Codeweaver

Name: Codeweaver
Author: knitli

by knitliofficialv0.1.0-alpha.3

CodeWeaver provides AI agents with precise context from codebases through hybrid semantic search, enabling high-quality, structured understanding of code.

From the registry: Semantic code search built for AI agents. Hybrid, AST-aware, context for 166 languages.

GitHub Repository Website

Install & configure

Prerequisites

required
Install code-weaver
Add code-weaver to your project via uv
```
$ uv add code-weaver
```
required
Initialize profile
Run `cw init --profile recommended` or `quickstart` (local)
```
$ cw init --profile recommended
```
required
Start daemon
Start the background indexing daemon
```
$ cw start
```

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `codeweaver` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install code-weaver** — Add code-weaver to your project via uv Run: `uv add code-weaver`
- **Initialize profile** — Run `cw init --profile recommended` or `quickstart` (local) Run: `cw init --profile recommended`
- **Start daemon** — Start the background indexing daemon Run: `cw start`

Canonical MCP server config (stdio transport):
- command: `cw`
- args: ["mcp"]
- optional environment variables:
  - `VOYAGE_API_KEY`: Voyage AI API key (needed with 'recommended' profile) (example: `<your-voyage-api-key>`)

Note: Hybrid semantic/AST/keyword code search with 27 languages. Profiles: recommended (Voyage AI + Qdrant) or quickstart (local FastEmbed + Qdrant).

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: Hybrid semantic/AST/keyword code search with 27 languages. Profiles: recommended (Voyage AI + Qdrant) or quickstart (local FastEmbed + Qdrant).