# Morph Documentation

## Docs

- [Create Git repository](https://docs.morphllm.com/api-reference/create-git-repository.md): Creates a new Git repository in Azure DevOps and the Morph database. Supports organization-scoped repositories. Most developers use `morphGit.init()` from the SDK instead of calling this directly.
- [Apply API](https://docs.morphllm.com/api-reference/endpoint/apply.md): Apply code edits at 10,500 tok/s with 98% accuracy via OpenAI-compatible API
- [Compact API](https://docs.morphllm.com/api-reference/endpoint/compact.md): Compress chat history and code context at 33,000 tok/s with byte-identical output
- [Code Apply API](https://docs.morphllm.com/api-reference/endpoint/direct.md): Direct code apply endpoint with structured parameters for automated workflows
- [Tab Next Action Prediction API](https://docs.morphllm.com/api-reference/endpoint/donotshare.md): Tab Next Action Prediction API endpoints
- [Embedding API](https://docs.morphllm.com/api-reference/endpoint/embedding.md): Generate code and text embeddings with morph-embedding-v4 via OpenAI-compatible API
- [Enterprise Apply](https://docs.morphllm.com/api-reference/endpoint/enterprise.md): Enterprise Apply API with custom model configurations
- [Report API](https://docs.morphllm.com/api-reference/endpoint/report.md): Report failed or problematic completions to improve Morph model quality
- [Rerank API](https://docs.morphllm.com/api-reference/endpoint/rerank.md): Reorder search results by relevance using morph-rerank-v4
- [WarpGrep API](https://docs.morphllm.com/api-reference/endpoint/warpgrep.md): Semantic code search subagent that explores repositories in ~6 seconds
- [Get Git references (git protocol)](https://docs.morphllm.com/api-reference/get-git-references-git-protocol.md): Git protocol endpoint that returns repository references (branches, tags). Called automatically by git clients during clone/fetch operations. Typically not invoked directly by developers.
- [Git fetch/clone operation](https://docs.morphllm.com/api-reference/git-fetchclone-operation.md): Git protocol endpoint for fetching repository data. Used automatically by git clone, git fetch, and morphGit.clone(). Proxies requests to Azure DevOps with authentication translation.
- [Git push operation](https://docs.morphllm.com/api-reference/git-push-operation.md): Git protocol endpoint for pushing changes to the repository. Automatically triggers the embedding pipeline on successful push. Used by git push and morphGit.push().
- [Self-Hosting](https://docs.morphllm.com/api-reference/self-hosting.md): Run Morph models in your own environment with self-hosting options
- [Authentication](https://docs.morphllm.com/auth.md): Learn how to authenticate with Morph API using Bearer tokens
- [Enterprise Solutions](https://docs.morphllm.com/enterprise.md): Deploy Morph with enterprise-grade security, compliance, and support
- [Glossary](https://docs.morphllm.com/glossary.md): Key terms and concepts used across Morph documentation
- [Agent Tools (edit_file)](https://docs.morphllm.com/guides/agent-tools.md): Build precise AI agents that edit code fast without full file rewrites using Morph's edit_file tool
- [Vercel AI SDK](https://docs.morphllm.com/guides/ai-sdk.md): Stream fast code edits with Morph using the Vercel AI SDK
- [Blaxel Sandboxes](https://docs.morphllm.com/guides/blaxel.md): Apply edits and execute AI code via tool calls inside a secure sandboxed environment on Blaxel.
- [Using Morph with browser-use](https://docs.morphllm.com/guides/browser-use.md): Use morph-computer-use-v0 with browser-use Python SDK for 10x cheaper browser automation
- [Claude Code](https://docs.morphllm.com/guides/claude-code.md): Step-by-step guide to make Claude Code better and faster using Morph.
- [Context Selection](https://docs.morphllm.com/guides/context.md): Learn how to select and optimize context for your prompts to improve model performance
- [Freestyle](https://docs.morphllm.com/guides/freestyle.md): How to integrate Morph Fast Apply with Freestyle Dev Servers for lightning-fast AI code editing.
- [GitHub PR Testing](https://docs.morphllm.com/guides/github-integration.md): Automatically test preview deployments on every PR
- [Morph Apply](https://docs.morphllm.com/guides/index.md): The fastest way to apply updates from GPT-4o, Claude, and others into your files
- [Morph MCP Server](https://docs.morphllm.com/guides/mcp.md): Add fast AI code editing to Claude Desktop, Cursor, VS Code and more with Morph Apply API
- [One Shot: Prompt to implement your edit_file tool](https://docs.morphllm.com/guides/oneshot.md): Ready-to-use edit_file tool implementation using Morph's fast apply API - just copy and paste into your Cursor workspace
- [General Prompting](https://docs.morphllm.com/guides/prompting.md): Learn how to use prompt models like Claude, GPT-4o, and Gemini optimized for agentic workflows
- [Retrieval](https://docs.morphllm.com/guides/retrieval.md): Simple, effective code retrieval strategies for any repository size
- [WarpGrep in Python](https://docs.morphllm.com/guides/warp-grep-python.md): Build a complete WarpGrep agent harness in Python
- [XML Tool Calls](https://docs.morphllm.com/guides/xml-tool-calls.md): Learn why XML tool calls outperform JSON for code editing and how to implement them with Claude and other LLMs
- [Introduction](https://docs.morphllm.com/introduction.md): Specialized models and subagents for AI coding agents
- [Agent Context (llms.txt)](https://docs.morphllm.com/llm-quickstart.md): Give your coding agent full Morph context in ~9k tokens
- [MCP Integration](https://docs.morphllm.com/mcpquickstart.md): Connect to Morph's 10,500 tok/s file editing via Model Context Protocol
- [Apply Model](https://docs.morphllm.com/models/apply.md): Code merging at 10,500 tok/s with 98% accuracy
- [morph-compactor](https://docs.morphllm.com/models/compact.md): morph-compactor model for context compression at 33,000 tokens per second
- [Embedding Model](https://docs.morphllm.com/models/embedding.md): Create semantic embeddings for code with our OpenAI-compatible API
- [Rerank Model](https://docs.morphllm.com/models/rerank.md): Reorder search results by relevance with our specialized reranking API
- [Quickstart](https://docs.morphllm.com/quickstart.md): Go from zero to a working Fast Apply call in 90 seconds
- [Browser Automation](https://docs.morphllm.com/sdk/components/automation/browser/direct.md): Agent browser testing that's 10x cheaper and 250% faster
- [GitHub SDK](https://docs.morphllm.com/sdk/components/automation/browser/github.md): Access PR context, post comments, and manage check runs through your connected GitHub account
- [GitHub Actions](https://docs.morphllm.com/sdk/components/automation/browser/github-actions.md): AI-powered browser testing for preview deployments
- [Browser Automation as Agent Tool](https://docs.morphllm.com/sdk/components/automation/browser/tool.md): Use browser automation as a tool in your AI agents
- [Mobile App Testing](https://docs.morphllm.com/sdk/components/automation/mobile/direct.md): Test iOS and Android apps with natural language on real devices
- [Mobile Automation as Agent Tool](https://docs.morphllm.com/sdk/components/automation/mobile/tool.md): Use mobile app automation as a tool in your AI agents
- [Compact](https://docs.morphllm.com/sdk/components/compact.md): Drop filler from chat history at 33,000 tok/s. No rewriting, no paraphrasing.
- [Fast Apply](https://docs.morphllm.com/sdk/components/fast-apply.md): AI file editing at 10,500 tokens/s - 1.8x faster, 40% fewer tokens
- [Glance](https://docs.morphllm.com/sdk/components/glance.md): Vision model trained to test code changes from a diff
- [Repo Storage](https://docs.morphllm.com/sdk/components/repos/git.md): AI-native git for coding agents
- [Git Operations](https://docs.morphllm.com/sdk/components/repos/git-operations.md): All standard Git operations for AI coding agents
- [Semantic Search](https://docs.morphllm.com/sdk/components/repos/semantic-search.md): Find code with natural language - ~1230ms, two-stage retrieval
- [Model Router](https://docs.morphllm.com/sdk/components/router.md): Automatic model selection trained on millions of vibecoding prompts
- [Subagents](https://docs.morphllm.com/sdk/components/subagents.md): Autonomous codebase exploration with bidirectional messaging
- [Codebase Search](https://docs.morphllm.com/sdk/components/warp-grep/codebase-search.md): Search local repositories with WarpGrep
- [Direct API Access](https://docs.morphllm.com/sdk/components/warp-grep/direct.md): Build your own agent harness around WarpGrep
- [Examples](https://docs.morphllm.com/sdk/components/warp-grep/examples.md): Production-ready WarpGrep agent patterns
- [GitHub Search](https://docs.morphllm.com/sdk/components/warp-grep/github-search.md): Search public GitHub repositories without cloning
- [WarpGrep](https://docs.morphllm.com/sdk/components/warp-grep/index.md): A code search subagent that finds relevant code in a separate context window. No embeddings, no indexing.
- [Sandbox Execution](https://docs.morphllm.com/sdk/components/warp-grep/sandbox-execution.md): Run WarpGrep in remote sandboxes and custom environments
- [Streaming](https://docs.morphllm.com/sdk/components/warp-grep/streaming.md): Stream WarpGrep search steps
- [Subagent as an Agent Tool](https://docs.morphllm.com/sdk/components/warp-grep/tool.md): Add WarpGrep as a search subagent to any coding agent
- [Examples](https://docs.morphllm.com/sdk/examples.md): Production-ready agent patterns
- [Compiler](https://docs.morphllm.com/sdk/genkit/compiler.md): Validate and compile generated code with security checks
- [GenKit](https://docs.morphllm.com/sdk/genkit/index.md): SDK for building generative UI applications where AI creates and renders React components in real-time
- [Storage](https://docs.morphllm.com/sdk/genkit/storage.md): Persist user-generated components with pluggable storage adapters
- [VibeArtifact](https://docs.morphllm.com/sdk/genkit/vibe-artifact.md): Production-ready component display with action buttons
- [VibeFrame](https://docs.morphllm.com/sdk/genkit/vibe-frame.md): Secure iframe rendering for AI-generated React components
- [TypeScript SDK](https://docs.morphllm.com/sdk/quickstart.md): Build AI agents that code, search, and test
- [API Reference](https://docs.morphllm.com/sdk/reference.md): Complete MorphClient API and types
- [Tools](https://docs.morphllm.com/sdk/tools.md): Four tools for building AI coding agents
- [Skill](https://docs.morphllm.com/skill.md)

## OpenAPI Specs

- [openapi](https://docs.morphllm.com/api-reference/openapi.json)
- [openapi-git](https://docs.morphllm.com/api-reference/openapi-git.json)


Built with [Mintlify](https://mintlify.com).