here's how I'm using @DevinAI bots for my businesses
software factory for code improvements (remove dead code, reliability issues)
marketing engineer for funnel fixes and expeirments
content engineer for product specific research and contnet
i built an agent native design library for your agents to level up for free
weekly design screen updates
markdown format for your agents to copy
detailed styling patterns and references to use
anti slop patterns
+ design skill pack with 9 sub skills to take your agents to the next level
ainativeoperators.ai/skills/…
We built the Google Analytics killer.
Introducing Humblytics - revenue analytics and CRO for your agent.
Humblytics brings site activity, Google Ads, Meta Ads and Stripe into Claude Code or Codex.
- Reader audits the landing page
- Writer drafts a change
- Tester runs the experiment after you approve it
It automatically helps you run AB experiments on your landing pages and optimizes for what makes you more money.
Start for FREE: humblytics.com
got tired of having to setup my tools, auth, skills, and workflows across different harnesses
got it all setup through notara.ai mcp
it shares memory, context, and tools so i can jump from devin to claude and codex without the setup
built a design hub for humans and agents
1) it has skills for your agents that can reference this design library
2) each website has an agent ingestible format, your agent can use
it breaks down patterns, rules, constraints, and how you can apply it to your ui
ainativeoperators.ai/design-…
Apple is working on a new app called Harbor
Harbor turns your Mac into a private AI inference server. Run open-weight models locally on Apple silicon—your data never leaves your hardware, and nothing reaches the cloud. Connect multiple Mac computers over Thunderbolt 5 to pool unified memory, enabling large models and higher concurrency that a single computer can handle alone.
Set up in minutes, not hours Harbor automatically detects your devices over Thunderbolt 5 to form a cluster. Plug in, start, and you’re running—no manual configuration, no command line, no infrastructure expertise required.
Download and run models directly Browse, download, and load open-weight models from within the app. Harbor handles model management so you can focus on the work, not the setup.
Cluster for scale Connect two or more Thunderbolt 5-capable Mac computers and Harbor pools their unified memory into a single inference resource. Run models that exceed any single computer’s capacity, or serve more concurrent requests across your cluster.
Harbor is currently in a private preview under the Claris brand.