chancelu/dsh-llmwiki

README 摘要

dsh-llmwiki Context Window = RAM, Local Wiki = Disk — long-term memory for DeepSeek Harness, powered by your local Markdown vault. TypeScript port of llmwiki, packaged as a native dsh plugin. What it does Mechanism dsh extension point Inject relevant wiki knowledge into the same turn's model request session/event ( agent/inbox/spliced , pre-assembly live event) → ctx.systemPrompt.context() Teach the model about memory ctx.systemPrompt.section() memory search — model recalls prior sessions / curated notes ctx.tools.register() memory save — model persists durable insights ctx.tools.register() Auto-capture every turn to chronicle/daily/YYYY-MM-DD.md session/event ( turn/end ) Retrieval: keyword + wikilink graph + temporal strategies fused with RRF (Reciprocal Rank Fusion), assembled under a token budget , with an LRU + TTL cache . Zero runtime dependencies beyond Node.js. Vault layout (created automatically) Open it with Obsidian, curate Layer-3 notes with [[wikilinks]] — the graph strategy follows them. Install Requires Node.js ≥ 22 (same as dsh itself) and a working dsh CLI ( npm install -g @deepseek-ai/dsh ) with pnpm on PATH. The package declares dsh.bundle , so dsh plugin add act…

分类