memweave 命令

常用示例

说明

memweave is a Python library and CLI that gives AI agents a persistent, searchable memory whose primary storage format is plain Markdown. Every memory file is hashed, chunked, and embedded into a single local SQLite database that combines FTS5 keyword ranking with sqlite-vec vector search, so retrieval works offline and merges keyword and semantic signals in one ranked list. Each subcommand maps directly onto a method of the underlying MemWeave Python class, which makes it natural to compose memweave with shell pipelines, editor hooks, and CI jobs without writing Python. Embeddings are cached by content hash, so re-running memweave index is cheap when most files are unchanged, and memweave search never invokes an LLM — only the embedding endpoint.

参数

index

Walk the workspace and embed any Markdown files whose SHA-256 has changed since the last run.

add _file_

Index a single Markdown file immediately.

search _query_

Run a hybrid (BM25 keyword + vector) search across the index.

files

List every tracked file with source labels and chunk counts.

stats

Print a summary of index state, search mode, cache usage, and staleness warnings.

-w, --workspace _PATH_

Workspace directory to operate on (default $PWD).

--embedding-model _NAME_

Override the embedding model (e.g. text-embedding-3-small).

--force

Skip change detection and reprocess every file.

--max-results _N_

Maximum number of search hits to return.

--min-score _F_

Drop hits below a relevance score.

--source-filter _NAME_

Restrict results to a labeled source (e.g. sessions).

--strategy _NAME_

Search strategy: hybrid (default), keyword, or semantic.

--mmr-lambda _F_

Maximal Marginal Relevance trade-off between relevance and diversity.

--decay-half-life-days _N_

Apply temporal decay so older notes rank lower over time.

--json

Emit JSON output suitable for piping into other tools.