Comment by jawiggins
16 hours ago
Previously I've shared optio - my project for orchestrating coding agents. It ties into ticketing systems and when assigned a ticket, it launches a coding agent in k8s and works until the PR is ready, resuming for failed CI or PR feedback (https://github.com/jonwiggins/optio/blob/main/docs/persisten...).
I think next I want to try and add features for long term memory for agents, but haven't decided on a good way to do it.
You could have a dedicated lightweight-agent running a cheap model in parallel to any workload, analysing the workload (like the prompt) and creating "memories" in a vector DB. These could be according to some guidelines. Alternatively, if there's safety risk - storing and approving could be decoupled and split into 2.