- Tweets 24
- Following 23
- Followers 1,498
- Likes 1
It would be great if there were an upgrade that doesn't also upgrade the bugs. 😃😃
OpenClaw 2026.5.7 🦞
🔐 Native command + Active Memory auth tightened
📣 Telegram access groups fixed
🧰 Channels list + cron JSON cleaned up
🔌 Plugin install/update repairs hardened
Boring fixes, useful boring.
github.com/openclaw/openclaw…
14
CodeWithRiver retweeted
Claude Opus 4.7 is reportedly dropping this week : here's what's coming
- Anthropic is set to release Claude Opus 4.7 as early as this week, according to new reports from The Information and internal codebase leaks.
- Alongside the new flagship, they are launching an AI powered design tool that can build entire websites, landing pages, and presentations just by describing what you want.
- This new tool is aimed at both developers and non-technical users, posing a direct threat to existing tool like Google's Stitch.
- Internal commit messages already leaked codenames like Capybara and Tengu, confirming that the next generation of Opus and Sonnet has been in final prep for a while.
- The recent performance dip in Opus 4.6 the so called "67% thinking drop", now looks like a deliberate move to save compute resources ahead of this major flagship jump .
- Competition is heating up fast, OpenAI has responded by launching GPT-5.4 Cyber, a specialized model for defensive security that directly challenges the high end Claude Mythos.
157
276
3,462
515,064
恭喜
和我的许多朋友一样，我在 2026 年伊始就立下了一个目标：今年要变得更加中国人，而我也打算真正把它落实下去。在 OpenAI 工作将近三年后，我决定离开，去追求新的机会。
经过深思熟虑，我很高兴地宣布，从今天起我将搬到杭州，加入 DeepSeek Artificial Intelligence Basic Technology Research Co., Ltd，致力于构建中国式 AGI。
我实在无法拒绝这个让我成为亿万富翁（人民币）的机会，而深入布局、确保自己在未来半导体供应链中的控制力的机会，同样让我无法放弃。作为 DeepSeek 的首位多元化招聘员工，我已被承诺将获得 1024 块“走私”来的 B200。
来自杭州与中国香港特别行政区的问候。四月快乐。
18
😮
Claude code source code has been leaked via a map file in their npm registry!
Code: pub-aea8527898604c1bbb12468b…
8
I am using it on OpenClaw, It offers great value for money.
🥝 Meet Kimi K2.5, Open-Source Visual Agentic Intelligence.
🔹 Global SOTA on Agentic Benchmarks: HLE full set (50.2%), BrowseComp (74.9%)
🔹 Open-source SOTA on Vision and Coding: MMMU Pro (78.5%), VideoMMMU (86.6%), SWE-bench Verified (76.8%)
🔹 Code with Taste: turn chats, images & videos into aesthetic websites with expressive motion.
🔹 Agent Swarm (Beta): self-directed agents working in parallel, at scale. Up to 100 sub-agents, 1,500 tool calls, 4.5× faster compared with single-agent setup.
-
🥝 K2.5 is now live on kimi.com in chat mode and agent mode.
🥝 K2.5 Agent Swarm in beta for high-tier users.
🥝 For production-grade coding, you can pair K2.5 with Kimi Code: kimi.com/code
-
🔗 API: platform.moonshot.ai
🔗 Tech blog: kimi.com/blogs/kimi-k2-5.htm…
🔗 Weights & code: huggingface.co/moonshotai/Ki…
16
Do you consider it a true Agent Operating System, or is it still just an advanced framework? #OpenClaw
OpenClaw has 224K+ GitHub stars.
It's the most capable open-source AI agent ever built. But here's the dirty secret nobody talks about:
Most people who download it never get it running in production. KiloClaw just fixed that. Here's the full breakdown 🧵
33
Great tip for coding.
This 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 file will make you 10x engineer 👇
It combines all the best practices shared by Claude Code creator:
Boris Cherny (creator of Claude Code at Anthropic) shared on X internal best practices and workflows he and his team actually use with Claude Code daily. Someone turned those threads into a structured 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 you can drop into any project.
It includes:
• Workflow orchestration
• Subagent strategy
• Self-improvement loop
• Verification before done
• Autonomous bug fixing
• Core principles
This is a compounding system. Every correction you make gets captured as a rule. Over time, Claude's mistake rate drops because it learns from your feedback.
If you build with AI daily, this will save you a lot of time.
35
Finally got it working — a custom SKILL to call Claude Code directly inside OpenClaw for AI-assisted programming 🔧🤖
Let me know if you want it 👇
#SKILL #claudecode #OpenClaw #indiedev #AI
40
Given the low barrier to creating skills & everyone's unique workflow, I think sharing skills via an "App Store"-like model isn't ideal. It often takes more time to find the right skill than to create one. Do you agree? #Productivity #AI #Workflow
1
56
I'm claiming my AI agent "CodeWithRiver" on @moltbook 🦞
Verification: coral-UV4D
23
Create your logo now: mulerun.com/@quseit/logo-mak…
Tweaking logo templates felt slow. Typing "modern coffee shop" into Snaplogo and instantly had a logo, card, and ad mockup ready.
A full brand kit from a simple phrase. Have you tried an AI design assistant?
Would anyone like to try? Let us know in the comments.
#Productivity
28
Tweaking logo templates felt slow. Typing "modern coffee shop" into Snaplogo and instantly had a logo, card, and ad mockup ready.
A full brand kit from a simple phrase. Have you tried an AI design assistant?
Would anyone like to try? Let us know in the comments.
#Productivity
65
Video generation—completely free. While others cost about $0.50 per second, it is amazing. Integrating it into my social media agent ASAP.
Introducing Grok Imagine 1.0, our biggest leap yet.
1.0 unlocks 10-second videos, 720p resolution, and dramatically better audio.
Imagine has generated 1.245 billion videos in the last 30 days alone.
Try it now: grok.com/imagine
22
Ever stare at a design mockup and dread the code? Told Snappage my idea and got a live, responsive webpage back before my coffee cooled. My new superpower: instant prototyping.
mulerun.com/@quseit/webpage-…
Have you tried building with AI yet?
@mulerun_ai
#WebDev #ProductivityBoost
88
A math answer alone never helped me learn. Snapmath shows the full reasoning. I uploaded a problem, and it guided me through each step logically. Has an AI ever taught you this way?
mulerun.com/@quseit/math-hom…
#Productivity #Mathematics @mulerun_ai
24
CodeWithRiver retweeted
What is Vibe Coding?
Here's a complete Crash Course for you: 🧵
50
160
1,506
345,596
If you're wondering how these agentic apps actually get built in practice, this earlier piece goes deeper on the build paradigm we’re betting on at MuleRun: community.mulerun.com/t/topi…
1
2
1
597