- Building a Retool/Looker alternative for internal tools so non-technical teams can build their own without creating busywork for engineers.
- Works like Lovable/Replit with two differences: Got 3,000 integrations out of the box through Pipedream SDK and got access controls in place with embedded auth, backend (django) and database
Analysis done with Claude Code and then Codex to verify. Each agent was given API keys in free tiers to play around and test the sandboxes for various things.
Fair point the README focuses more on benchmarks than implementation here's the short version:
1. Use `git ls-files` instead of walking the filesystem (huge speed win - dropped Chromium 59GB scan from 6.6s to 0.46s)
2. Parse each file path into components (folders, filename, extension)
3. Score each file based on how query terms match path components, weighted by position and depth
4. Return top N matches sorted by score
The core insight: /services/stripe/webhook.handler.ts already encodes the semantic relationship between "stripe" and "webhook" through its structure. No need to read file contents or generate embeddings.
I should add an architecture doc to the repo, thanks for the nudge.
There was an old legendary HN comment around the following concept:
"All things being equal, people buy from their friends. So just make more friends"
If you are confident of your services, just make more friends. Talk to people more. If it is too salesly already, you lost the conversation. Instead try and learn about their lives. I sometimes even open up with "No agenda to sell, genuinely curious"
Note: If anyone finds the link to the comment, please drop it here to credit the author.
Banker.so | Computer inside a computer inside an agent
Started this out by building a spreadsheet controlled by an LLM. Now putting a direct filesystem inside, simplified enough to have programmatic control of slide builders, spreadsheets, terminals and vibecoding applications
reply