# AGENTS.md
- Remove obsolete paths. Ship only current code.
- Use simplest code that meets needs now.
- Build in layers. Ship smallest working version first. Add on top of working product.
- Keep modules separate with clear concerns.
- Prefer mature libraries that simplify or stabilize.
- Check existing deps, docs, and types first.
- Design for the long term.
- Study proven products. Adopt their patterns.
Replying to @helloiamleonie @liquidai
Amazing work congrats!
I love this space, finally I can get a decent model to fit full ctx in my 6gb vram
Replying to @1kartikkabadi1
it's so token efficient it's ridiculous
Replying to @leo114119
Have you even tried Terra?
That model is a beast!
So token efficient is ridiculous. Almost like it doesn't even think
Replying to @0xWhiteMage
yes , this at 300 freaking million tokens
Replying to @brandon_galang
Openai even more than anthropic
Their models are so token efficient
Replying to @RamaswmySridhar
Open models were focused on coding not general intelligence.
Also much smaller Nr of params
Billions Vs Trillions
Replying to @daveeyyy_
Tera is the most efficient intel/tokens model ever imo
Replying to @thdxr
thank you for this.
the push I needed for my agent.
Though in the past you said we shouldn't even try coz you guys are so ahead?
Replying to @NartOutHere
It's raining in Bucharest since last 3 days.
Replying to @brandonkruger @DogukanUrker
Don't expect miracles. It's good at tool calling agentic stuff
Not very smart
