Open-source self-hosted alternative to Notion, Evernote, and Obsidian Sync.

https://github.com/gamosoft/NoteDiscovery https://x.com/tom_doerr/status/2082550801872929081

Runs a 1-billion parameter LLM locally on low-cost hardware using just 45MB of RAM and zero dependencies.

https://github.com/RightNow-AI/picolm https://x.com/tom_doerr/status/2082780186316075060

Day 576: Won $10,500 in the Hyperbeat Fantasy league. 🏆

I told you this was one of the craziest $0 entry cost opportunities I'd seen.

After the sybil review, I moved from 3rd to 1st place and took home the top prize.

Huge thank you to everyone who used my referral. Your activity helped me secure the win, and as promised, everyone who met the volume requirement received $100 from me.

Thank you, Hyperbeat.
Thank you to everyone who used my referral.

Let's keep winning together.

AirPodsDesktop brings Apple AirPods functionality to Windows and Linux by displaying battery levels and enabling features like automatic ear detection and low latency audio.

https://github.com/SpriteOvO/AirPodsDesktop https://x.com/tom_doerr/status/2082532370368880717

I cut Fable 5 token usage 2.5x with just one change!

(100% open-source solution)

- Before: 5.5 M tokens · 7 errors · $8.94
- After: 2.3 M tokens · 0 errors · $4.17

The final build was the same for both, but the path the agent took wildly differed.

In both runs, the agent started with the same thing, i.e., it understood the backend before building anything, like:

- Permission policies
- Available storage buckets
- Auth providers configured
- How edge functions are deployed

The first run used Firebase, which was built for a human dev using a dashboard.

While the dev can read the above state by clicking through tabs, an agent has no dashboard. So it gathered the same info through API calls.

And there's no single Firebase call that returned this info. The agent required to query multiple times, and each query over-returned.

For instance, when the agent asked how sign-in is configured, Firebase also returned the entire auth surface and every method it supported.

This was far more context than what it needed. And it repeated across every part of the backend it inspected.

Some states (like which auth providers are active) weren't queryable at all. I provided it myself. Otherwise, the agent would have guessed.

Errors further compounded the token usage.

When a dev sees "permission denied," they can look at the console and figure out whether it's a rule, a path, or an unauthenticated request.

Firebase returned the same string to the agent as well, and it had none of that surrounding context to debug.

So it guessed again, picked the most likely cause, and rewrote code, utilizing more tokens.

This Firebase setup cost me 5.5M tokens and 7 manual interventions during errors on a full-stack RAG app.

But I brought that down to 2.3M tokens and 0 manual interventions by using InsForge as the backend context engineering layer (open-source and self-hostable via Docker).

It provides the same primitives as Supabase/Firebase, but structures the entire information layer for agents, instead of dashboards.

In one CLI call that consumed ~500 tokens, the agent saw the full backend topology before writing a single line of code.

This included auth, database, storage, edge functions, model gateway, micro VMs, and deployment.

Also, instead of loading the entire product surface into context on every task, four narrowly scoped skills activated only when relevant to keep cognitive load minimal.

And to ensure efficient retries if needed, every CLI operation returned structured JSON with meaningful exit codes, so the agent never guessed what to do next.

Here's the InsForge GitHub Repo: https://github.com/InsForge/InsForge

(don't forget to star 🌟)

The video below depicts the final build, comparing Firebase and InsForge.

If you want to dive deeper, my co-founder recently published a full walkthrough building the same RAG app on both backends and inspected them end-to-end.

The article is quoted below!

Tested MiniMax H3 against Seedance 2.0 using the exact same video sequence via Omni Reference.

Honestly surprised. H3 wins on prompt accuracy, smoother camera work, sound design, and overall narrative flow. It just feels way more cohesive and polished. https://x.com/socialwithaayan/status/2082799820167905359

If you want to become god-level with AI engineering, then learn these 17 concepts (save now):