Show HN: Continual Learning with .md (github.com)

[flagged]

I've seen a lot of such systems come and go. One of my friends is working on probably the best (VC-funded) memory system right now.

The problem always is that when there are too many memories, the context gets overloaded and the AI starts ignoring the system prompt.

Definitely not a solved problem, and there need to be benchmarks to evaluate these solutions. Benchmarks themselves can be easily gamed and not universally applicable.

is this based on Karapathy's LLM Wiki idea (link: https://gist.github.com/karpathy/442a6bf555914893e9891c11519...)? . I leveraged Karapathy's wiki idea and built MCPTube- it's a CLI and also an MCP server that turns YouTube videos into a compounding knowledge base. Check it out and let me know what you think (link: https://github.com/0xchamin/mcptube)

Using the same approach for dev documentation storage: https://ctxlayer.dev/

Has been working for me for a couple of months already. So far human curation of context is the way to go.

Seems interesting. Ill give it a try on my agent, memory is definitely an ongoing issue. How long have you been running this in a continuous state? Also have you tried other LLM's and seen a difference on how well they can use it?

Your example is with Codex - OpenAI could implement this easily on their end right? Every prompt of yours was an API call and they have a log, they can easily re-create a quick history of what you did/asked for before?

I love how you approached this with markdown !

I guess the markdown approach really has a advantage over others.

PS : Something I built on markdown : https://voiden.md/

Have you noticed an relationship between recall and the number of files/memories?

I really like the simplicity of this! What's retrieval performance and speed like?

[dead]

[dead]

[dead]