A free model that runs fully on your machine. No account, no monthly bill, and nothing you type leaves your computer.
Install Ollama (a free app for running models locally)
ollama pull igorls/gemma-4-12B-it-heretic-GGUF
ollama run igorls/gemma-4-12B-it-heretic-GGUF, then type /set nothink (with thinking on, answers get cut off)
Optional: ollama launch claude connects it to Claude Code, but tool use is still rough
It’s a 7.4 GB download and wants a GPU with 8–12 GB of memory.
It’s a modified Gemma 4 with the safety training removed, so what you do with it is on you. And fewer refusals don’t make it smarter: for real coding, cloud models still win.
Bookmark it. The day you hit a rate limit, you’ll want these 4 commands.
Addy Osmani, who works on Claude Code at Anthropic, has a concern about where AI is taking our minds.
He admits that his AI agents now cover so much of his daily work that he hardly has to think critically anymore.
In his view, the slide into mental dependence happens in three steps. First comes cognitive offloading, where you hand routine tasks to AI. Next is deferral, where you start taking its answers at face value. The last step is cognitive surrender, where you trust it without question.
His warning is that any ability you stop practicing fades, and it fades faster than most people expect.
Addy Osmani, who works on Claude Code at Anthropic, has a concern about where AI is taking our minds.
He admits that his AI agents now cover so much of his daily work that he hardly has to think critically anymore.
In his view, the slide into mental dependence happens in three steps. First comes cognitive offloading, where you hand routine tasks to AI. Next is deferral, where you start taking its answers at face value. The last step is cognitive surrender, where you trust it without question.
His warning is that any ability you stop practicing fades, and it fades faster than most people expect.
This repository gives you a free team of AI workers running directly on your hardware
Forget messaging back and forth with single chatbots. This tool deploys an entire company on your computer: the lead manager automatically distributes tasks, while specialized agents write code, research information, and handle routine work without your involvement.
You just set the overall goal, and the system figures out who handles what. Full privacy, zero subscriptions, and 100% local operation.
Bookmark this before it goes viral. Link to the repository is in the comments.
This repository gives you a free team of AI workers running directly on your hardware
Forget messaging back and forth with single chatbots. This tool deploys an entire company on your computer: the lead manager automatically distributes tasks, while specialized agents write code, research information, and handle routine work without your involvement.
You just set the overall goal, and the system figures out who handles what. Full privacy, zero subscriptions, and 100% local operation.
Bookmark this before it goes viral. Link to the repository is in the comments.
It is hard to believe, but 66,000 GitHub stars went to a way of running Claude Code without paying Anthropic
1. Open https://t.co/SEPe3iMvH2, on Mac or Linux run the curl installer from the README
2. Run fcc-server on Linux or open the Free Claude Code app on Mac and Windows, it opens the Admin UI
3. Turn on Proxy Authentication with your own token, by default the proxy is open to your whole network
4. Create an API key at https://t.co/LgVWtkHqC6, paste it under Providers, NVIDIA NIM, Add key, Save, then click Apply
5. Start the agent with fcc-claude
6. Switch in the native /model picker among providers you set up, 61 in the catalog, free and paid, DeepSeek, Kimi, Groq, Ollama
7. Add Fallback Models so a dead provider rolls to the next one, a failed request can consume usage from more than one
Free routes mean other models, not Claude, Anthropic does not support this, and your code goes to the provider unless it is local
The README claims 1.3B+ free tokens a month, availability and limits are set by each provider and can change
Full guide in the article below
This prompt turns an AI agent from "writes code however it feels" into "finishes the job on its own"
Drop it into CLAUDE.md and forget the endless "now fix this one more thing":
1. Plan first. Any task with 3+ steps starts with a plan. If something goes sideways, stop and re-plan instead of pushing through
2. Subagents for the side work. Research and parallel analysis go to separate agents, so the main context stays clean
3. Self-improvement loop. Got corrected? Write the rule into tasks/lessons.md. The same mistake never happens twice
4. Not "done" until it's proven. Tests, logs, a diff against main. Ask yourself: "Would a staff engineer approve this?"
5. Elegance, without the fanaticism. Feels hacky? Redo it with everything you know now. Don't overcomplicate small fixes
6. It fixes bugs itself. Got an error, a log, or a failing CI? It sorts it out without hand-holding
Plus three principles: simplicity, root causes instead of patches, and touching as little code as possible
Full text in the video above.
Bookmark this. You'll want it tomorrow, and you won't feel like hunting for it.
One of them, Haggle Bot, according to the company itself, found more than $100K in savings in its first week by going through spend and contracts and preparing negotiations. And that’s just one bot out of 134.
I put them all into one video and scrolled through them by number. There are bots for outbound sales and lead finding, for hiring and sourcing people, for nightly code audits and testing, for SEO and ads, and for expenses, invoices, and contracts. There are personal ones too: a bot that hunts for an apartment and a bot that picks a credit card.
The main thing is that they work around the clock and actually do the work instead of just answering in a chat.
Links to the bots and the template marketplace are in the comments. ↓
Save this post. When you start building your own bots, this list will save you a ton of time, and I won’t be putting it together a second time.
@swadeshkumar_ The funniest part is how simple it is. Just a markdown file the agent rereads each session, and it stops making the same mistake twice )
I made AI build a device that’s 2,000 years old, and it works
The Antikythera Mechanism: 33 bronze gears that tracked eclipses and lunar phases before the common era. Now it’s a 3D simulator: spin it, cut it open, explode it into parts, and watch how every gear moves the pointers.
Claude Opus 5.5 built it with Teardown, a free skill from SkillMD. All you need is a reference image and a couple of lines of text.
→ a model driven by real physics equations, not just an animation
→ take it apart and run it with one click
→ open source, works through Claude Code
The skill is in the comments ↓
Bookmark this post: in a week everyone will be asking how it’s done, and you’ll already have the answer.