Dsh Evolve
chenzheshushi-commits/dsh-evolve · productivity
Self-evolving memory + skill lifecycle for DeepSeek Harness — durable cross-session memory with zero-token deterministic recall, tiered approval, reinforcement learning from repetition, and anti-bloat convergence for bot.
★ 9GitHub stars
0Forks
2026-09-07Last updated
JavaScriptLanguage
MITLicense
Key features
- Structured records (fact / preference / decision / lesson / todo / note) with scope (user = everywhere, project = here) and importance 1–3.
- Model-written memories pass through a deterministic gate that decides auto-confirm vs.
- Re-observing the same understanding doesn't duplicate it — it reinforces it.
- High-value lessons sharing a tag crystallize into a SKILL.md.
- Storage is JSON as the source of truth plus a Markdown mirror you can read and hand-edit.
Requirements
- Degradation is graceful by design: if SQLite/FTS5 is unavailable the plugin falls back to pure bigram recall, and any optional dependency that's missing disables only its own feature.
- It never blocks the harness from booting.
Install command
dsh plugin --profile web add github:chenzheshushi-commits/dsh-evolve