11–20 of 147 posts
I do not get it. If the agent is not mutating state the change can be checked in. If it is mutating external state, version control won't save you.
1. to have a human in the loop to approve certain changes 2. rollback changes that end up being incorrect 3. allow reviewing the timeline and history to figure out what changed and how
Just my two cents: less is more and the first impression matters a lot. I'm saying this because we see a new agent sandbox tool on the front-page almost every day. Most of them have an AI-made landing page design, lots of animations, lots of words. This has become a bad sign for me. I can tell that you put time into it, made a video, and everything, but I guess I'm suffering from some kind of fatigue of having to go…
Do git and branching fit into this at all?
Interesting. Literally saw a tweet talking about exactly this last night. Not sure how I feel about it using on your hosted service, while your home page is asking me for analytics data and only the cli and sdk are open source.
Fair enough - the underlying technology is indeed open source ( https://github.com/treeverse/lakeFS ) - the service provides the hosting and tooling to make it easy for consumption by agents.
I get providing a hosted service, but I don't understand how it makes it easier for agents to consume unless you're hosting an MCP? My understanding is an agent skill and a cli tool is all an agent needs?
I do not get it. If the agent is not mutating state the change can be checked in. If it is mutating external state, version control won't save you.
the repo acts as a source of truth for agents. think memory, data & code. If an agent decides to change any of those, version control allows: 1. to have a human in the loop to approve certain changes 2. rollback changes that end up being incorrect 3. allow reviewing the timeline and history to figure out what changed and how
Interesting. Their versioned storage sandbox seems to be what really sets them apart
I don't get it, it looks like they are copying data to the sandbox filesystem why would that impact production data? Because the agent can re-upload the file to s3?
That said, using LakeFS is probably a better long term solution and I like this approach.
Just my two cents: less is more and the first impression matters a lot. I'm saying this because we see a new agent sandbox tool on the front-page almost every day. Most of them have an AI-made landing page design, lots of animations, lots of words. This has become a bad sign for me. I can tell that you put time into it, made a video, and everything, but I guess I'm suffering from some kind of fatigue of having to go…
Earlier quoted context omitted.
Fair enough - the underlying technology is indeed open source ( https://github.com/treeverse/lakeFS ) - the service provides the hosting and tooling to make it easy for consumption by agents.
Thats a cool project. I didn't scroll down far enough to see that. Thanks for the correction I get providing a hosted service, but I don't understand how it makes it easier for agents to consume unless you're hosting an MCP? My understanding is an agent skill and a cli tool is all an agent needs?