Indeed. With Lowdefy we really try to go to great effort to abstract away the plumbing. We're very pleased with how simple the config surface is for these Agents.
Sure. We've been building Lowdefy since 2020, we use it as the web framework for all our consulting customers at https://resonancy.io , where we build back office software for businesses.
We've built all kinds of internal tools using Lowdefy, CRMs, reporting apps, ticketing systems, workflow, SOP and QC tools, call centre automation tools, customer portals, survey apps and more.
We find that having a well define abstraction framework in place helps us scale our custom apps really efficiently, particularly from a maintenance pov. Also sharing work across our team, etc. It helps if everything is pluggable, and well documented. By making Lowdefy open-source it has helped our team maintain the discipline to enforce best practices across our stack.
Lowdefy is very declarative, and it lets you build data intensive web apps in just a few lines of yaml. With AI code gen, this is where the power of the framework guard rails and generated apps really accelerate the apps we can create while following the same patterns that our team applies over all the solutions we build.
As for change in direction, no. We have a demand for building agentic experiences from our customers, and found that we could wrap it really nicely into the Lowdefy framework, especially when building in additional functionality like agents co-authoring web forms and more.
We feel that agents inside your apps is a great fit, since you can expose the same api routes, auth roles and more to agents with ease.
Well done on the launch! We’ve doubled down on the apps as YAML paradigm a few years ago and its pay great dividends on all fronts, esp now with code gen spinning out apps faster than ever for us (generated yaml). Our largest app is well over 500k lines of yaml - for those complaining about 1000 lines lol. With the right tool stack and conventions its so much easier to read, write. review and maintain.
Shameless plug, we’ve built Lowdefy (open source) and 100s of dashboards using it. Have a look and keen to unpack if you’re interested in sharing experiences. Specially have a look at what we did with operators for dynamic needs.
https://github.com/lowdefy/lowdefy
It sure is hard. But have a closer look, these guys have been going over the results for 10 years improving, refining and discarding. What also helps is that they are highly regarded career scientists and engineers. Dig a little deeper on this one..
Not saying that it can’t be faulty experiments / results.. But truely nice to see some experimental science.
Well done on this milestone! Gave zed a decent chance last week and it wins on many fronts to replace my now scattered setup.
1. For me to use it I need to apply prettier formatting of the current project (maybe there is a way? i could not find it)
2. I need to run the claude cli, not an agent interface. or allow me to place the terminal on the left in the agent view or something.
for the everything else it was a win. will give it another chance in a month or three to see if it can do, excited to have a setup that easily navigates code diffs.
This is a very exciting field, more specifically in combination with asymmetric capacitors.
Exodus Propulsion [0] under NASA’s lead scientist of electrostatics, Dr Charles Buhler and his team have been observing some very puzzling and exciting results. Would recommend anyone interested in this to check this out.
[0] - https://www.exoduspropulsion.space
As far as I know they are still trying to piece together the underlying physics, but they are 10 years in and 1000s of experiments later, some of which has been reproduced.
Anyone else looking at these developments and thinking that local llms are the future. So many advantages above remote, and the hardware is just not there jet, but another leap like apple silicon and the tech is there..
Ofcourse large corps will have fancy proprietary models, but for every day queries and tasks, local feels like a huge, and just slightly out of reach.
For me this is where a config layer shines. Develop a decent framework and then let the agents spin out the configuration.
This allows a trusted and tested abstraction layer that does not shift and makes maintenance easier, while making the code that the agents generate easier to review and it also uses much less tokens.
This is a very cool idea. I’ve been dragging CC around very large code bases with a lot of docs and stuff. it does great but can be a swing and a miss.. have been wondering if there is a more efficient / effective way. This got me thinking. Thanks for sharing!
https://youtu.be/0A3sGymV6kY