Launching today
lala.ai
Intelligent • Local first • Reasoning ⚡Built for local first
5 followers
Intelligent • Local first • Reasoning ⚡Built for local first
5 followers
lala.ai is a project-scoped reasoning layer that runs on your machine. Ingest notes, docs, and feeds into projects and reason over them locally.
I built lala because I wanted something that sits between a local LLM runtime and my actual working knowledge, not another generic chatbot, and not a coding agent pretending to know my context. I wanted a tool that could reason over my own notes, docs, research, and project material, stay scoped to a specific project, and run entirely on my machine.
What ships in v1
CLI-first workflow
Project-scoped retrieval
File/folder / RSS ingestion
BM25 / PostgreSQL full-text retrieval
Single-model direct + reasoning flow
lala serve to bootstrap the local runtime
Important: what v1 does not pretend to be
I don’t want to do the usual AI launch thing where the page implies magic that isn’t actually there.
So, plainly:
semantic/vector retrieval is not in the v1 answer path yet
structured memory extraction is not fully real yet
this is not a coding agent
this is not “just works in one click” software yet
There could be many silent bugs present. Please lets me know in case you found
A real setup currently needs:
Docker
an ai-config.yml
local GGUF model files on disk
That setup friction is real, and I’d rather be honest about it than hide it behind marketing copy.
I’d love feedback on 3 things specifically
Does the product category make sense?
Is “local reasoning layer over project knowledge” clear, or is there a better framing?
How painful is the setup story?
I already know this is the weakest part right now. I want blunt feedback on what feels unnecessary or badly designed.
What would make Plan: genuinely valuable for your workflow?
I think this is one of the more interesting parts of lala, but I want to know where it actually helps.
If you try it and it breaks, confuses you, or feels overengineered, say it directly. That’s more useful than polite feedback.
does this need an always-on background process or does it only run when im actively querying a project, kinda curious how much it would bog down my laptop on bigger projects
@metehangtcx Not an always-on background app in the usual sense, but Lala Serve brings up Docker containers, and today you need to stop them yourself. So it’s not constantly “thinking” in the background, but the local runtime does stay up until you shut it down. Bigger projects mainly hit ingestion, retrieval, and local model inference rather than idle overhead.
how does this compare to just using something like Obsidian with an LLM plugin, and does it work offline once the initial setup is done?
@hiraozlen85206
After the initial setup, Lala runs fully offline.
You need Docker, an ai-config.yml, and local GGUF models on disk — but once that’s in place, the runtime is local.
And on the Obsidian question: yes, Obsidian + the right AI plugin + a local model can absolutely cover a lot of similar ground. If you configure it carefully, you can make it private, local-first, and even reasonably project-scoped. That’s a fair comparison, and I don’t want to pretend otherwise.
The difference I’m aiming for with lala.ai is product shape, not “Obsidian can’t do this.”
Obsidian is a knowledge workspace that can be extended with AI.
lala.ai is a local reasoning runtime built around project-bounded context and planning.
So the focus in lala is making a few things explicit instead of plugin-dependent:
project boundary - reason inside a named project, not a vague vault
runtime contract - local models, retrieval, and execution are part of the product itself
planning workflow - Plan: is a first-class mode, not just “chat with my notes”
So yes - if someone already has a great Obsidian + local AI setup, they may not need lala at all. That’s totally valid.
The bet here is that there’s room for a tool that is not a documenting application with AI attached, but a local reasoning system for turning a bounded body of project knowledge into grounded answers and plans
Love that reasoning stays local and project-scoped instead of just being another cloud wrapper, feels like real respect for the user's data.
@n_yalc23333 Exactly the goal: keep reasoning grounded in your own project context, without shipping your knowledge off to a cloud service.