chenkezhen480/dsh-semantic-memory

README excerpt

dsh-plugin-semantic-memory 中文 （README.zh.md，推荐） English Semantic long-term memory for DeepSeek Harness. A dsh-plugin (Cordis plugin) that gives the model a persistent, embedding-based memory across sessions — unlike the harness's built-in session query (literal FTS5), this store retrieves by meaning . Zero-config out of the box : install, restart, and start a new session. The local embedding model downloads itself on first use ( 100 MB); the four tools, per-question recall, and 5-turn auto-summarization all work with defaults. You only configure when you want something different (see Configuration). Features - Cross-session semantic memory — facts, decisions, preferences, and notes persisted as JSONL under $DSH HOME/memories/memories.jsonl . - Embedding retrieval — cosine similarity over normalized vectors; provider is pluggable: - local (default): ONNX inference via @huggingface/transformers with Xenova/bge-small-zh-v1.5 (offline, 100 MB model, cached in /.cache/huggingface ). - api : any OpenAI-compatible /embeddings endpoint (e.g. SiliconFlow, Zhipu, DashScope). - Memory decay & strengthening — each entry's effective strength halves over the configured half-life since its last a…

Category