Ben Foster retweeted
AI products can introduce different operational requirements than traditional subscription software.
This article by @CredytAI examines why Stripe usage-based billing is fundamentally broken for AI products:
Ben Foster retweeted
✨ I open sourced my first Chrome extension 🚀 SuperLevels
github.com/levelsio/superlev…
I vibe coded it to replace all my Chrome extensions that are increasingly being bought up by spyware and malware companies who sell your data or worse hack your accounts and steal your stuff/money/data, which I'd call one of the top security risks right now
For example: Chrome extensions can read your cookies or localStorage data, including session tokens, then login to your web or email accounts and hack you, they can inject code into any site to pull data form any site you browse, then break into your crypto accounts, drain your wallets, and selling your browsing history to ad companies, but that'd actually be the most favorable thing to happen of all these! Chrome extensions are just very very very unsafe
So I coded my own, that I can trust because I made it, and I can read the source code: my extension is called 🚀SuperLevels and has all the features that the Chrome extensions I used to use have but all built into one safe one
The cool thing is it's 100% open source and free, and you can audit the code first with AI yourself before installing it, and then if you do install it, customize it to your liking again with AI
It has these features that improve my daily workflow while browsing the web:
🚮 Tab Cleaner
Automatically closes inactive tabs after a configurable timeout (default: 5 minutes). Set excluded hosts to keep important tabs alive. View and re-open recently closed tabs.
🍪 Cookie Editor
Full cookie manager for the current site. View, edit, add, and delete cookies. Export cookies as JSON. Expand any cookie to see and modify all fields including domain, path, SameSite, secure, and httpOnly flags.
🔀 Redirect Tracer
See every redirect hop your browser took to reach the current page. Shows status codes (301, 302, 307, etc.) with a visual chain. Copy the full redirect chain to clipboard.
🌙 Dark Mode
Instant dark mode for any website using CSS filter inversion. Adjustable brightness. Toggle per-site or globally. Images and videos are automatically re-inverted so they look normal.
𝕏 X Dim Mode
Custom dim theme for X/Twitter with 7 color palettes: Dim, Slate, Jade, Plum, Dusk, Ember, or a custom hue. Live preview in the popup.
⚡ JS Toggle
Disable JavaScript per-site with one click. Useful for debugging, reading articles without popups, or testing progressive enhancement. Page reloads automatically.
🚫 GDPR Cookie Consent Dismisser
Auto-hides and auto-clicks cookie consent banners. Supports OneTrust, CookieBot, Didomi, Quantcast, GDPR plugins, and dozens more frameworks. Toggle off if a site breaks.
🎨 Live CSS Editor
Write custom CSS for any website, applied in real-time as you type. Saved per-domain. Supports tab key for indentation.
📺 YouTube Unhook
Removes YouTube distractions: no homepage feed, no sidebar suggestions, no end screen overlays, no Shorts. Search still works — just no algorithmic recommendations.
🎵 Music Recognizer
Shazam-like music identification for any tab. Captures 10 seconds of audio and identifies the song via ACRCloud (free signup, bring your own API key). Results link to YouTube. History of recognized songs.
🖼 Picture-in-Picture
Pop the largest video on the current tab into a floating PiP window with one click.
🗺 Google Maps Links
Re-adds clickable Maps links and map preview cards to Google Search results.
🖼 View Image
Adds a "View Image" button back to Google Images, linking directly to the full-size original image.
{} JSON Formatter
Auto-detects pure JSON response pages and formats them with syntax highlighting, collapsible sections, and a dark theme. Copy or view raw with one click. Never triggers on regular HTML pages.
✨ Added 🖼️ Picture-in-Picture to my own Chrome extension 🚀 SuperLevels
It lets you watch YouTube in a PIP frame while away from the tab
The only Chrome extensions I still run now are just uBlock Lite and Claude and my password manager
About 20 less Chrome extensions now, and thus 20 less attack vectors of eventually guaranteed malware and spyware!
Ben Foster retweeted
The wait is over. Cloudflare Email Service is now in public beta 📧
Send and receive emails directly from Workers or REST API with global delivery on Cloudflare's network
And just in time for you to build email agents with the Agents SDK!
Ben Foster retweeted
.@NousResearch Hermes Agent shipped LLM-Wiki integration and this is a big deal for anyone running research-heavy agent setups.
LLM-Wiki is Karpathy's project for building knowledge bases and research vaults using LLMs as the indexing engine. it studies sources like web pages, code, papers... and produces a structured Obsidian-compatible vault. an actual researched body of work you can navigate, link, and extend.
the workflow now is:
hermes update /llm-wiki <topic>
and the agent goes off, researches, and builds you a vault.
----
why this matters for my setup:
I run 3 research crons daily: research-ai at, research-defi, research-deepdive.
they produce findings, write to memory files, log to @AliveContext_ walnuts.
LLM-Wiki does this different. a research vault organised by topic, not by date. with Obsidian's bidirectional linking, you get a real knowledge graph instead of a timeline.
what this infers about where AI agents are heading:
agents are starting to produce their own reference material. actual structured knowledge bases that compound over time.
to start: point LLM-Wiki at the topics you care about, let it run while you sleep, wake up to a vault you can read like a wiki. then your other agent jobs query that vault instead of re-searching the web every time. research becomes cumulative instead of repetitive.
Ben Foster retweeted
If you use GitHub (especially if you pay for it!!) consider doing this *immediately*
Settings -> Privacy -> Disallow GitHub to train their models on your code.
GitHub opted *everyone* into training. No matter if you pay for the service (like I do). WTH
github.com/settings/copilot/…
Ben Foster retweeted
Did you know about the opusplan model in Claude Code?
/model opusplan
It's a hybrid alias that automatically uses Opus in plan mode for complex reasoning, then switches to Sonnet for execution.
Best of both worlds: Opus thinks, Sonnet builds
Ben Foster retweeted
Chrome just became massively more agent-friendly 🔥 Your real, signed-in browser can now be natively accessible to any coding agent.
No extensions.
No headless browser.
No screenshots.
No separate logins.
Just one toggle to enable it.
Check this out: developer.chrome.com/blog/ch…
New @openclaw beta is up: it comes with the new live browser control that Google added in latest Chrome! enable via chrome://inspect#remote-debugging
Your clanker will know when to use what, or you can ast it. new "user" profile session is there!
developer.chrome.com/blog/ch…
Ben Foster retweeted
A couple of suggestions for Claude Code productivity, from someone in the profitable SaaS trenches:
For ANY non-trivial feature: shift-tab into planning mode, and mention "do deep research on best practices and known issues, using web search" to the prompt. READ the plan, adjust, and have it execute. Plans survive compaction MUCH better than vibe-prompted features, particularly if they're bigger.
/plugin marketplace add mksglu/claude-context-mode
(significantly bigger context window, uses an MCP to load files into context via reference instead of parking the whole file there)
/plugin install claude-warden@claude-warden
(much better protection against destructive actions)
Create a /documents/ folder with these files:
- platform-docs.md (describes EVERY feature of your product in detail, generated by a skill that goes through each file/screen and sums up functionality)
- ICPs.md (a document that defines each of your ideal customers, what they need, what theywant to and can do. A dossier for each kind, like what a private detective would produce)
-styleguide.md (contains a description of the visual feel of your application. certain colors, hierarchies. you can have CC generat that from an existing codebase using the --chrome flag to "see it")
- also great: roadmap.md/vision.md (gives exploratory runs some guidance), data-reference.md (explains the kind of connection between your domaindata that is not expressed in the models and their relationships)
Maintain a CLAUDE.md that references all these /documents/*.md files in the system prompt (and forces code to be compliant).
Any of these docs can be inferred from an existing codebase. Ask CC to use the AskUserQuestion skill to get your feedback on anything unclear. Ask it to persist plans and complex ideas in markdown form in your /documents folder.
That will make the experience MUCH more enjoyable and manageable than a vanilla CC.
Ben Foster retweeted
✨ Introducing LLMock: A deterministic mock LLM server for testing
Test your AI powered apps reliably, without burning money on real API calls or fighting non-deterministic outputs in CI.
Open-sourced for the community.
llmock.copilotkit.dev
Ben Foster retweeted
I stopped paying for Claude Code.
$200/month for an API subscription to write code.
Then Ollama dropped Anthropic API compatibility.
Now Claude Code connects to free, local models on my machine.
Here's the exact setup (took me 10 minutes):
1. Install Ollama
→ curl -fsSL https:// ollama .com/install .sh | sh
2. Pull a model
→ ollama pull qwen2.5-coder
3. Point Claude Code at localhost
→ ANTHROPIC_BASE_URL=http: //localhost :11434 claude
That's it. Claude Code thinks it's talking to Anthropic. It's talking to your laptop.
Best models I've tested:
• Qwen 2.5 Coder - best all-around for code generation
• DeepSeek-Coder - strongest at debugging and refactoring
• Llama 3 - solid general reasoning
Local models aren't Sonnet or Opus. Complex multi-file refactors still stumble. Long context windows get messy.
But for everyday coding - scaffolding, tests, quick edits, boilerplate - they handle it fine.
Your code never leaves your machine.
Your bill goes from $200/month to $0.
Your API key stays in your pocket.
(Save this for later.)
🤖 Made with AI
Ben Foster retweeted
New in Claude Code: Remote Control.
Kick off a task in your terminal and pick it up from your phone while you take a walk or join a meeting.
Claude keeps running on your machine, and you can control the session from the Claude app or claude.ai/code
Ben Foster retweeted
Bought a new Mac mini to properly tinker with claws over the weekend. The apple store person told me they are selling like hotcakes and everyone is confused :)
I'm definitely a bit sus'd to run OpenClaw specifically - giving my private data/keys to 400K lines of vibe coded monster that is being actively attacked at scale is not very appealing at all. Already seeing reports of exposed instances, RCE vulnerabilities, supply chain poisoning, malicious or compromised skills in the registry, it feels like a complete wild west and a security nightmare. But I do love the concept and I think that just like LLM agents were a new layer on top of LLMs, Claws are now a new layer on top of LLM agents, taking the orchestration, scheduling, context, tool calls and a kind of persistence to a next level.
Looking around, and given that the high level idea is clear, there are a lot of smaller Claws starting to pop out. For example, on a quick skim NanoClaw looks really interesting in that the core engine is ~4000 lines of code (fits into both my head and that of AI agents, so it feels manageable, auditable, flexible, etc.) and runs everything in containers by default. I also love their approach to configurability - it's not done via config files it's done via skills! For example, /add-telegram instructs your AI agent how to modify the actual code to integrate Telegram. I haven't come across this yet and it slightly blew my mind earlier today as a new, AI-enabled approach to preventing config mess and if-then-else monsters. Basically - the implied new meta is to write the most maximally forkable repo and then have skills that fork it into any desired more exotic configuration. Very cool.
Anyway there are many others - e.g. nanobot, zeroclaw, ironclaw, picoclaw (lol @ prefixes). There are also cloud-hosted alternatives but tbh I don't love these because it feels much harder to tinker with. In particular, local setup allows easy connection to home automation gadgets on the local network. And I don't know, there is something aesthetically pleasing about there being a physical device 'possessed' by a little ghost of a personal digital house elf.
Not 100% sure what my setup ends up looking like just yet but Claws are an awesome, exciting new layer of the AI stack.
Ben Foster retweeted
NanoClaw, the lightweight alternative to Clawdbot / OpenClaw already reached 10.5K Github stars ⭐️
Compared with OpenClaw, NanoClaw’s specialty is simplicity plus OS level isolation.
- Much smaller and manageable codebase, only 4K lines.
- Runs in containers for security.
- Connects to WhatsApp, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK
- stores state in SQLite, runs scheduled jobs, and keeps each chat group isolated with its own memory file and its own Linux container so the agent only sees directories you explicitly mount.
- its safety model leans on application controls like allowlists and pairing codes inside a shared Node process.
OpenClaw is built for broad multi channel coverage, while NanoClaw intentionally stays minimal so you customize by changing a small codebase instead of operating a big framework.
Ben Foster retweeted
Prompts for Google Nano Banana Pro with a web gallery
github.com/YouMind-OpenLab/a…
Ben Foster retweeted
ElevenLabs just lost its moat 🤯
Someone just dropped Voicebox, and it clones any voice from just a 3-second audio clip, running 100% locally on your machine.
100% Open Source
Ben Foster retweeted
NVIDIA just dropped PersonaPlex-7B 🤯
A full-duplex voice model that listens and talks at the same time.
No pauses. No turn-taking. Real conversation.
100% open source. Free.
Voice AI just leveled up.
huggingface.co/nvidia/person…