Amp TypeScript SDK

Use the Amp SDK to programmatically deploy the Amp agent anywhere you run TypeScript. Execute Amp CLI commands programmatically with full type safety, streaming responses, and complete control over your AI coding agent workflows.

Why use the Amp SDK?

The Amp TypeScript SDK brings the Amp agent directly into your applications with simple, reliable functionality:

- Stream Inputs: Send prompts and messages incrementally to the Amp agent
- Stream Outputs: Receive structured JSON responses (system, assistant, result) as the agent executes tasks
- Multi-turn Conversations: Maintain back-and-forth interactions across multiple executions
- Thread Continuity: Continue an existing thread (latest or by ID) to build stateful agent workflows
- Programmatic Settings: Configure working directories, settings, and tools without user prompts — ideal for automation
- MCP Integration: Extend Amp with custom Model Context Protocol servers and tools
- Custom Skills: Define and use custom agent skills to extend Amp's functionality

What can you build?

The Amp SDK enables a wide range of AI-powered applications:

$3

- Code Review Agent: Automated pull request analysis and feedback
- Documentation Generator: Create and maintain project documentation
- Test Automation: Generate and execute test suites
- Migration Assistant: Help upgrade codebases and refactor legacy code

$3

- CI/CD Integration: Smart build and deployment pipelines
- Issue Triage: Automatically categorize and prioritize bug reports
- Code Quality Monitoring: Continuous analysis of code health metrics
- Release Management: Automated changelog generation and version bumping

Quick Start

$3

``bash


Install the Amp SDK using npm

npm install @sourcegraph/amp-sdk

or yarn

yarn add @sourcegraph/amp-sdk
`

Once installed, add your API key to the environment. You can access your API key at ampcode.com/settings.

`bash
export AMP_API_KEY=sgamp_your_api_key_here
`

$3

Now that you have the SDK installed and your API key set up, you can start using Amp with the execute() function:

`typescript
import { execute } from '@sourcegraph/amp-sdk'

// Simple execution - get the final result
for await (const message of execute({ prompt: 'What files are in this directory?' })) {
if (message.type === 'result' && !message.is_error) {
console.log('Result:', message.result)
break
}
}
`

The execute() function only requires that you provide a prompt to get started. The SDK streams messages as the agent works, letting you handle responses and integrate them directly into your application.

Core Concepts

$3

The SDK streams different types of messages as your agent executes:

`typescript
for await (const message of execute({ prompt: 'Run tests' })) {
if (message.type === 'system') {
// Session info, available tools, MCP servers
console.log('Available tools:', message.tools)
} else if (message.type === 'assistant') {
// AI responses and tool usage
console.log('Assistant is working...')
} else if (message.type === 'result') {
// Final result (success or error)
console.log('Done:', message.result)
}
}
`

$3

When you just need the final result without handling streaming:

`typescript
async function getResult(prompt: string): Promise {
for await (const message of execute({ prompt, options: { dangerouslyAllowAll: true } })) {
if (message.type === 'result') {
if (message.is_error) {
throw new Error(message.error)
}
return message.result
}
}
throw new Error('No result received')
}

// Usage
try {
const result = await getResult('List all TypeScript files in this project')
console.log('Found files:', result)
} catch (error) {
console.error('Failed:', error.message)
}
`

$3

Continue conversations across multiple interactions:

`typescript
// Continue the most recent conversation
for await (const message of execute({
prompt: 'What was the last error you found?',
options: { continue: true },
})) {
if (message.type === 'result') {
console.log(message.result)
}
}

// Continue a specific thread by ID
for await (const message of execute({
prompt: 'Can you update that code we discussed?',
options: { continue: 'T-abc123-def456' },
})) {
if (message.type === 'result') {
console.log(message.result)
}
}
`

Common Configuration

$3

For automation scenarios, bypass permission prompts:

`typescript
const options = {
dangerouslyAllowAll: true, // Skip permission prompts
}

for await (const message of execute({
prompt: 'Make changes without asking for permission',
options,
})) {
// Handle messages...
}
`

$3

Specify where Amp should run:

`typescript
for await (const message of execute({
prompt: 'Refactor the auth module',
options: { cwd: './my-project' },
})) {
// Process messages...
}
`

$3

See what's happening under the hood:

`typescript
for await (const message of execute({
prompt: 'Analyze this project',
options: {
logLevel: 'debug', // Shows CLI command in console
logFile: './amp-debug.log', // Optional: write logs to file
},
})) {
// Process messages
}
`

$3

Select which agent mode to use. The mode controls the model, system prompt, and tool selection:

`typescript
for await (const message of execute({
prompt: 'Quickly fix this typo',
options: {
mode: 'rush', // Use rush mode for faster responses
},
})) {
// Process messages
}
`

Available modes:

- smart (default): Balanced mode with full capabilities
- rush: Faster responses with streamlined tool usage
- large: 1M-token long-context workhorse
- deep: Extended reasoning for complex tasks

$3

Add labels to threads created by execute().

`typescript
for await (const message of execute({
prompt: 'Summarize this repo',
options: {
labels: ['sdk', 'summary'],
},
})) {
if (message.type === 'result') {
console.log(message.result)
break
}
}
`

$3

Control who can see threads created by execute():

`typescript
for await (const message of execute({
prompt: 'Analyze this private codebase',
options: {
visibility: 'private', // Only you can see this thread
},
})) {
if (message.type === 'result') {
console.log(message.result)
break
}
}
`

Available visibility levels:

- workspace (default): Visible to all workspace members
- private: Only visible to you
- public: Visible to anyone with the link
- group: Visible to members of your user group (Enterprise)

$3

Control which tools Amp can use with fine-grained permissions:

`typescript
import { execute, createPermission } from '@sourcegraph/amp-sdk'

for await (const message of execute({
prompt: 'List files and run tests',
options: {
permissions: [
// Allow listing files
createPermission('Bash', 'allow', { matches: { cmd: 'ls *' } }),
// Allow running tests
createPermission('Bash', 'allow', { matches: { cmd: 'npm test' } }),
// Ask before reading sensitive files
createPermission('Read', 'ask', { matches: { path: '/etc/*' } }),
],
},
})) {
// Process messages
}
`

Permission rules support:

- Pattern matching: Use * wildcards and regex patterns
- Context control: Restrict rules to main thread or sub-agents
- Delegation: Delegate permission decisions to external programs

Learn more about permissions in the manual and the appendix.

Advanced Usage

$3

For building user interfaces that show real-time progress:

`typescript
async function executeWithProgress(prompt: string) {
console.log('Starting task...')

for await (const message of execute({ prompt })) {
if (message.type === 'system' && message.subtype === 'init') {
console.log('Tools available:', message.tools.join(', '))
} else if (message.type === 'assistant') {
// Show tool usage or assistant responses
const content = message.message.content[0]
if (content.type === 'tool_use') {
console.log(Using ${content.name}...)
} else if (content.type === 'text') {
console.log('Assistant:', content.text.slice(0, 100) + '...')
}
} else if (message.type === 'result') {
if (message.is_error) {
console.log('Failed:', message.error)
} else {
console.log('Completed successfully!')
console.log(message.result)
}
}
}
}
`

$3

Handle long-running operations gracefully:

`typescript
async function executeWithTimeout(prompt: string, timeoutMs = 30000) {
const signal = AbortSignal.timeout(timeoutMs)

try {
for await (const message of execute({
prompt,
signal,
options: { dangerouslyAllowAll: true },
})) {
if (message.type === 'result') {
return message.result
}
}
} catch (error) {
if (error.message.includes('aborted')) {
throw new Error(Operation timed out after ${timeoutMs}ms)
}
throw error
}
}
`

$3

Extend Amp's capabilities with custom tools and data sources:

`typescript
import { execute, type MCPConfig } from '@sourcegraph/amp-sdk'

const mcpConfig: MCPConfig = {
playwright: {
command: 'npx',
args: ['-y', '@playwright/mcp@latest', '--headless'],
env: { NODE_ENV: 'production' },
},
database: {
command: 'node',
args: ['./custom-mcp-server.js'],
env: { DB_CONNECTION_STRING: process.env.DATABASE_URL },
},
}

for await (const message of execute({
prompt: 'Test the login flow on staging environment',
options: { mcpConfig, dangerouslyAllowAll: true },
})) {
if (message.type === 'system') {
console.log(
'MCP Servers:',
message.mcp_servers.map((s) => ${s.name}: ${s.status}),
)
}
// Handle other messages...
}
`

To find out more about extending Amp with MCP servers, visit the MCP Configuration section of the manual.

$3

Build streaming conversations using async generators:

`typescript
import { execute, createUserMessage } from '@sourcegraph/amp-sdk'

async function* generateMessages() {
yield createUserMessage('Start analyzing the codebase')

// Wait for some condition or user input
await new Promise((resolve) => setTimeout(resolve, 1000))

yield createUserMessage('Now focus on the authentication module')
}

for await (const message of execute({
prompt: generateMessages(),
})) {
if (message.type === 'result') {
console.log(message.result)
}
}
`

$3

Configure Amp's behavior with a settings file, like the settings.json. You can provide Amp with a custom settings file you have saved in your project:

`typescript
import { execute } from '@sourcegraph/amp-sdk'

// Use a custom settings file
for await (const message of execute({
prompt: 'Deploy the application',
options: {
settingsFile: './settings.json',
logLevel: 'debug',
},
})) {
// Handle messages...
}
`

Example settings.json:

`json
{
"amp.mcpServers": {
"playwright": {
"command": "npx",
"args": ["-y", "@playwright/mcp@latest", "--headless", "--isolated"]
}
},
"amp.commands.allowlist": ["npx", "node", "npm"],
"amp.tools.disable": ["mermaid", "mcp__playwright__browser_resize"]
}
`

To find all available settings, see the Configuration Settings.

$3

Extend Amp's capabilities with custom toolbox scripts:

`typescript
for await (const message of execute({
prompt: 'Use my custom deployment scripts',
options: {
toolbox: '/usr/repository-path/toolbox', // Path to toolbox scripts
},
})) {
// Handle messages...
}
`

To find out more about Amp Toolboxes, see the Toolboxes section of the Amp documentation.

$3

Load custom skills from a specified directory:

`typescript
for await (const message of execute({
prompt: 'Use my custom deployment skill',
options: {
skills: './my-skills', // Path to custom skills directory
},
})) {
// Process messages
}
`

To learn more about creating custom skills, see the Agent Skills section of the Amp documentation.

Functions

$3

The main function for executing Amp CLI commands programmatically.

`typescript
function execute(options: ExecuteOptions): AsyncIterable
`

#### Parameters

- options (ExecuteOptions) - Configuration for the execution

#### Returns

- AsyncIterable - Stream of messages from the Amp CLI

#### Example

`typescript
import { execute } from '@sourcegraph/amp-sdk'

for await (const message of execute({
prompt: 'Analyze this codebase',
options: {
cwd: './my-project',
dangerouslyAllowAll: true,
},
})) {
if (message.type === 'assistant') {
console.log('Assistant:', message.message.content)
} else if (message.type === 'result') {
console.log('Final result:', message.result)
break
}
}
`

$3

Helper function to create properly formatted user input messages for streaming conversations.

`typescript
function createUserMessage(text: string): UserInputMessage
`

#### Parameters

- text (string) - The text content for the user message

#### Returns

- UserInputMessage - A formatted user input message

#### Example

`typescript
import { createUserMessage } from '@sourcegraph/amp-sdk'

const message = createUserMessage('Analyze this code')
console.log(message)
// Output: { type: 'user', message: { role: 'user', content: [{ type: 'text', text: 'Analyze this code' }] } }
`

$3

Helper function to create permission objects for controlling tool usage.

`typescript
function createPermission(
tool: string,
action: 'allow' | 'reject' | 'ask' | 'delegate',
options?: {
matches?: Record
context?: 'thread' | 'subagent'
to?: string
},
): Permission
`

#### Parameters

- tool (string) - The name of the tool to which this permission applies (supports glob patterns)
- action ('allow' | 'reject' | 'ask' | 'delegate') - How Amp should proceed when matched
- options (object, optional) - Additional configuration for the permission
- matches (Record) - Match conditions for tool arguments
- context ('thread' | 'subagent') - Only apply this rule in specific context
- to (string) - Command to delegate to (required when action is 'delegate')

#### Returns

- Permission - A permission object that can be used in the permissions array

#### Examples

`typescript
import { createPermission } from '@sourcegraph/amp-sdk'

// Allow all Bash commands
createPermission('Bash', 'allow')

// Allow specific git commands
createPermission('Bash', 'allow', {
matches: { cmd: 'git *' },
})

// Ask before allowing Read operations on sensitive paths
createPermission('Read', 'ask', {
matches: { path: '/etc/*' },
})

// Delegate web browsing to a custom command
createPermission('mcp__playwright__*', 'delegate', {
to: 'node browse.js',
})

// Only apply in subagent context
createPermission('Bash', 'reject', {
context: 'subagent',
})
`

$3

Create a new empty thread and return its ID.

`typescript
async function threads.new(options?: ThreadsNewOptions): Promise
`

#### Parameters

- options (ThreadsNewOptions, optional) - Configuration for the new thread

#### Returns

- Promise - The thread ID

#### Example

`typescript
import { threads } from '@sourcegraph/amp-sdk'

// Create a new private thread
const threadId = await threads.new({ visibility: 'private' })
console.log('Created thread:', threadId)
`

$3

Get a thread rendered as markdown.

`typescript
async function threads.markdown(options: ThreadsMarkdownOptions): Promise
`

#### Parameters

- options (ThreadsMarkdownOptions) - Options containing the thread ID

#### Returns

- Promise - The thread content as markdown

#### Example

`typescript
import { threads } from '@sourcegraph/amp-sdk'

// Get thread content as markdown
const markdown = await threads.markdown({ threadId: 'T-abc123-def456' })
console.log(markdown)
`

Types

$3

Configuration options for the execute() function.

`typescript
interface ExecuteOptions {
prompt: string | AsyncIterable
options?: AmpOptions
signal?: AbortSignal
}
`

#### Properties

| Property | Type | Required | Description |
| --------- | ------------------------------------------- | -------- | -------------------------------------------------------------------------------------------- |
| prompt | string \| AsyncIterable | Yes | The input prompt as a string or async iterable of user messages for multi-turn conversations |
| options | AmpOptions | No | CLI configuration options |
| signal | AbortSignal | No | Signal for cancellation support |

$3

Configuration options that map to Amp CLI flags.

`typescript
interface AmpOptions {
cwd?: string
mode?: 'smart' | 'rush' | 'large'
dangerouslyAllowAll?: boolean
visibility?: 'public' | 'private' | 'workspace' | 'group'
settingsFile?: string
logLevel?: 'debug' | 'info' | 'warn' | 'error' | 'audit'
logFile?: string
mcpConfig?: string | MCPConfig
env?: Record
continue?: boolean | string
toolbox?: string
skills?: string
permissions?: Permission[]
labels?: string[]
}
`

#### Properties

| Property | Type | Default | Description |
| --------------------- | --------------------------------------------------- | --------------- | ------------------------------------------------------------------------ |
| cwd | string | process.cwd() | Current working directory for execution |
| mode | 'smart' \| 'rush' \| 'large' | 'smart' | Agent mode - controls model, system prompt, and tool selection |
| dangerouslyAllowAll | boolean | false | Allow all tool usage without permission prompts |
| visibility | 'public' \| 'private' \| 'workspace' \| 'group' | 'workspace' | Thread visibility level |
| settingsFile | string | - | Path to custom settings file |
| logLevel | 'debug' \| 'info' \| 'warn' \| 'error' \| 'audit' | 'info' | Logging verbosity level |
| logFile | string | - | Path to write logs |
| continue | boolean \| string | false | Continue most recent thread (true) or specific thread by ID (string) |
| mcpConfig | string \| MCPConfig | - | MCP server configuration as JSON string, or config object |
| env | Record | - | Additional environment variables |
| toolbox | string | - | Folder path with toolbox scripts |
| skills | string | - | Folder path with custom skills |
| permissions | [Permission[]](#permission) | - | Permission rules for tool usage |
| labels | string[] | - | Labels to add to the thread |

Message Types

The SDK streams various message types during execution. All messages implement the base StreamMessage type.

$3

Initial message containing session information and available tools.

`typescript
interface SystemMessage {
type: 'system'
subtype: 'init'
session_id: string
cwd: string
tools: string[]
mcp_servers: Array<{
name: string
status: 'connected' | 'connecting' | 'connection-failed' | 'disabled'
}>
}
`

#### Properties

| Property | Type | Description |
| ------------- | --------------------------------------- | -------------------------------------------- |
| session_id | string | Unique identifier for this execution session |
| cwd | string | Current working directory |
| tools | string[] | List of available tool names |
| mcp_servers | Array<{name: string, status: string}> | Status of MCP servers |

$3

AI assistant responses with text content and tool usage.

`typescript
interface AssistantMessage {
type: 'assistant'
session_id: string
message: {
id: string
type: 'message'
role: 'assistant'
model: string
content: Array
stop_reason: 'end_turn' | 'tool_use' | 'max_tokens' | null
stop_sequence: string | null
usage?: Usage
}
parent_tool_use_id: string | null
}
`

#### Properties

| Property | Type | Description |
| -------------------- | ---------------- | ------------------------------------------------ |
| session_id | string | Unique identifier for this execution session |
| message | object | The assistant's message content |
| parent_tool_use_id | string \| null | ID of parent tool use if this is a tool response |

$3

User input and tool results.

`typescript
interface UserMessage {
type: 'user'
session_id: string
message: {
role: 'user'
content: Array
}
parent_tool_use_id: string | null
}
`

#### Properties

| Property | Type | Description |
| -------------------- | ---------------- | ------------------------------------------------ |
| session_id | string | Unique identifier for this execution session |
| message | object | The user's message content |
| parent_tool_use_id | string \| null | ID of parent tool use if this is a tool response |

$3

Final successful execution result.

`typescript
interface ResultMessage {
type: 'result'
subtype: 'success'
session_id: string
is_error: false
result: string
duration_ms: number
num_turns: number
usage?: Usage
permission_denials?: string[]
}
`

#### Properties

| Property | Type | Description |
| -------------------- | ----------------- | -------------------------------------------- |
| session_id | string | Unique identifier for this execution session |
| result | string | The final result from the assistant |
| duration_ms | number | Total execution time in milliseconds |
| num_turns | number | Number of conversation turns |
| usage | Usage | Token usage information |
| permission_denials | string[] | List of permissions that were denied |

$3

Final error result indicating execution failure.

`typescript
interface ErrorResultMessage {
type: 'result'
subtype: 'error_during_execution' | 'error_max_turns'
session_id: string
is_error: true
error: string
duration_ms: number
num_turns: number
usage?: Usage
permission_denials?: string[]
}
`

#### Properties

| Property | Type | Description |
| -------------------- | ----------------- | -------------------------------------------- |
| session_id | string | Unique identifier for this execution session |
| error | string | Error message describing what went wrong |
| duration_ms | number | Total execution time in milliseconds |
| num_turns | number | Number of conversation turns |
| usage | Usage | Token usage information |
| permission_denials | string[] | List of permissions that were denied |

$3

Plain text content block.

`typescript
interface TextContent {
type: 'text'
text: string
}
`

$3

Tool execution request.

`typescript
interface ToolUseContent {
type: 'tool_use'
id: string
name: string
input: Record
}
`

$3

Result from tool execution.

`typescript
interface ToolResultContent {
type: 'tool_result'
tool_use_id: string
content: string
is_error: boolean
}
`

$3

Token usage and billing information from API calls.

`typescript
interface Usage {
input_tokens: number
cache_creation_input_tokens?: number
cache_read_input_tokens?: number
output_tokens: number
service_tier?: string
}
`

#### Properties

| Property | Type | Description |
| ----------------------------- | -------- | ---------------------------------- |
| input_tokens | number | Number of input tokens used |
| cache_creation_input_tokens | number | Tokens used for cache creation |
| cache_read_input_tokens | number | Tokens read from cache |
| output_tokens | number | Number of output tokens generated |
| service_tier | string | Service tier used for this request |

Input Types

$3

Formatted user input message for streaming conversations.

`typescript
interface UserInputMessage {
type: 'user'
message: {
role: 'user'
content: Array<{
type: 'text'
text: string
}>
}
}
`

$3

Configuration for MCP (Model Context Protocol) servers. Supports both stdio-based and HTTP-based servers.

`typescript
type MCPConfig = Record

// MCPServer is a union of stdio and HTTP server configurations
`

MCPServer accepts either a stdio server config (with command) or an HTTP server config (with url):

`typescript
const mcpConfig: MCPConfig = {
playwright: { command: 'npx', args: ['-y', '@playwright/mcp'] },
remote: { url: 'https://api.example.com/mcp' },
}
`

#### MCPServer Properties

Stdio server:

| Property | Type | Required | Description |
| ---------- | ------------------------ | -------- | ------------------------------------ |
| command | string | Yes | Command to start the MCP server |
| args | string[] | No | Command line arguments |
| env | Record | No | Environment variables for the server |
| disabled | boolean | No | Whether this server is disabled |

HTTP server:

| Property | Type | Required | Description |
| ----------- | ------------------------ | -------- | -------------------------------------- |
| url | string | Yes | URL of the HTTP MCP server |
| headers | Record | No | HTTP headers to send with requests |
| transport | string | No | Transport type (e.g., "sse") |
| oauth | object | No | OAuth configuration for authentication |
| disabled | boolean | No | Whether this server is disabled |

OAuth config (for HTTP servers):

| Property | Type | Required | Description |
| -------------- | ---------- | -------- | ----------------------- |
| clientId | string | Yes | OAuth client ID |
| clientSecret | string | No | OAuth client secret |
| authUrl | string | Yes | OAuth authorization URL |
| tokenUrl | string | Yes | OAuth token URL |
| scopes | string[] | No | OAuth scopes |
| redirectUrl | string | No | OAuth redirect URL |

$3

Options for creating a new thread.

`typescript
interface ThreadsNewOptions {
visibility?: 'private' | 'public' | 'workspace' | 'group'
}
`

#### Properties

| Property | Type | Required | Description |
| ------------ | ------------------------------------------------- | -------- | ----------------- |
| visibility | 'private' \| 'public' \| 'workspace' \| 'group' | No | Thread visibility |

$3

Options for getting thread markdown.

`typescript
interface ThreadsMarkdownOptions {
threadId: string
}
`

#### Properties

| Property | Type | Required | Description |
| ---------- | -------- | -------- | --------------------------------- |
| threadId | string | Yes | The thread ID to get markdown for |

$3

Individual permission rule for controlling tool usage.

`typescript
interface Permission {
tool: string
matches?: Record
action: 'allow' | 'reject' | 'ask' | 'delegate'
context?: 'thread' | 'subagent'
to?: string
}
`

#### Properties

| Property | Type | Required | Description |
| --------- | -------------------------------------------- | -------- | ----------------------------------------------------------- |
| tool | string | Yes | Tool name (supports glob patterns like Bash or mcp__*) |
| matches | Record | No | Match conditions for tool arguments |
| action | 'allow' \| 'reject' \| 'ask' \| 'delegate' | Yes | How Amp should proceed when the rule matches |
| context | 'thread' \| 'subagent' | No | Apply rule only in main thread or sub-agents |
| to | string | No | Command to delegate to (required when action is delegate) |

#### Example

`typescript
import { execute, createPermission } from '@sourcegraph/amp-sdk'

for await (const message of execute({
prompt: 'Deploy the application',
options: {
permissions: [
// Allow git commands
createPermission('Bash', 'allow', { matches: { cmd: 'git *' } }),
// Allow reading files
createPermission('Read', 'allow'),
],
},
})) {
// Handle messages
}
`

$3

Match condition for tool arguments. Supports strings (with glob patterns or regex), arrays (OR logic), booleans, numbers, null, undefined, and nested objects.

`typescript
type PermissionMatchCondition =
| string
| PermissionMatchCondition[]
| { [key: string]: PermissionMatchCondition }
| boolean
| number
| null
| undefined
`

#### Examples

`typescript
// String pattern with wildcard
{
cmd: 'npm *'
}

// Array for OR logic
{
cmd: ['npm install', 'npm test', 'npm run build']
}

// Regex pattern
{
cmd: '/^git (status|log|diff)$/'
}

// Nested object matching
{
env: {
NODE_ENV: 'production'
}
}
``

Requirements

- Node.js 18 or higher