Skip to content

knitli/codeweaver

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
CodeWeaver logo

CodeWeaver

Semantic code search for Claude, Gemini, ChatGPT — across 166+ languages

Python Version License Alpha Release MCP Compatible

InstallationFeaturesComparison


What It Does

CodeWeaver gives Claude and other AI agents precise context from your codebase. Not keyword grep. Not whole-file dumps. Actual structural understanding through hybrid semantic search.

You, or Claude, or your intern, can ask questions like:

  • "Where do we handle OAuth tokens?"
  • "Find all API endpoint definitions"
  • "Show me error handling in the payment flow"

CodeWeaver returns the exact functions, classes, and code blocks — even in unfamiliar languages or massive repositories.

Example:

Without CodeWeaver:
  Claude: "Let me search for 'auth'... here are 50 files mentioning authentication"
  Result: Generic code, wrong context, wasted tokens

With CodeWeaver:
  You: "Where do we validate OAuth tokens?"
  Claude gets: The exact 3 functions across 2 files, with surrounding context
  Result: Precise answers, focused context, actual understanding

⚠️ Alpha Release: This works, but it's early. Use it, break it, help shape it.


How CodeWeaver Stacks Up

Quick Reference Matrix

Feature CodeWeaver Serena Cursor Copilot Workspace Sourcegraph Cody Continue.dev Bloop Aider
Approach Semantic search Symbol lookup (LSP) Semantic Semantic Keyword Semantic Semantic Repo maps
Tool Count 1 20+ N/A N/A N/A N/A N/A N/A
Prompt Overhead ~500 tokens ~16,000 tokens N/A N/A N/A N/A N/A N/A
Search Speed Moderate (embeddings) Very fast (LSP) Moderate Server-side Fast Moderate Fast On-demand
Embedding Providers 17 0 (no embeddings) 1-2 1 0 (deprecated) 4-5 1 0
Language Support 166+ ~30 (LSP required) ~50-100 All (text) All ~165 Unknown ~165+
Requires Language Server ❌ No ✅ Yes ❌ No ❌ No ❌ No ❌ No ❌ No ❌ No
Symbol Precision ⚠️ Semantic match ✅ Exact symbols ⚠️ Semantic ⚠️ Semantic ⚠️ Keyword ⚠️ Semantic ⚠️ Semantic ✅ Exact
Concept Search ✅ Yes ❌ Symbols only ✅ Yes ✅ Yes ⚠️ Limited ✅ Yes ✅ Yes ❌ No
Editing Capabilities ❌ No ✅ Yes (9 tools) ✅ Yes ✅ Yes ✅ Yes ✅ Yes ❌ No ✅ Yes

Notes:

  • Serena tool count: Varies by context (20+ in claude-code, up to 35 total available)
  • Serena prompt overhead: Measured with 21 active tools in claude-code context (~16,000 tokens)
  • Language counts: CodeWeaver supports 166+ unique languages (27 with AST parsing, 139 with intelligent delimiter-based chunking)

📊 See detailed competitive analysis →


🚀 Getting Started

Quick Install

Using the CLI with uv:

# Add CodeWeaver to your project
uv add --prerelease allow --dev code-weaver

# Initialize config and MCP setup
cw init

# Verify setup
cw doctor

# Start the server
cw server

📝 Note: cw init defaults to CodeWeaver's recommended profile:

Want full offline? Use cw init --profile quickstart for local-only operation.

🐳 Prefer Docker? See Docker setup guide →

MCP Configuration

To watch and handle your files, CodeWeaver always runs an HTTP server. You can connect to that or use your typical stdio setup:

cw init adds CodeWeaver to your project's .mcp.json:

{
  "mcpServers": {
    "codeweaver": {
      "type": "stdio",
      "cmd": "uv",
      "args": ["run", "codeweaver", "server"],
      "env": {"VOYAGE_API_KEY": "your-key-here"}
    }
  }
}

or with http:

{
  "mcpServers": {
    "codeweaver": {
      "type": "http",
      "url": "http://127.0.0.1:9328"
    }
  }
}

✨ Features

🔍 Smart Search

  • Hybrid search (sparse + dense vectors)
  • AST-level understanding (27 languages)
  • Semantic relationships
  • Language-aware chunking (166+ languages)

🌐 Language Support

  • 27 languages with full AST/semantic parsing
  • 166+ languages with language-aware chunking
  • Cross-language normalization
  • Family heuristics for smart fallback

🔄 Resilient & Offline

  • Full offline operation with local models
  • Automatic failover to backup vector store
  • Works airgapped (no cloud required)
  • Graceful degradation with health monitoring

🔌 Provider Flexibility

  • 17 embedding providers
  • 50+ embedding models
  • Sparse & dense embedding model support
  • 5 reranking providers
  • See full provider list →

⚙️ Configuration

  • ~15 config sources (TOML/YAML/JSON/ENV)
  • Cloud secret stores (AWS/Azure/GCP)
  • Hierarchical merging
  • Profiles for common setups

🛠️ Developer Experience

  • Live indexing with file watching
  • Move detection (no re-indexing duplicates)
  • Full CLI (cw / codeweaver)
  • Health & metrics endpoints

💭 Philosophy

The Bigger Picture

I started building CodeWeaver because I believe AI agents need better context infrastructure. Right now:

  • Agents re-read the same huge files repeatedly
  • They get shallow, text-based context instead of structural understanding
  • They are mostly given tools built for humans, not for how they actually work
  • You don't control what context they see or how they get it

CodeWeaver addresses this with one focused capability: structural + semantic code understanding that you control and can deploy however you want.

Is this solving a big problem? We think so. But we're in alpha; we're probably not there yet. We also need real-world usage to prove it. That's where you come in. Use it, make it better. Worst case -- it's a good tool, best case -- you get better results and cut costs on AI.

📖 Read the detailed rationale →


Built with ❤️ by Knitli

⬆ Back to top