I feel like I'm always behind the LLM crazy-curve. I'm also getting sick of context switching between LLM apps. Me and Claude Code are basically down to pair-writing test cases, documentation, and commit messages. Now that Perplexity is moving into the desktop space I thought I'd show what I've got to HN and see if I can get some more hands on King Louie.
It has 13 providers, rules to pick the best LLM for each task, agents with a couple dozen built-in tools, semantic memory with embeddings, P2P mesh networking, and a skill system. The LLM-written README.md gives more in-depth details.
Happy to answer questions about the architecture, routing engine, and how I deal with context reduction. Also actively looking for contributors. Cross platform, JavaScript/Electron, MIT licensed, and plenty of unsolved problems left if you're into agent tooling, LLM routing, Context Reduction, or P2P networking.
Atlas designs and shapes the future of computing products. Atlas Wristband is a fitness monitor
that identifies your exercises, counts your reps and sets, calculates the calories you burned and
evaluates your form.
POSITION DESCRIPTION
We are currently looking for a skilled front-end web developer to help design and maintain the
Atlas Wearables public site, user dashboard and HTML5-based mobile apps; all in a motivated
and creative environment with a close-knit team.
Our stack is Python/Django/Maria+Redis+Mongo/Angular (moving to React)/Cordova
To be honest, I think the $10BN figure is a number that was pulled out of thin air. Project connect is estimated at around $1.4BN and covers a lot of the same area, just above ground.
I've been using this since it launched, it's invaluable in helping answer the question of "I wonder what people's knee-jerk reaction is to this change..."
Just curious...will you be paying the retailers up-front and dealing with the customers or just be a middle-man and the retailers receive payment as the customer pays?