Show HN: Komi-learn – continuous memory and self-improvement for coding agents
rainxchzed
21 points
3 comments
May 31, 2026
Related Discussions
Found 5 related stories in 85.4ms across 9,043 title embeddings via pgvector HNSW
- Show HN: Hippo, biologically inspired memory for AI agents kitfunso · 72 pts · April 06, 2026 · 59% similar
- Show HN: Continual Learning with .md wenhan_zhou · 23 pts · April 13, 2026 · 58% similar
- Show HN: AI memory with biological decay (52% recall) SachitRafa · 82 pts · April 26, 2026 · 57% similar
- Show HN: Agent Kernel – Three Markdown files that make any AI agent stateful obilgic · 40 pts · March 23, 2026 · 55% similar
- Show HN: Omar – A TUI for managing 100 coding agents karim7 · 12 pts · May 01, 2026 · 55% similar
Discussion Highlights (1 comments)
loehnsberg
It sounds like it solves the problem that everybody who vibe codes over multiple projects runs into, but it does not provide evidence that it actually works and that it is better than structured collection of md files. I think what is lacking in this field are benchmarks like LoCoMo for long sessions.