https://github.com/flow-engineer/flow
I built Instinct internally for a product of ours 6 months back, and it got 2000 users within a couple weeks organically.I am now open-sourcing the framework I used so anyone can launch Instinct like experiences on WhatsApp and iMessage.
Both compaction with validation and predictive fetching are the way to go.
I do not want to write an implementation for this myself, and if Synap is that implementation, I'd like to ask you a few questions: 1. Does it work with context that's not just agent conversations, but rather documents? 2. Is it better than RAG on large dataset? 3. What does on-prem options look like?
As a founder, I've always had the hardest time building landing pages.You either buy a template and spend hours editing, or scream at Cursor to "make it beautiful". It's exhausting and waste of our time as founders.We simply need AI to generate beautiful landing pages that we can ship.I'd been working on this problem statement for a while and was able to get great results when I provided AI...
We created a URL similar to https://vscode.dev/github/<organization>/<repo>with a small catch that it creates an AI agent indexed on the repo code + issues.Just use, https://app.commanddash.io/agent?github=your_repo_url.Here is the marketplace of all the agents users have created on Open Source Projects: https://app.commanddash.io/marketplaceAdd yours?