As a founder, I can definitely feel this pain.
So much company knowledge is just the thing on our laptops, and then we hope we can write accurate docs later. Actually we can't because our docs usually miss some important context.
If this can turn the actual workflow into a usable guide, I can see it help a lot with onboarding and customer handoffs.
Maybe we can use some tool like yours later to improve how we organize company knowledge!
Cool. After reading your README, the "post-part" hook is the most interesting part for me. Chunk-level hooks make it easier to plug into things like rclone or other workflows.
As you mentioned, the single .rapel-state.json file tracks all chunk metadata. Does that state also pin the origin file identity while resuming, so it can detect if the remote file changed between sessions?
The repo-native approach is pretty cool.
Many agent systems still feel opaque because the operational context is buried within prompts and tools. Putting the company memory into Git makes the whole thing much more inspectable.
For me, the interesting part is the review loop after agents have written the code. For a native app that handles files and sanitized HTML, did you rely more on tests, manual use, or reading the generated Rust/JS directly?
It makes sense to do replay before prevention. For an agent, the challenge is often not recognizing that a bad action occurred, but reconstructing the complete decision context that led to it.
I'm wondering how you handle replay if the retrieved context or external state has changed since the original run.
For me, the interesting part here isn't GPT-2, it's the memory discipline. I feel like most inference runtimes slowly leak allocations everywhere as features pile up.
Do you think the DMG installation method will continue to be a long-term part of the macOS ecosystem, or is it more of a continuation of indie Mac culture?
So innovative!
I've talked to your goose and I found this is really a great way to test whether I truly understand concept. I don't know how the goose thinks, maybe it would be even better if it allowed me to upload my own data and ask questions based on that context.
I think your concept of this APP is meaningful for most people.
I'm curious to know how you handle data calibration, especially when it comes to different regions, remote offers, and issues with uneven sample distribution.
Awesome job! It really frees up my hands. As another reviewer mentioned, I’m so curious to know exactly what this robot can do when cleaning a room, how thoroughly it cleans, and who can monitor its status and how.
The way you color these trails is so good! It is clearer and easier to read than other existing maps. Also the information is detailed so that users can have an expectation before going there.
I'm just wondering if you plan to expand yours beyond the US eventually?
This idea is super cool! I love traveling and feel that the core of a trip is exploring local/authentic life, so your product perfectly matches my needs! If all people sharing their routes are local and the recommendations are real, not ads, it will be reliable for me to use it to find places.
Just one thing, I can't use it in my country:( Hope you can make it globally:)
Love this kind of project, honestly. Feels way more real than most AI wrapper stuff. Just wondering how stable the Pandora API ended up being after reverse-engineering it.
Pretty cool to see someone actually running public ODoH infra instead of just talking about privacy in theory. I'm just wondering what the biggest operational pain has been so far running a public relay.
A lot of agent workflows really are just tool selection + argument extraction + structured output. How does this behave once workflows become multi-step and state starts accumulating across calls?
I really like your local-first idea. Just one question: what do you think is still the biggest weakness of local OCR models compared with cloud APIs? Is it layout parsing, reading order, or messy scans?