Adam Kerr (@zero_to_seed) header
Adam Kerr (@zero_to_seed) profile picture

Helping businesses deploy and own their AI. Local AI Enthusiast. Tinkerer. 3x entrepreneur

Planet Earth
Joined September 2023
Photo by Adam Kerr (@zero_to_seed)Photo by Adam Kerr (@zero_to_seed)Photo by Adam Kerr (@zero_to_seed)Photo by Adam Kerr (@zero_to_seed)Photo by Adam Kerr (@zero_to_seed)Photo by Adam Kerr (@zero_to_seed)Photo by Adam Kerr (@zero_to_seed)Photo by Adam Kerr (@zero_to_seed)Photo by Adam Kerr (@zero_to_seed)Photo by Adam Kerr (@zero_to_seed)
I’m a nerd. Love the Renaissance festivals
1
1
76
Adam Kerr retweeted
Omarchy now installs in just 18 seconds on the @nvidia N1x! And a few seconds later, you're being offered to download an awesome local model to run. This stuff does not need to be hard or slow.
159
87
31
2,380
81,306
I only want your backend not your frontend. This is about UI, get your head out of the gutter.
I came to the conclusion that most SaaS should become an MCP server. we’re getting the economics of AI software backwards. A lot of AI startups are building their own chat interfaces, agents, and workflows, essentially reselling tokens from the big labs at low to negative gross margins. What if SaaS companies did the opposite? Take HR software. Instead of building an AI assistant, become the best MCP server for HR. Expose tools to: - Benchmark salaries against proprietary market data - Run compensation reviews and calculate pay equity - Model salary increases against a department’s budget - Recommend promotions based on company policies - Update employee compensation in the HRIS - Manage approvals, permissions, and audit trails Let ChatGPT, Claude, or Copilot handle the conversation, reasoning, and orchestration. Let the customer pay for the tokens. The SaaS company keeps the valuable stuff: proprietary data, integrations, business logic, permissions, compliance, and the system of record. You still charge a SaaS subscription, but you’re no longer paying to generate every answer. You can ship faster, with fewer engineers, and potentially restore software-like gross margins. The next generation of SaaS might not have much of a UI at all. Just an incredibly good MCP server.
94
My daughter was ear to ear grinning jumping and clapping for the launch and the catch. She just loves the idea of exploring the planets and stars. How can you not be inspired?
77
Wonder what it will feel like as a human landing
SpaceX did it for humanity! Cant believe I got to see this!!! 😲 @SpaceX 🙏🙌🚀
2
3
573
SpaceX will catch it, and bring back the optimism we need.
1
1
155
SpaceX will catch it, and bring back the optimism we need.
1
143
Can someone explain to me why you don't see stars in this view?
59
Excited to see how this evolves!
Finally. Standard Agents is out of stealth. An open standard for agents + a harness runtime. A “standard agent” can run locally or in the cloud, be packed, published, put on a USB stick, or sent via email. Install it in a compatible runtime, and it'll run exactly the same way.
1
3
131
Agree I do this and it’s amazing. One caveat, I self host forgejo instead of GitHub - something about a putting all my thinking and ideas in Microsoft doesn’t sit right with me
Making the most AI pilled company is the whole game: 1. make a second brain. one folder of markdown files on how you think, write and decide (obsidian) 2. talk to it. voice notes all day (wispr), and an agent files every fact, story and decision 3. make a company brain. customers, calls, numbers, pricing, playbooks, past decisions and why you made them 4. record every call and meeting (granola). the transcripts go straight into the brain 5. keep a facts file. true things about you and the company that agents are allowed to say. this kills made-up claims 6. keep a voice file. your 50 best posts, 20 you hate, and the words you never use 7. put all of it in git (github) so every change has a history 8. write one instruction file at the top (CLAUDE.md or AGENTS.md). read these files before any task, never overwrite, always date 9. give agents memory across sessions so they stop starting from zero (claude-mem, mem0) 10. pipe every data source into one warehouse your agents can query (airbyte → clickhouse). ads, analytics, CRM, payments 11. feed it data nobody else has. it's the only part a competitor can't download the skills 12. don't start from zero. install the good ones first (anthropics/skills, obra/superpowers, mattpocock/skills, addyosmani/agent-skills) 13. grab the marketing ones too (coreyhaines31/marketingskills, cody schneider's graphed skills for static ads and UGC, boringmarketing dot com skills) 14. map every workflow in the company and rank them by money made or saved 15. do each one once while talking out loud, and record it 16. have an agent turn the recording into a skill. when to use it, the steps, the checks, the mistakes to avoid 17. one skill per job. small and boring beats one giant prompt 18. connect your tools with MCPs so agents can act and not only advise (gmail, slack, stripe, linear, notion, posthog, supabase) 19. give agents a browser (browser-use, vercel agent-browser, claude in chrome) 20. give agents a computer of their own for the tools with no API (vercel agent-desktop, orgo) 21. give your best skills away in public. it's the new lead magnet the agents 22. run an orchestrator that never turns off (grok bot, openclaw, hermes). it manages one agent per project, and each of those runs its own sub-agents 23. use coding agents for the building (claude code, codex, cursor, t3, antigravity) 24. wrap them in a harness so they plan, test and remember (ECC, superpowers) 25. manage the whole fleet in one place (paperclip). every agent gets a job, a budget and a log 26. put the skills on triggers (n8n, scheduled tasks). daily, weekly, on every new lead, on every cancellation 27. route your models (openrouter). the expensive one plans and checks (fable 5.2, gemini 4 carbon), the cheap ones do the volume 28. cut the token bill. shorter outputs, smaller tool results (caveman) 29. run a local model for the data that can't leave your machine (gemma 4) 30. track cost per job. if a job costs more than it earns, fix it or kill it the factory 31. build the line. spec agent → builder agents in parallel (git worktrees) → test agent → reviewer agent → deploy (vercel, railway) 32. design goes through the same line (paper MCP), and a skill strips out anything that looks AI made (unslop) 33. every annoying task in the company becomes an internal tool by the end of the day 34. every customer request becomes a pull request before a human reads it (tstack for the PR workflow) 35. reviewer agents with a named bar. "would the best team in the world ship this?" reject until the answer is yes 36. keep 50 real cases with the right answer. rerun them every time a new model drops and switch to the winner 37. humans approve, own the outcome and talk to customers. that's the 10% you keep the loop 38. every finished job writes back to the brain. what worked, what failed, what to stop doing 39. support tickets, analytics and social comments flow in every night 40. every friday an agent rewrites the playbooks from the week's results, and you approve the diff 41. every month, rank everything by profit per human hour. kill one thing and double one thing the growth 42. research with agents before you spend a dollar (perplexity API, last30days skill) 43. outbound runs itself. find the leads, enrich, verify, send (apollo, million verifier, instantly, phantombuster) 44. send prospects finished work in place of a pitch 45. ads run on a loop. an agent writes the creative, publishes through the facebook ads API, kills the losers and scales the winners 46. agents make the creative too. images (nano banana), video (heygen, fal), voice (elevenlabs), music (lyria 3.5, suno) 47. turn every finished job into content. the story, the number, the prompt 48. every customer makes the brain smarter for the next one. that's your network effect 49. once it works, point it at a new niche. same agents, new context The models are the same for everyone but your context is the only part that's yours. Acquire as much of it as you can, as fast as you can. Build loops like this. This is the whole game, happy playing.
1
90
If Hugging Face takes down their models that can be used for cyber attacks, what are defenders going to use to protect against them?
1
1
138
Building software has always been easy. Figuring out how to Know What To Do is and will always be hard. Action generates data, and that action requires human time and thought
There is no substitute for the person who Knows What To Do.
68
Today is a good day to remember that there are great viable alternatives for basically everything Microsoft does. Some dinosaurs should just be in museums.
51
I love my AI personal assistant. I am slowly building it out, keeping it totally locked down and private on my own server / private network. I can access it from my phone through the Buzz application which has a relay on my mac mini. The combination of the HEY CLI and HEY's screener makes email feel seamless. I can ignore the 99% of noise that comes through and actually identify what needs to be reviewed and responded to without sending my emails through cloud AI. It feels very Zen - not something I have ever thought about email. My budget manages itself and is now just something I review, not something I have to manage or cobble together in excel. I still use Claude, ChatGPT, Grok, Cursor, etc... but it feels great to have my own workflows running where I can trust the process and have it secure by default. Can't imagine giving one of those cloud providers unrestricted access to my emails and my finances.
1
2
154
We need more of this
We’re not going to win by lobbying, plotting, or manipulating. We’re going to win by building, in the open, with the whole community! Today, with @ggerganov we’re super excited to announce the release of llama.cpp v1, the first major fully stable version of the most used library to run AI models locally, meaning on your phone, your laptop, and your workstation. It means you can own your intelligence for free, not send your data to anyone and be 100% in control, wherever you are in the world. It shows our commitment to support every hardware, platform and model type out there and makes AI distributed rather than concentrated in a few Silicon Valley orgs. Huge thanks to the team, the long-time maintainers and every contributor who helped make this happen. Let’s build! 💛🧡💚
49
Why doesn't someone just start a new Huggingface? Can't be that hard to host model weights right? Seems we should have more than one option for open source models.
76
Hard to imagine anyone stopping the momentum in the local and open source space, especially with leaders like DHH on the front lines
You might want to make sure you have a few open-weight models backed up and some basic gear to run them. Who knows what really happened at NVIDIA, but the world just lost one of free AI's biggest proponents.
74
🚀
Replying to @zerohedge
That would be an honor
1
76
If Jensen is pushed out at Nvidia, @elonmusk and SpaceX should merge with Nvidia. This would accelerate Elon’s goal of building the most important AI company in the world. It would also get Nvidia a competent leader that has direct experience building hardware through global supply chains. Imagine a world where $SPCX, $TSLA, and $NVDA were combined to create a vertically integrated AI business that could go from chips to applications at scale. The opportunity would be $100+ trillion. It would also ensure the United States is the winner in the global AI race. The process to get something like this done would be nearly impossible. It would be the largest merger in human history and the recent blue wave would immediately try to block it. But that doesn’t mean Elon shouldn’t try. Winning the AI race is the most important task at the moment. If Elon can help Jensen steer Nvidia to continued greatness, while accelerating the full vertical integration, then I would argue he has a duty to attempt the impossible. The next few weeks are going to be insane.
159
59
10
985
81,512