Sunstone Weave: Local Semantic Code Search
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BLACKWINDOW_WEAVE_CACHE | No | Where the encoder and the indexes live. Default `~/.cache/blackwindow-weave`. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| weave_folderA | Index a folder on this machine (source code and docs) for semantic search, or bring its index up to date: only files that changed since the last run are read again. Call it once per project. The first run downloads the 33M-parameter encoder (133 MB) and embeds every passage on the CPU; a run longer than 25 s continues in the background and weave_list reports its progress. |
| weave_searchA | Search the woven folders in plain language: where something is defined, handled, configured or explained. Returns the nearest passages with their file, line range and centred-cosine score. Use it before grep when you do not know the identifier or file name. |
| weave_listA | List the folders this server has indexed, with their file and passage counts. |
| weave_forgetA | Delete a folder's index from this machine. The folder's own files are not touched. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool maps to a distinct operation in the indexing lifecycle: index (weave_folder), query (weave_search), inspect (weave_list), and remove (weave_forget). There is no meaningful overlap, and the descriptions reinforce when to use each (e.g. search before grep).
The weave_ prefix is applied uniformly, giving a clear namespace. Suffixes are mostly verbs (search, list, forget) except weave_folder, which is a noun referring to the resource it indexes, a minor deviation but still readable and predictable.
Four tools is a tight, well-scoped set for a semantic-index server: create, query, enumerate, and delete. It is on the lean side with no configuration or content-retrieval tool, but each tool earns its place and nothing feels redundant.
The index lifecycle is fully covered: build/refresh (weave_folder), search (weave_search), list (weave_list), and delete (weave_forget), with re-indexing handled by weave_folder's incremental behavior. Minor gap: no tool to fetch a passage's or file's contents directly, so agents must fall back on other file-reading tools after a search hit.