Keel

An AI assistant whose memory belongs to you

Artificial Intelligence

GitHub

Virtual Assistants

Tech

Visit WebsiteSee on Product HuntLoom ⧉Github ⧉Twitter ⧉

Keeping everything in plain markdown on your own machine just feels right. Really like this approach.

The "memory belongs to you" framing is really compelling. Curious about how the memory extraction works in practice. Does it capture everything from every conversation, or does it intelligently decide what's worth remembering? Because the signal-to-noise ratio in my AI chats is probably 20% actual decisions and insights and 80% back-and-forth debugging. Storing all of that would be noisy - storing just the conclusions and key context would be gold.

This is great and I use md files in a very similar way (I just let my coding agent maintain the md files).

One suggestion would be to move away from the Anthropic branding - it looks exactly like an Anthropic product - its confusing

The "memory stays with you, not the vendor" angle is exactly right. We run multiple AI workflows across a B2B services operation and the biggest friction isn't the model — it's that context resets with every session. I've tried solving this with prompt templates and shared docs but neither is clean. Curious how you're handling sync when the same underlying question comes up across different users on the same team?

"Memory belongs to you" is the right framing — but the under-discussed piece is that the memory only compounds value if it's *structured* enough for the assistant to find. Unstructured logs become a noisy haystack the AI re-reads every time; structured memory becomes a template library the AI composes from. We've seen exactly this dynamic on Eloquens (https://www.eloquens.com/channel...) where project-finance model templates work as portable memory across deals — every new mandate is partially solved by what previous mandates already encoded. Question for Keel: do you expose any schema/structure layer so memory can be queried as templates, or is it still primarily unstructured retrieval?

The markdown-on-disk approach is underrated. Most "local AI" tools still phone home for context storage, which defeats the point. One thing I'm curious about: how does Keel handle memory across different models? If I switch from Claude to Ollama mid-project, does the context transfer cleanly or do you lose the thread?

Memory that belongs to the user is a great trust signal — most AI tools make it feel like the data is theirs, not yours. How granular is the control? Can users edit or delete specific memories, or is it all-or-nothing? Curious how you've approached that UX

Hey Medha — 'the day the model gets deprecated, my brain goes with it' should be on the homepage. As a fellow solo founder, looking forward to the Windows build.

@medhaforcebewithyou congrats for the launch l 🚀 As a user, where can I actually see what the assistant remembers about me, and can I delete things if I want to?