The local first approach is definitely the right move for project memory. How do you handle context window limits when a project memory stats getting large?
Interesting approach! I've been working on something complementary — local-first LLM observability called opensmith. Different angle but same philosophy of keeping everything local.
The local first approach is definitely the right move for project memory. How do you handle context window limits when a project memory stats getting large?
Interesting approach! I've been working on something complementary — local-first LLM observability called opensmith. Different angle but same philosophy of keeping everything local.