Weave
A highly efficient, secure, and stable application development platform with excellent performance, easy scalability, and deep integration of AI capabilities such as LLM, AI Chat, RAG, and Agents.高效、安全、稳定的服务研发平台，具备良好性能，同时易扩展，深度集成LLM、AIChat、RAG、Agent等
What is Weave?
Weave is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to highly efficient, secure, and stable application development platform with excellent performance, easy scalability, and deep integration of ai capabilities such as llm, ai chat, rag, and agents.高效、安全、...
A highly efficient, secure, and stable application development platform with excellent performance, easy scalability, and deep integration of AI capabilities such as LLM, AI Chat, RAG, and Agents.高效、安全、稳定的服务研发平台，具备良好性能，同时易扩展，深度集成LLM、AIChat、RAG、Agent等
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A highly efficient, secure, and stable application developme
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx weaveConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Weave
Weave is an AI-powered Git merge driver that uses tree-sitter for syntax-aware conflict resolution, allowing it to intelligently merge code changes that would otherwise produce conflicts. Written in Rust and designed for speed and correctness, it integrates as a custom merge driver for Git or Jujutsu (jj), intercepting conflict scenarios and applying LLM-based resolution strategies. Teams working on large codebases with frequent branch merges use Weave to reduce manual conflict resolution time and improve merge accuracy across languages parsed by tree-sitter.
Prerequisites
- Rust toolchain (cargo) installed for building from source, or Homebrew on macOS
- Git 2.x configured in your repository
- Optionally: Jujutsu (jj) version control for alternative VCS integration
- An MCP-compatible client if using the MCP interface
- LLM API access (configured via Weave's settings) for AI-assisted conflict resolution
Install Weave
Install via Homebrew on macOS, or build both the CLI and merge driver from source using Cargo.
# macOS
brew install weave
# From source (requires Rust)
git clone https://github.com/Ataraxy-Labs/weave
cd weave
cargo install --path crates/weave-cli
cargo install --path crates/weave-driverSet up Weave as your Git merge driver
Run the setup command to register weave-driver as the merge tool in your Git configuration. Use --local to modify only the current repository.
# Global setup
weave setup
# Repository-local setup (preserves .gitattributes)
weave setup --localConfigure for Jujutsu (optional)
If using Jujutsu instead of Git, add the Weave merge tool configuration to your jj user config.
[merge-tools.weave]
program = "weave-driver"
merge-args = ["$base", "$left", "$right", "-o", "$output", "-l", "$marker_length", "-p", "$path"]
merge-conflict-exit-codes = [1]
merge-tool-edits-conflict-markers = true
conflict-marker-style = "git"Preview a merge before committing
Use the CLI to preview how Weave would resolve conflicts between branches before actually merging, allowing you to review AI decisions.
weave-cli preview feature-branchConfigure MCP integration
Add Weave to your MCP client configuration to use it as an MCP tool provider for merge operations.
{
"mcpServers": {
"weave": {
"command": "npx",
"args": ["weave"]
}
}
}Revert to standard Git if needed
If you want to stop using Weave as your merge driver, run the unsetup command to restore standard Git merge behavior.
weave unsetupWeave Examples
Client configuration
MCP client configuration for using Weave as a code merge assistant.
{
"mcpServers": {
"weave": {
"command": "npx",
"args": ["weave"]
}
}
}Prompts to try
Use Weave via your AI assistant for merge-related analysis and conflict resolution.
- "Preview the merge of my feature-branch into main and show me any potential conflicts"
- "Set up Weave as the Git merge driver for this repository"
- "Resolve the conflict in src/api/handler.ts using the right-side changes as the base"
- "Show me which files would conflict if I merge the auth-refactor branch now"Troubleshooting Weave
weave-driver is not invoked during git merge
Run `weave setup` again and verify that .gitattributes contains merge=weave entries for the relevant file patterns, and that your .gitconfig or .git/config has a [merge "weave"] section pointing to weave-driver.
Build fails with missing Rust dependencies
Ensure your Rust toolchain is up to date with `rustup update stable`. The Weave crates require a recent stable Rust release. If tree-sitter grammars fail to compile, check that a C compiler (gcc or clang) is available on your PATH.
Merge preview shows unexpected output
Use `weave-cli preview <branch>` with a specific file path to narrow down the conflict. Check that the tree-sitter grammar for your language is included in Weave's supported parsers. For unsupported file types, Weave falls back to standard three-way merge.
Frequently Asked Questions about Weave
What is Weave?
Weave is a Model Context Protocol (MCP) server that highly efficient, secure, and stable application development platform with excellent performance, easy scalability, and deep integration of ai capabilities such as llm, ai chat, rag, and agents.高效、安全、稳定的服务研发平台，具备良好性能，同时易扩展，深度集成llm、aichat、rag、agent等 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Weave?
Follow the installation instructions on the Weave GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Weave?
Weave works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Weave free to use?
Yes, Weave is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Weave Alternatives — Similar Coding Agents Servers
Looking for alternatives to Weave? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Weave in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Weave?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.