freshcrate
Skin:/
Home > MCP Servers > codeweaver

codeweaver

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

Why this rank:Healthy release cadenceStrong adoptionRelease freshness

Description

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

README

CodeWeaver logo

CodeWeaver

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

Python Version License Release MCP Compatible codecov

DocumentationInstallationFeaturesComparison


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

📊 See detailed competitive analysis →


🚀 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

Release History

VersionChangesUrgencyDate
v0.1.2## What's Changed ## [0.1.2] - 2026-04-16 <!-- generated by git-cliff --> ## Installation Install from PyPI: ```bash pip install code-weaver ``` Or download the wheel/source distribution from the assets below. ## Verification All release artifacts are built from source and include: - 📦 Wheel distribution (.whl) - 📦 Source distribution (.tar.gz) **Full Changelog**: https://github.com/knitli/codeweaver/compare/v0.1.1...v0.1.2 High4/16/2026
vrefs/heads/main## What's Changed ## [refs/heads/main] - 2026-04-17 ### Documentation - Docs(changelog): prepend v0.1.2 [skip ci] - Docs(api): Remove API pages that do not have useful API surface, rebuild remaining docs ### Features - Feat(doc): docs launched! <!-- generated by git-cliff --> ## Installation **This is a pre-release version.** Install with: ```bash pip install --pre code-weaver # Or specific version: pip install code-weaver==refs/heads/main ``` Or download the wheel/source distribution fHigh4/16/2026
v0.1.1## What's Changed ## [0.1.0] - 2026-04-06 ### Bug Fixes- fix: remove null include key in _reusable-test.yml matrix strategy; add pkl to mise.toml ([#298](https://github.com/knitli/codeweaver/pull/298)) ### Other Changes- Prepare for v0.1.0 release with versioning updates ([#296](https://github.com/knitli/codeweaver/pull/296)) <!-- generated by git-cliff --> ## Installation Install from PyPI: ```bash pip install code-weaver ``` Or download the wheel/source distribution from the assets belowHigh4/7/2026
v0.1.0## What's Changed ## [0.1.0] - 2026-04-06 CodeWeaver v0.1.0 — First stable release Extensible MCP server for semantic code search, graduating from 5 alpha releases and 316 commits of hardening. Highlights: - Single find_code tool interface for intelligent codebase context - 20+ embedding providers (Voyage, OpenAI, Cohere, Bedrock, local) - Qdrant vector store with in-memory and server modes - AST-based semantic chunking for 20+ languages, delimiter chunking fMedium4/6/2026
v0.1.0-alpha.5## What's Changed ## [0.1.0-alpha.5] - 2025-12-04 ### Bug Fixes- fix: copilot-oom errors and qdrant healthcheck failures in ci ([#192](https://github.com/knitli/codeweaver/pull/192))- feat: implement automatic embedding reconciliation in indexer, add related tests, fix issue preventing sparse embedding storage ([#188](https://github.com/knitli/codeweaver/pull/188)) ### Other Changes- Feat: Initial docs implementation with Starlight -- Proof of Concept ([#193](https://github.com/knitli/codeweaLow12/4/2025
v0.1.0-alpha.4## What's Changed ## [0.1.0-alpha.4] - 2025-12-03 <!-- generated by git-cliff --> ## Installation **This is a pre-release version.** Install with: ```bash pip install --pre code-weaver # Or specific version: pip install code-weaver==0.1.0-alpha.4 ``` Or download the wheel/source distribution from the assets below. ## Verification All release artifacts are built from source and include: - 📦 Wheel distribution (.whl) - 📦 Source distribution (.tar.gz) **Full Changelog**: https://github.comLow12/3/2025
v0.1.0-alpha.3## What's Changed ## [0.1.0-alpha.3] - 2025-12-02 ### Bug Fixes- fix: resolve critical relative path issues in packaged build Approved. There are two failing tests from other work; will be resolved in other commits. ([#185](https://github.com/knitli/codeweaver/pull/185)) ### Other Changes- feat: default stdio transport; add background daemon and daemon persistence, improve test coverage PR Approved. server.json issue will be addressed in another PR; CLA failure is a known issue getting addrLow12/3/2025
v0.1.0-alpha.2## What's Changed ## [0.1.0-alpha.2] - 2025-12-02 ### Bug Fixes- fix: replace unsupported 'find' filter in git-cliff template ([#183](https://github.com/knitli/codeweaver/pull/183))- Verify sparse-only vector search fix (ISSUE-001) ([#176](https://github.com/knitli/codeweaver/pull/176))- Fix Docker Compose CI test failures - correct Qdrant health endpoint ([#178](https://github.com/knitli/codeweaver/pull/178))- chore: Add plans for server separation of services refactor to enable… ([#179](httpLow12/2/2025
v0.1.0-alpha.1## What's Changed - Initial alpha release ## Installation **This is a pre-release version.** Install with: ```bash pip install --pre codeweaver # Or specific version: pip install code-weaver==0.1.0-alpha.1 ``` Or download the wheel/source distribution from the assets below. ## Verification All release artifacts are built from source and include: - 📦 Wheel distribution (.whl) - 📦 Source distribution (.tar.gz) **Full Changelog**: https://github.com/knitli/codeweaver/compare/v0.1.0-alpha.1Low11/27/2025

Dependencies & License Audit

Loading dependencies...

Similar Packages

claude-code-plugins-plus-skills423 plugins, 2,849 skills, 177 agents for Claude Code. Open-source marketplace at tonsofskills.com with the ccpi CLI package manager.@intentsolutionsio/intent-labs-pack@0.1.0
AgentGuardProtect AI agents by detecting and blocking prompt, command injection, Unicode bypass, and social engineering attacks with customizable security controls.main@2026-09-10
Athena-PublicThe Linux OS for AI Agents — Persistent memory, autonomy, and time-awareness for any LLM. Own the state. Rent the intelligence.v9.9.9
codelogic-mcp-serverAn MCP Server to utilize Codelogic's rich software dependency data in your AI programming assistant.v1.3.2
pentest-mcp-server⚙️ Enable AI agents to conduct autonomous penetration testing on any Linux distribution with a persistent and robust Model Context Protocol server.main@2026-06-12

More in MCP Servers

difyProduction-ready platform for agentic workflow development.
tabularisA lightweight, cross-platform database client for developers. Supports MySQL, PostgreSQL and SQLite. Hackable with plugins. Built for speed, security, and aesthetics.
ai-agents-from-zero 🚀 2026 最系统的 AI Agent 速成指南|智能体实战教程 · 完整学习路径 + 实战项目 + 面试题库 · 对标大模型应用开发工程师岗位 · 覆盖LangChain / LangGraph / Coze / Dify / MCP / skills / LLM / RAG / 提示词 · 企业级部署与微调 · 从0到企业级落地 + 从学习到上线项目 + 面试准备一体化
studioOpen-source control plane for your AI agents. Connect tools, hire agents, track every token and dollar