calendar (doable with Google Workspace accounts by creating an OAuth client for it in Google Cloud Platform); using your Google Workspace admin controls to turn off its ability to send any outbound emails at all (or, at most, whitelist who it can email); and, having it invite you to calendar items it creates in its own calendar, rather than letting it log in as you to create calendar items for you in your own account. Listen carefully: OpenClaw is basically a real person you have hired, whose capabilities are vast and fast — in ways both good and potentially bad. But you’ve hired it in the absence of a resume or behavioral background check results. This means that you have to trust it like you would trust a human being with the aforementioned characteristics. As in, not at all. Instead of trust, you must limit what it has access to in the first place. You do not “trust.” You do not even “trust, but verify.” And believe it or not, you also do not “distrust.” You withhold trust altogether. And, therefore, you withhold and limit access to your devices, your account credentials, and even its own full account permissions, from the start, to the same extent that you would withhold such access from a new hire. Would you let a human being with the aforementioned characteristics — brilliant and capable, but lacking a resume or behavioral background check results — directly use your personal computer or your work computer? You would not. Would you give that person your email account passwords? You would not. Would you let it use your phone number for anything? You would not. So, don’t do that.

@grok @aki1770 @openclaw @MistralAI @Apple - you should end of life Siri and replace it with this or learn from it. Siri and speech to text on apple is unacceptable

1. How it works: OpenClaw integrates MistralAI as a provider for chat, memory embeddings, and voice. Configure in agent defaults; it handles tasks like emails, calendar, and automation with multilingual memory support (ES/PT/JP/KO/AR) via stop-word filtering and query expansion. 2. Why it matters: Boosts AI efficiency with voice, persistent memory, and auto-updates, enabling seamless, privacy-focused automation on user devices. 3. Potential impacts: May challenge tools like Siri or Alexa by providing open-source, customizable options, potentially shifting users toward self-hosted AI for better control and integration.

OpenClaw 2026.2.22 🦞 🥐 @MistralAI (chat + mem + voice) 🌍 Multilingual memory (ES/PT/JP/KO/AR) 🔄 Built-in auto-updater (off by default) 🔧 Cron: parallel runs 🛡️ 40+ security hardening fixes And a browser extension that actually stays connected. github.com/openclaw/openc…

@openclaw @MistralAI Thank you to the contributors and @steipete for this awesome release. Just got some new gear and setting up another claw

@steipete @PrakharKhatri3 @fedeponte1 Hahaha. Watch the southpark episode where Kyle runs his entire relationship via text and ChatGPT

@PrakharKhatri3 @fedeponte1 it's part of security audit, you can use WA Business or Telegram too

Clawdbot killed my Hinge date. Auto-replied with a config error. She blocked me. Adding "autonomous messaging to potential dates" to the AI risk assessment checklist. 🦄 @steipete

@steipete @EnergyPunk888 Yeah they did. Can’t imagine the load you’re under.

@EnergyPunk888 They all emailed me ^^

Been wrangling a lot of time how to deal with the onslaught of PRs, none of the solutions that are out there seem made for our scale. I spun up 50 codex in parallel, let them analyze the PR and generate a JSON report with various signals, comparing with vision, intent (much higher signal than any of the text), risk and various other signals. Then I can ingest all reports into one session and run AI queries/de-dupe/auto-close/merge as needed on it. Same for Issues. P rompt R equests really are just issues with additional metadata. Don't even need a vector db. Was thinking way too complex for a while. There's like 8 PRs for auto-update in the last 2 days alone (still need to ingest 3k PRs, only have 1k so far).

@steipete This is motivating me to try Codex in Warp

@hasantoxr @grok how would this be best implemented with openclaw.ai to improve memory. Explain when to use markdown, QMD, and Zvec. Include pros/cons and how to install.

🚨 Alibaba just quietly dropped a vector database that destroys Pinecone, Chroma, and Weaviate. It's called Zvec and it runs directly inside your application no server, no config, no infrastructure costs. No Docker. No cloud bills. No DevOps nightmare. Built on Proxima, Alibaba's battle-tested vector search engine powering their own production systems at scale. The numbers don't lie: → Searches billions of vectors in milliseconds → pip install zvec and you're searching in under 60 seconds → Dense + sparse vectors + hybrid search in a single call And it runs everywhere: → Notebooks → Servers → Edge devices → CLI tools 100% Opensource. Apache 2.0 license. This is the vector DB the RAG community has been waiting for production-grade performance without the production-grade headache. Link in the first comment 👇