Documentation Index
Fetch the complete documentation index at: https://docs.morphllm.com/llms.txt
Use this file to discover all available pages before exploring further.
One client. Build better, faster, cheaper prod-ready AI coding agents.
Install
npm install @morphllm/morphsdk
Edge environments? Use @morphllm/morphsdk/edge for Cloudflare Workers, Vercel Edge, or Deno. See Fast Apply and Model Router for examples.
Quick Start
import { MorphClient } from '@morphllm/morphsdk';
const morph = new MorphClient({ apiKey: "YOUR_API_KEY" });
// 1. Edit code (10,500 tokens/s)
await morph.fastApply.execute({
target_filepath: 'src/auth.ts',
instructions: 'Add null check',
code_edit: '// ... existing code ...\nif (!user) throw new Error("Invalid");\n// ... existing code ...'
});
// 2. Search code (~1230ms)
const results = await morph.codebaseSearch.search({
query: 'Where is JWT validation?',
repoId: 'my-project'
});
// 3. Test in browser, return a video and logs
await morph.browser.execute({
task: 'Test login flow',
url: 'https://myapp.e2b.dev',
model: 'gemini-flash-latest' // morph-computer-use-v0 in beta
});
// 4. Version control (triggers embedding)
await morph.git.push({ dir: './my-project' });
Get your API key: morphllm.com/dashboard/api-keys
Use with AI Agents
Give Morph tools to Claude, GPT, or any AI framework:
import Anthropic from '@anthropic-ai/sdk';
import { MorphClient } from '@morphllm/morphsdk';
import { createEditFileTool } from '@morphllm/morphsdk/tools/fastapply/anthropic';
import { createCodebaseSearchTool } from '@morphllm/morphsdk/tools/codebase-search/anthropic';
const morph = new MorphClient({ apiKey: "YOUR_API_KEY" });
const anthropic = new Anthropic();
const response = await anthropic.messages.create({
model: "claude-sonnet-4-5-20250929",
max_tokens: 12000,
tools: [
createCodebaseSearchTool({ repoId: 'my-project' }),
createEditFileTool()
],
messages: [{
role: "user",
content: "Find the auth code and add error handling"
}]
});
// Agent searches codebase, then edits files autonomously
Fast Apply
10,500 tokens/s merging
Semantic Search
2-stage retrieval, ~1230ms
Git Storage
Auto-embedding on push
Next Steps
Fast Apply
Learn the lazy edit format
Examples
Real agent patterns