Relistencode/dsh-recall
Conversation history recall for DSH: three-layer (literal/fuzzy/semantic) retrieval over every past session's original text, fully local & offline — AI never forgets what you told it. One-command install via dsh.bundle.patch, semantic layer runs in a worker thread.
Conversation history recall for DeepSeek Harness — a 'memory maze' for the agent built from every conversation you have had together: every decision, setting, discussion or casually mentioned requirement is remembered. Ask 'where were we?' and it walks the maze, brings back the conversation verbatim, and answers as naturally as if it had never forgotten. Three-layer retrieval (literal / fuzzy / semantic) over every past session, fully local & offline, and compaction-proof: it works even after sessions are compacted away.
Install
dsh plugin --profile web add dsh-recall@0.2.2npm package dsh-recall (0.3.0 on registry, README pins 0.2.2 — registry-verified 2026-08-28): dsh plugin --profile web add dsh-recall@0.2.2, or dsh plugin --profile web add git+https://github.com/Relistencode/dsh-recall.git. Node ≥ 22, DSH web profile, fully local & offline.
Compatibility
DeepSeek Harness web profile. Node ≥ 22. Fully local & offline (no external API).
Details
- Repo: Relistencode/dsh-recall
- Category: Memory
- Stars: 3
- Version: npm dsh-recall (README: 0.2.2; registry latest 0.3.0, verified 2026-08-28)
- Last push: 2026-08-16
- First seen: 2026-08-15
Recent updates
conversation history recall; three-layer retrieval (literal/fuzzy/semantic); fully local & offline; compaction-proof.
FAQ
- Is it offline?
- Yes — 100% local & offline; no external API is involved.
- What retrieval methods does it use?
- Three layers: literal, fuzzy and semantic retrieval over every past session.
- Does compaction erase memories?
- No — recall is compaction-proof; it still finds conversation content after sessions are compacted.
Alternatives
Phant0Meow/dsh-memory-meow · Scorp1o117/dsh-tdai-memory · bwndlct/dsh-session-export