Agent Skills

codeweaver

code reviewknitli12 stars

Semantic code search for AI agents — 166+ languages, hybrid search, works offline

Install

uvx code-weaver
  • CODEWEAVER_CONFIG_FILEoptional — Specify a custom config file path for CodeWeaver. Only needed if not using the default locations.
  • CODEWEAVER_DEBUGoptional — Enable debug mode for CodeWeaver.
  • CODEWEAVER_EMBEDDING_API_KEYoptional · secret — Specify the API key for the embedding provider, if required. Note: {', '.join([p for p in _providers_for_kind('embedding') if p.])}
  • CODEWEAVER_EMBEDDING_MODELoptional — Specify the embedding model to use.
  • CODEWEAVER_EMBEDDING_PROVIDERoptional — Specify the embedding provider to use.
  • CODEWEAVER_HOSToptional — Set the server host for CodeWeaver.
  • CODEWEAVER_LOG_LEVELoptional — Set the log level for CodeWeaver (e.g., DEBUG, INFO, WARNING, ERROR).
  • CODEWEAVER_MCP_PORToptional — Set the MCP server port for CodeWeaver if using http transport for mcp. Not required if using the default port (9328), or stdio transport.
  • CODEWEAVER_PORToptional — Set the port for the codeweaver management server (information and management endpoints).
  • CODEWEAVER_PROFILEoptional — Use a premade provider settings profile for CodeWeaver.
  • CODEWEAVER_PROJECT_NAMEoptional — Set the project name for CodeWeaver.
  • CODEWEAVER_PROJECT_PATHoptional — Set the project path for CodeWeaver.
  • CODEWEAVER_RERANKING_API_KEYoptional · secret — Specify the API key for the reranking provider, if required.
  • CODEWEAVER_RERANKING_MODELoptional — Specify the reranking model to use.
  • CODEWEAVER_RERANKING_PROVIDERoptional — Specify the reranking provider to use.
  • CODEWEAVER_SPARSE_EMBEDDING_MODELoptional — Specify the sparse embedding model to use.
  • CODEWEAVER_SPARSE_EMBEDDING_PROVIDERoptional — Specify the sparse embedding provider to use.
  • CODEWEAVER_VECTOR_STORE_API_KEYoptional · secret — Specify the API key for the vector store, if required.
  • CODEWEAVER_VECTOR_STORE_PORToptional — Specify the port for the vector store.
  • CODEWEAVER_VECTOR_STORE_PROVIDERoptional — Specify the vector store provider to use.
  • CODEWEAVER_VECTOR_STORE_URLoptional — Specify the URL for the vector store.
  • CODEWEAVER__TELEMETRY__DISABLE_TELEMETRYoptional — Disable telemetry data collection.
  • CODEWEAVER__TELEMETRY__TOOLS_OVER_PRIVACYoptional — Opt-in to potentially identifying collection of query and search result data. This is invaluable for helping us improve CodeWeaver's search capabilities. If privacy is a higher priority, do not enable this setting.
  • HTTPS_PROXYoptional — HTTP proxy for requests (Used by: Azure, Azure, Voyage)
  • OPENAI_API_KEYoptional · secret — API key for OpenAI-compatible services (not necessarily an API key *for* OpenAI). The OpenAI client also requires an API key, even if you don't actually need one for your provider (like local Ollama). So provide a dummy key if needed. (Used by: Azure, Cerebras, Deepseek, Fireworks, Github, Groq, Heroku, Moonshot, Ollama, Openai, Openrouter, Perplexity, Together, Vercel, X Ai)
  • OPENAI_LOGoptional — One of: 'debug', 'info', 'warning', 'error' (Used by: Azure, Cerebras, Deepseek, Fireworks, Github, Groq, Heroku, Moonshot, Ollama, Openai, Openrouter, Perplexity, Together, Vercel, X Ai)
  • SSL_CERT_FILEoptional — Path to the SSL certificate file for requests (Used by: Azure, Azure, Voyage)
  • AI_GATEWAY_API_KEYoptional · secret — API key for Vercel service
  • AWS_ACCOUNT_IDoptional — AWS Account ID for Bedrock service
  • AWS_REGIONoptional — AWS region for Bedrock service
  • AWS_SECRET_ACCESS_KEYoptional · secret — AWS Secret Access Key for Bedrock service
  • AZURE_COHERE_API_KEYoptional · secret — API key for Azure Cohere service (cohere models on Azure)
  • AZURE_COHERE_ENDPOINToptional — Endpoint for Azure Cohere service (cohere models on Azure)
  • AZURE_COHERE_REGIONoptional — Region for Azure Cohere service
  • AZURE_OPENAI_API_KEYoptional · secret — API key for Azure OpenAI service (OpenAI models on Azure)
  • AZURE_OPENAI_ENDPOINToptional — Endpoint for Azure OpenAI service (OpenAI models on Azure)
  • AZURE_OPENAI_REGIONoptional — Region for Azure OpenAI service (OpenAI models on Azure)
  • COHERE_API_KEYoptional — Your Cohere API Key
  • CO_API_URLoptional — Host URL for Cohere service
  • DEEPSEEK_API_KEYoptional · secret — API key for DeepSeek service
  • GEMINI_API_KEYoptional — Your Google Gemini API Key
  • GOOGLE_API_KEYoptional — Your Google API Key
  • HF_HUB_VERBOSITYoptional — Log level for Hugging Face Hub client
  • HF_TOKENoptional — API key/token for Hugging Face service
  • HTTPS_PROXYoptional — HTTP proxy for requests
  • INFERENCE_KEYoptional · secret — API key for Heroku service
  • INFERENCE_URLoptional — Host URL for Heroku service
  • MISTRAL_API_KEYoptional — Your Mistral API Key
  • OPENAI_API_KEYoptional · secret — API key for OpenAI-compatible services (not necessarily an API key *for* OpenAI). The OpenAI client also requires an API key, even if you don't actually need one for your provider (like local Ollama). So provide a dummy key if needed.
  • OPENAI_LOGoptional — One of: 'debug', 'info', 'warning', 'error'
  • QDRANT__LOG_LEVELoptional — Log level for Qdrant service
  • QDRANT__SERVICE__API_KEYoptional · secret — API key for Qdrant service
  • QDRANT__SERVICE__ENABLE_TLSoptional — Enable TLS for Qdrant service, expects truthy or false value (e.g. 1 for on, 0 for off).
  • QDRANT__SERVICE__HOSToptional — Hostname of the Qdrant service; do not use for URLs with schemes (e.g. 'http://')
  • QDRANT__SERVICE__HTTP_PORToptional — Port number for the Qdrant service
  • QDRANT__TLS__CERToptional — Path to the TLS certificate file for Qdrant service. Only needed if using a self-signed certificate. If you're using qdrant-cloud, you don't need this.
  • SSL_CERT_FILEoptional — Path to the SSL certificate file for requests
  • TAVILY_API_KEYoptional — Your Tavily API Key
  • TOGETHER_API_KEYoptional · secret — API key for Together service
  • VERCEL_OIDC_TOKENoptional · secret — OIDC token for Vercel service
  • VOYAGE_API_KEYoptional · secret — API key for Voyage service
README.md

[!WARNING]

CodeWeaver is no longer maintained

We're really proud of CodeWeaver and think it's pretty awesome, but we can't maintain it anymore.

We're focused on something else.

CodeWeaver is (was?) a sophisticated, smart, code search tool with wide provider support. and it's still licensed under your choice of MIT or Apache-2.0.

So please, fork it and build something great!

CodeWeaver logo

CodeWeaver

Exquisite Context for Agents — Infrastructure that is Extensible, Predictable, and Resilient.

Python Version License Release MCP Compatible codecov

Documentation • Installation • Features • Comparison

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.

CodeWeaver is Professional Context Infrastructure. With 100% Dependency Injection (DI) and a Pydantic-driven configuration system, it provides the reliability and extensibility required for industrial-grade AI deployments.

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, 60-80% token reduction

CodeWeaver is no longer in alpha!

Early Release (0.x): CodeWeaver is in active development. APIs may change between minor versions. It's very well-tested but still in 'it works on my machine' territory. Use it, break it, help shape it.

How CodeWeaver Stacks Up

Quick Reference Matrix

Feature CodeWeaver Legacy Search Tools
Search Type Hybrid (Semantic + AST + Keyword) Keyword Only
Context Quality Exquisite / High-Precision Noisy / Irrelevant
Extensibility DI-Driven (Zero-Code Provider Swap) Hardcoded
Reliability Resilient (Automatic Local Fallback) Fails on API Timeout
Token Usage Optimized (60–80% Reduction) Wasted on Noise

🚀 Getting Started

Quick Install

Using the CLI with uv:

# Add CodeWeaver to your project
uv add code-weaver

# Initialize with a profile (recommended uses Voyage AI)
cw init --profile recommended

# Verify setup
cw doctor

# Start the background daemon
cw start

📝 Note: cw init supports different Profiles:

  • recommended: High-precision search (Voyage AI + Qdrant)
  • quickstart: 100% local, private, and free (FastEmbed + Local Qdrant)

Want full offline? See the Local-Only Guide.

🐳 Prefer Docker? See Docker setup guide →

✨ Features

🔍 Exquisite Context

  • Hybrid search (sparse + dense vectors)
  • AST-level understanding (27 languages)
  • Reciprocal Rank Fusion (RRF)
  • Language-aware chunking (166+ languages)

🛡️ Industrial Resilience

  • Automatic local fallback (FastEmbed)
  • Circuit breaker pattern for APIs
  • Works airgapped (no cloud required)
  • Pydantic-driven validation at boot-time

🧩 Universal Extensibility

  • 100% DI-driven architecture
  • 17+ integrated providers
  • Custom provider API
  • Zero-code provider swapping

🛠️ Developer Experience

  • Live indexing with file watching
  • Diagnostic tool (cw doctor)
  • Multiple CLI aliases (cw / codeweaver)
  • Selectable profiles for easy setup

💭 Philosophy: Context is Oxygen

AI agents face too much irrelevant context, causing token waste, missed patterns, and hallucinations. CodeWeaver addresses this with one focused capability: structural + semantic code understanding that you control.

  • Curation over Collection: Give agents exactly what they need, nothing more.
  • Privacy-First: Your code stays local if you want it to.
  • Infrastructure over Tooling: Built to be the reliable foundation for your AI stack.

📖 Read the detailed rationale →

Official Documentation: docs.knitli.com/codeweaver/

Built with ❤️ by Knitli

⬆ Back to top

Related servers

gitdiagramahmedkhaleel200418KVisualize any GitHub codebase: free interactive architecture diagrams and one-minute explainer videos. Replace 'hub' with 'diagram' in any GitHub URL.repowiserepowise-dev7.1KCodebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.sembleminishlab6.2KFast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+readcodegraphcontextshashankss12054.2KAn MCP server plus a CLI tool that indexes local code into a graph database to provide context to AI assistants.

Search skills and MCP servers

Fuzzy search across 23,137 skills and servers