Show HN: Continual Learning with .md (github.com)
I have a proposal that addresses long-term memory problems for LLMs when new data arrives continuously (cheaply!). The program involves no code, but two Markdown files.
For retrieval, there is a semantic filesystem that makes it easy for LLMs to search using shell commands.
It is currently a scrappy v1, but it works better than anything I have tried.
Curious for any feedback!
18 comments
[ 164 ms ] story [ 509 ms ] threadGood question. Since it is just an LLM reading files, it depends entirely on how fast it can call tools, so it depends on the token/s of the model.
Haven't done a formal benchmark, but from the vibes, it feels like a few seconds for GPT-5.4-high per query.
There is an implicit "caching" mechanism, so the more you use it, the smoother it will feel.
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.
You need clever naming for the filesystem and exploration policy in AGENTS.md. (not trivial!)
The benchmark is definitely the core bottleneck. I don't know any good benchmark for this, probably an open research question in itself.
I think in terms of noise, it is less problematic here because not everything is being retrieved. The agent can selectively explore subsets of the tree (plus you can edit the exploration policy by yourself).
Since there is no context bloat, it is quite forgivable to just write things down.
I guess the markdown approach really has a advantage over others.
PS : Something I built on markdown : https://voiden.md/
Has been working for me for a couple of months already. So far human curation of context is the way to go.