Image created with gemini-3.1-flash-image-preview with claude-sonnet-4-5. Image prompt: Using the provided reference image, keep the exact compositional layout with subject dominating left third and atmospheric smoke filling right two-thirds, deep blue-purple cinematic lighting, and emotional weight, but replace the central figure with a vintage arcade claw machine in tight profile close-crop, glass cabinet reflecting moody neon, mechanical claw suspended inside reaching toward a glitter-covered plush toy, misty haze drifting rightward, white lowercase text ‘openclaw’ overlaid on right side in thin Helvetica Neue Light, bittersweet post-party stillness, shallow depth of field, HBO prestige drama aesthetic.
Starting tomorrow at 12pm PT, Claude subscriptions will no longer cover usage on third-party tools like OpenClaw. You can still use these tools with your Claude login via extra usage bundles (now available at a discount), or with a Claude API key.
https://x.com/bcherny/status/2040206440556826908?s=20
GLM-5.1 is here! Try it on OpenClaw🦞🦞🦞 ollama launch openclaw –model glm-5.1:cloud Claude Code ollama launch claude –model glm-5.1:cloud Chat with the model ollama run glm-5.1:cloud
https://x.com/ollama/status/2041556572334428576
AI 101: Hermes Agent – OpenClaw’s Rival? Differences and Best Use Cases
https://x.com/TheTuringPost/status/2039813131250323650
Hermes Agent vs. OpenClaw, What’s the difference? 1. Skills OpenClaw’s skills are written and refined by humans, while Hermes mostly forms them itself. 2. Memory Hermes has memory stack with compact persistent memory + searchable session history in SQLite + optional modeling +
https://x.com/TheTuringPost/status/2040936147720048909
Run Gemma 4 locally with OpenClaw 🦀 in 3 steps:
https://x.com/googlegemma/status/2041512106269319328
Need to set up my OpenClaw to update and restart my Claude Dispatch to add computer use so I can use that instead.
https://x.com/emollick/status/2040166468877164704
With GLM-5.1,
https://t.co/nvW0zf0SAH maintains the #1 open model rank in Code Arena and is now within ~20 points of the top overall while outperforming Claude Sonnet 4.6, Opus 4.5, GPT-5.4 High, and Gemini-3.1 Pro. Open models are now competitive at the frontier.
https://x.com/arena/status/2042643933768151485
woke up and my mentions are full of these Both me and @davemorin tried to talk sense into Anthropic, best we managed was delaying this for a week. Funny how timings match up, first they copy some popular features into their closed harness, then they lock out open source.
https://x.com/steipete/status/2040209434019082522
OpenClaw development is moving too fast. They’re adding features that should be skills. I’ve now onboarded 10+ “”normie”” friends to ai agents, and every single one of them prefers Hermes. Great work @Teknium
https://x.com/DoctaDG/status/2041051272560923090
The next version of @OpenClaw comes with native video generation. To start, I added support for the following companies: – Alibaba – BytePlus – fal – Google – MiniMax – OpenAI – Qwen – Together – xAI
https://x.com/steipete/status/2040928953653744003
Give your agent the Molty spicy SOUL upgrade: stronger opinions, less corporate sludge, better instincts, and replies that might finally sound like someone worth talking to at 2am 🦞
https://x.com/openclaw/status/2041003999856406714
i’m being asked for oneliner descriptions of each track, so here goes (pushback/improvements welcome): 1. Claw track: This is the year of the personal agent – many people have been dreaming of a personal AI, from being a friend to an executive assistant. @steipete’s OpenClaw
https://x.com/swyx/status/2041517332011352121
OpenClaw 2026.4.2 🦞 🔄 Durable Task Flow orchestration 🔓 Better native exec defaults + approvals 🤖 Copilot + Kimi + provider hardening 🔌 Tighter plugin activation boundaries 🛡️ Hardened provider transport + routing Less bloat. More lobster.
https://x.com/openclaw/status/2039789061154685323
Working on a new QA process where we use openclaw to QA openclaw with a new synthetic message channel. Orchestrator agent understands project, defines tasks (e.g. ask agent to create cron) then verifies that agent did what that. If failure -> spin up subagent to analyze+fix.
https://x.com/steipete/status/2040894021036384502
Prediction: This is gonna kill some oss projects. “”On the kernel security list we’ve seen a huge bump of reports. We were between 2 and 3 per week maybe two years ago, then reached probably 10 a week over the last year with the only difference being only AI slop, and now since
https://x.com/steipete/status/2039782190838686088
OpenClaw 2026.4.7 🦞 🔮 openclaw infer 🎬 music + video editing 💾 session branch/restore 🔗 webhook-driven TaskFlows 🤖 Arcee, Gemma 4, Ollama vision 🧠 memory-wiki: persistent knowledge, not just vibes Because “trust me bro” is not a knowledge system.
https://x.com/openclaw/status/2041714270212108657
Very happy for @badlogicgames and @mitsuhiko any my small part in robbing their sleep.
https://x.com/steipete/status/2041865587714863198
Anyone who wanna help me test the GPT 5.4 🦞upgrades: openclaw update –channel dev
https://x.com/steipete/status/2040924872885301296
it took a hammer, but i managed to beat emotions into GPT.
https://x.com/steipete/status/2040982273193869671
you said GPT felt like bread, so we stopped serving carbs. 🥖❌🦞
https://x.com/steipete/status/2040813772491595997
Managing open source is way harder than managing [paid] closed source projects. At work, you have authority. With OSS you have GitHub Issues.
https://x.com/steipete/status/2041716727998796021
Trending on Hacker News rn.
https://x.com/steipete/status/2041719008953606148
I keep hitting quota limits from GitHub’s API. This hasn’t been designed with agents in mind.
https://x.com/steipete/status/2040067429242675523
AM I HOT PEOPLE OR SLOP CANNON
https://x.com/steipete/status/2039948914112209390
Can your OpenClaw dream?
https://x.com/TheTuringPost/status/2041584758421909805
Factorio × ∞
https://x.com/steipete/status/2039972988054106254
glad they banned openclaw, the servers are finally reliable again
https://x.com/steipete/status/2041849503704141961
GPTEESUS HAS RISEN
https://x.com/steipete/status/2040998797921145272
̶p̶o̶p̶ geek culture
https://x.com/steipete/status/2041225122866938364
redemption arc completed 🦞💻
https://x.com/steipete/status/2042019503907717344
Second 🚢 of the day.
https://x.com/steipete/status/2041715707314946073
See you there!
https://x.com/steipete/status/2039496525282496861
There’s a big wave coming””
https://x.com/steipete/status/2040492573819904026
LangSmith Fleet 🤝
https://t.co/LBy0PVGlGm Arcade provides enterprise grade access to 8,000+ tools As of today, you can connect to all these tools from LangSmith Fleet. This lets you easily build your own no-code Claude Cowork/OpenClaw style agents Blog:
https://x.com/hwchase17/status/2041598614712283390
OpenClaw 2026.4.5 🦞 🎬 Built-in video + music generation 🧠 /dreaming is now real 🔀 Structured task progress ⚡ Better prompt-cache reuse 🌍 Control UI + Docs now speak 12 more languages Anthropic cut us off. GPT-5.4 got better. We moved on.
https://x.com/openclaw/status/2040998570317197607
Hooked up GPT 5.4 to auto-translate our docs via automatic GitHub trigger; way better than what google translate gives you. (also takes significantly longer, so happens once a day)
https://x.com/steipete/status/2040831898620932397
langosta · lagosta · Hummer · homard · aragosta · ıstakoz · homar · الكركند · ロブスター · 바닷가재 · 龙虾 · lobster OpenClaw docs now speak 12 languages 🌍🦞 We moved translations into a dedicated docs repo, added per-language glossaries + translation memory, and retranslate
https://x.com/openclaw/status/2040833418687127916
Some folks try to spin a narrative that I don’t like local models, meanwhile I spent a lot of time making it easy to use OpenClaw with them. Latest release adds support for inferrs, which is a new super efficient TurboQuant inference server:
https://x.com/steipete/status/2041935840935371034
It’s insane! I have a jumpy WiFi on a plane – but who cares. As long as a message goes through, my #openclaw – Alan Tea – is working – it’s running on an old computer 24/7. So so fun, no need so far to buy any other equipment
https://x.com/TheTuringPost/status/2041163715031261258
pourquoi je migre openclaw → hermes de @NousResearch 1/ meilleur skills system , tout les skills openclaw sont manuels tandis qu’hermes les réécrits apres usage pour qu’ils s’optimisent au fil du temps 2/ la mémoire cross-session fait qu’il se construit autour de moi et
https://x.com/spideystreet/status/2041172439468511266
Tried Hermes by @NousResearch and finding it much easier to use than OpenClaw. No more fiddling around and adding skills, I just get Hermes to write them itself. Hermes with minimax-m2.7 has been amazing so far.
https://x.com/SnuuzyP/status/2040999794894663996
📝Summarize 0.13 is out! 🎞️ Local video slides (–slides) 🤖 More model backends (GitHub Copilot) 🧠 Better GPT-5.4 support 📺 Better media handling (HLS detection.m3u8) It graduated from my tap to official homebrew formula! 🍺 brew install summarize
https://x.com/steipete/status/2041669438882087180
Leave a Reply