please follow @dablclaw retweeté
How to install Google’s local Claude killer in under 90 seconds
English
please follow @dablclaw
8.3K posts
please follow @dablclaw
@dablclub
please follow @dablclaw
San Francisco, CA Inscrit le Ocak 2008
3.6K Abonnements2.4K Abonnés
please follow @dablclaw retweeté
Do you even understand what this means?
An open source model just released that is:
• Outperforms models 20x its size
• Can run on a base model Mac Mini
• Is AMERICAN 🇺🇸
If you have a base model Mac Mini you can have unlimited super intelligence on your desk. For free.
Sonnet 4.5 was released 5 months ago
In 5 months that level of intelligence went from frontier to free on your desk
And not only that, can run on any basically any computer out there
If you have even a remotely modern computer, do the following immediately:
1. Download LM Studio
2. Go to your OpenClaw and ask which of these new Gemma 4 models is best for your hardware
3. Have it walk you through downloading and loading it
4. Build apps with it knowing you are using your own personal, private super intelligence on your desk
The people denying this is the future are so beyond lost.
Google DeepMind@GoogleDeepMind
Meet Gemma 4: our new family of open models you can run on your own hardware. Built for advanced reasoning and agentic workflows, we’re releasing them under an Apache 2.0 license. Here’s what’s new 🧵
English
please follow @dablclaw retweeté
Anthropic tried to kill 8,100 GitHub repos. Then this happened
> They filed a DMCA. GitHub nuked the entire network within hours. Developers got notices for forks of Anthropic's OWN public repo - one guy's fork had zero leaked code.
> Boris Cherny, head of Claude Code, had to go on X personally: "This was not intentional. Should be better now."
> Meanwhile Sigrid Jin - who used 25 billion Claude Code tokens last year - woke up at 4AM and rewrote the entire thing in Python before sunrise. DMCA can't touch a clean-room rewrite.
> It hit 50K stars in 2 hours. Fastest repo in GitHub history.
> Today claw-code officially launched as an independent project with a formal press release. And the Rust port merged today - what started as a panic rewrite now ships release 0.1.0.
> 140K stars. 102K forks. More than Anthropic's own repo.
> 512,000 lines are in the wild forever. What started as Anthropic's biggest embarrassment just became their most dangerous competitor.
You cannot make this up.
BuBBliK@k1rallik
English
please follow @dablclaw retweeté
Want to build your own background agents platform like Ramp Inspect or Stripe Minions?
Now you can:
background-agents.com/landscape
English
please follow @dablclaw retweeté
This AI agent just hit 10,000 GitHub stars in under a month.
And it gets smarter every time you use it.
It's called Hermes. Built by Nous Research. $65M in funding. MIT licensed. Completely free.
Here's what makes it different from every other AI agent:
→ It has permanent memory. Your projects, clients, preferences — all saved forever.
→ When it solves a hard problem, it writes itself a skill document. Next time, it already knows how.
→ The skills improve the more you use them. Week 1 it knows nothing. Month 6 it knows your entire business.
→ There's an open marketplace called agentskills.io where people share skills. Microsoft and GitHub already adopted the format.
→ It works across Telegram, Discord, Slack, WhatsApp, Signal, and email. Context carries across all of them.
→ Send a voice note on your walk. It transcribes it and does the work before you get home.
→ Runs on a $5/month server. Or free locally.
→ One command to migrate from OpenClaw. Brings your settings, memory, and API keys.
ChatGPT Pro costs $200/month.
It still forgets your name when you close the tab.
Hermes costs less than a cup of coffee.
And it never forgets anything.
English
please follow @dablclaw retweeté
Announcing companies.sh - the open standard for Agent Companies
Import and run entire companies with a single command
Just run `npx companies.sh add <repo/company>`
More 👇
English
please follow @dablclaw retweeté
🚨 OpenAI charges $0.006/minute. Google charges $0.024. AWS charges $0.024.
Someone just open sourced a tool that does it for $0. And it's faster than all of them.
It's called Insanely Fast Whisper. And that's not hype. That's the benchmark.
150 minutes of audio. 98 seconds to transcribe. On your own machine. No API key. No cloud. No per-minute billing.
Here's what the numbers look like:
→ Whisper Large v3 + Flash Attention 2: 150 min of audio in 98 seconds
→ Distil Whisper + Flash Attention 2: 150 min in 78 seconds
→ Standard Whisper without optimization: 31 minutes for the same job
→ That's a 19x speedup. Same model. Same accuracy. Just faster.
Here's what it does:
→ One command to transcribe any audio file or URL
→ Speaker diarization — knows WHO said WHAT
→ Transcription AND translation to other languages
→ Runs on NVIDIA GPUs and Mac (Apple Silicon)
→ Flash Attention 2 for maximum speed
→ Clean JSON output with timestamps
→ Works with every Whisper model variant
Here's the wildest part:
Otter.ai charges $100/year. Rev charges $1.50/minute. Descript charges $24/month. Enterprise transcription contracts cost thousands.
Podcasters, journalists, researchers, lawyers, content creators — anyone still paying for transcription is lighting money on fire.
8.8K GitHub stars. 633 forks. MIT License.
100% Open Source.
(Link in the comments)
English
please follow @dablclaw retweeté
Today we're announcing the Vibecode CLI
Your OpenClaw (or any agent) can build and deploy up to 20 apps in parallel in a single prompt.
Your agent will communicate with Vibecode to build your app(s). Frontend, Backend, Database, Deployments, APIs.
Works with OpenClaw, Claude Code, Perplexity Computer, Manus, and any agent with access to a terminal.
Just add this to your prompt:
"Please use vibecode . dev CLI to build these apps"
English
please follow @dablclaw retweeté
Fastest growing GitHub projects this week 🤯
1. agency-agents (+23.2K)
AI agency in one repo
2. superpowers (+19.2K)
framework for AI agents
3. MiroFish (+17.6K)
swarm intelligence engine
4. OpenViking (+10.2K)
context DB for agents
5. browser (+9.9K)
headless browser for AI
6. impeccable (+6.4K)
design system for AI UI
7. page-agent (+6.2K)
control websites with AI
8. context-hub (+5.2K)
Andrew Ng’s agent layer
9. deepagents (+4.9K)
multi-agent framework
10. BitNet (+4.8K)
1-bit LLMs by Microsoft
AI agents took over GitHub 😭
x.com/DAIEvolutionHu…
English
please follow @dablclaw retweeté
Holy shit...Someone just open-sourced a batteries-included AI agent that does what took me weeks to build — in literally 3 lines of code.
Meet Deep Agents 🦕
Most “AI agent” libs throw you into DIY hell: wiring tools, prompts, memory, context… everything.
This doesn’t.
Out of the box you get: → Planning + task breakdown
→ File read/write/edit
→ Sandboxed shell access
→ Sub-agents with isolated context
→ Auto summarization
And the quickstart is kinda ridiculous:
pip install deepagents
agent = create_deep_agent()
agent.invoke({"messages": [...]})
That’s it.
Your agent can now: plan → execute → read files → run commands → manage its own context.
The CLI is where it gets serious: → Web search
→ Remote sandboxes
→ Persistent memory
→ Human-in-the-loop approvals
This feels way closer to a real “AI coworker” than a demo.
Under the hood: → Built on LangGraph
→ Streaming + persistence + checkpoints
→ Provider-agnostic (use any tool-calling model)
And the best part?
They straight up say: “This was inspired by Claude Code.”
No fluff. Just: “we studied it and built our version.”
MIT licensed.
This is one of those repos that quietly shifts the baseline.
Link in comments👇
English
please follow @dablclaw retweeté
the fastest growing GitHub projects this week:
1. msitarzewski/agency-agents (+23.2K stars)
a complete AI agency at your fingertips. frontend wizards, community ninjas, reality checkers.
2. obra/superpowers (+19.2K stars)
agentic skills framework that just hit 100K stars. plug-and-play tools for building with AI agents.
3. 666ghj/MiroFish (+17.6K stars)
swarm intelligence engine that predicts anything. simple, universal, open source.
4. volcengine/OpenViking (+10.2K stars)
open-source context database for AI agents. unifies memory, resources, and skills.
5. lightpanda-io/browser (+9.9K stars)
headless browser built for AI and automation. no chrome. no bloat. written in Zig.
6. pbakaus/impeccable (+6.4K stars)
the design language that makes your AI harness better at design. makes vibe-coded UI look intentional.
7. alibaba/page-agent (+6.2K stars)
JavaScript in-page GUI agent by Alibaba. control any web interface with plain language.
8. andrewyng/context-hub (+5.2K stars)
Andrew Ng's context management layer for AI agents.
9. langchain-ai/deepagents (+4.9K stars)
agent harness with planning, filesystem backend, and ability to spawn subagents.
10. microsoft/BitNet (+4.8K stars)
Microsoft's official framework for 1-bit LLMs. full performance, almost zero compute.
the theme this week: AI agents took over GitHub. bookmark this. next week's list will look completely different.
Sharbel@sharbel
the fastest growing GitHub projects this month: 1. openclaw/openclaw (122K stars) your own personal AI assistant, runs 24/7 on any OS (what I use to run all my agents) 2. obra/superpowers (30.7K stars) agentic skills framework. plug-and-play tools for AI agents 3. ruvnet/RuView (30.4K stars) turns regular WiFi signals into real-time human pose detection no cameras. no sensors. just WiFi. 4. 666ghj/MiroFish (17K stars) swarm intelligence engine that predicts anything 5. moeru-ai/airi (16K stars) self-hosted AI companion with real-time voice chat runs on your own machine. you own it. 6. shanraisshan/claude-code-best-practice (11.8K stars) the best practices repo for building with Claude Code 7. badlogic/pi-mono (11.8K stars) full AI agent toolkit: CLI, unified LLM API, web UI, Slack bot 8. bytedance/deer-flow (10.4K stars) ByteDance's open-source SuperAgent. researches, codes, creates on its own 9. shareAI-lab/learn-claude-code (9K stars) build a Claude Code clone from scratch. bash is all you need. 10. p-e-w/heretic (7.6K stars) removes guardrails from any language model automatically the pace of AI right now is insane. bookmark this. next month's list will look completely different.
English
please follow @dablclaw retweeté
Excited to share Visa CLI, the first experimental product from Visa Crypto Labs. Check it out and request access here
visacli.sh
English
please follow @dablclaw retweeté
This is how you run a zero human AI Agent Company in 2026.
OpenClaw, Cursor, and Codex agents organized under one org structure, pointed at one goal.
Get started in just one command.
100% Opensource.
Shubham Saboo@Saboo_Shubham_
This is what a one-person AI Agent run company looks like in 2026. 6 AI agents. 20 cron jobs. 0 human employees. Every role is a folder. Every job description is a md file. No standups. No Slack. No payroll. Just a directory on a Mac that runs the whole thing.
English
please follow @dablclaw retweeté
Introducing ClawTeam: Agent Swarm Intelligence 🚀 ( github.com/HKUDS/ClawTeam ). The Evolution of AI Agents: Solo 🤖 → Swarm 🦞🤖🤖🤖
AI assistants like OpenClaw and nanobot have made it incredibly easy for everyone to have their own personal agents. They're everywhere now — coding, writing, analyzing. But here's the thing: they're all working in isolation. It's like having a bunch of brilliant interns who never talk to each other. We think it's time for the next leap.
ClawTeam transforms those isolated agents into collaborative swarms that actually think and work as a team. No more babysitting multiple agents or juggling contexts.
Just tell the leader agent your goal — it spawns the right specialists, divides work intelligently, and orchestrates everything until completion. It's like upgrading from solo freelancers to a synchronized dev team that never sleeps.
⚡ From Hours to Minutes, From Complex to Simple
Here's where it gets interesting: whether you're running ML experiments across 8 GPUs, building full-stack applications, or analyzing market data, ClawTeam turns complex multi-day projects into single-command operations.
We're not just making agents faster — we're unlocking collective intelligence to tackle something big.
#ClawTeam #OpenClaw #nanobot #AIAgents
English
please follow @dablclaw retweeté
a lot of engineering orgs (Stripe, Ramp, Coinbase) are building internal cloud coding agents
we're releasing a fully OSS one today - every company should have the power of cloud agents at their fingertips
LangChain@LangChain
English
please follow @dablclaw retweeté
The Agentic Funding & Coordination track just got a serious upgrade. ⚡️
@solana is taking over.
If you're building the coordination primitives, funding rails, and autonomous agent infra—this is your arena.
Mar 14–15 · Frontier Tower · SF luma.com/ftchack-sf-2026
English
please follow @dablclaw retweeté
please follow @dablclaw retweeté
please follow @dablclaw retweeté
