Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions .github/workflows/release.yml
Original file line number Diff line number Diff line change
Expand Up @@ -73,11 +73,11 @@ jobs:
tag_name: v${{ steps.version.outputs.version }}
name: Release v${{ steps.version.outputs.version }}
body: |
Release v${{ steps.version.outputs.version }} of sentience-ts
Release v${{ steps.version.outputs.version }} of sentienceapi

## Installation
```bash
npm install sentience-ts@${{ steps.version.outputs.version }}
npm install sentienceapi@${{ steps.version.outputs.version }}
```
draft: false
prerelease: false
Expand Down
30 changes: 18 additions & 12 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,13 +5,19 @@ The SDK is open under ELv2; the core semantic geometry and reliability logic run
## Installation

```bash
npm install
npm run build
# Install from npm
npm install sentienceapi

# Install Playwright browsers (required)
npx playwright install chromium
```

**For local development:**
```bash
npm install
npm run build
```

## Quick Start: Choose Your Abstraction Level

Sentience SDK offers **4 levels of abstraction** - choose based on your needs:
Expand All @@ -21,7 +27,7 @@ Sentience SDK offers **4 levels of abstraction** - choose based on your needs:
Complete automation with natural conversation. Just describe what you want, and the agent plans and executes everything:

```typescript
import { SentienceBrowser, ConversationalAgent, OpenAIProvider } from 'sentience-ts';
import { SentienceBrowser, ConversationalAgent, OpenAIProvider } from 'sentienceapi';

const browser = await SentienceBrowser.create({ apiKey: process.env.SENTIENCE_API_KEY });
const llm = new OpenAIProvider(process.env.OPENAI_API_KEY!, 'gpt-4o');
Expand Down Expand Up @@ -52,7 +58,7 @@ await browser.close();
Zero coding knowledge needed. Just write what you want in plain English:

```typescript
import { SentienceBrowser, SentienceAgent, OpenAIProvider } from 'sentience-ts';
import { SentienceBrowser, SentienceAgent, OpenAIProvider } from 'sentienceapi';

const browser = await SentienceBrowser.create({ apiKey: process.env.SENTIENCE_API_KEY });
const llm = new OpenAIProvider(process.env.OPENAI_API_KEY!, 'gpt-4o-mini');
Expand Down Expand Up @@ -80,7 +86,7 @@ await browser.close();
Full control with semantic selectors. For technical users who want precision:

```typescript
import { SentienceBrowser, snapshot, find, click, typeText, press } from 'sentience-ts';
import { SentienceBrowser, snapshot, find, click, typeText, press } from 'sentienceapi';

const browser = await SentienceBrowser.create({ apiKey: process.env.SENTIENCE_API_KEY });
await browser.getPage().goto('https://www.amazon.com');
Expand Down Expand Up @@ -136,7 +142,7 @@ import {
OpenAIProvider,
Tracer,
JsonlTraceSink
} from 'sentience-ts';
} from 'sentienceapi';
import { randomUUID } from 'crypto';

const browser = await SentienceBrowser.create({ apiKey: process.env.SENTIENCE_API_KEY });
Expand Down Expand Up @@ -222,7 +228,7 @@ console.log(`Total tokens: ${totalTokens}`);
You can also use the tracer directly for custom workflows:

```typescript
import { Tracer, JsonlTraceSink } from 'sentience-ts';
import { Tracer, JsonlTraceSink } from 'sentienceapi';
import { randomUUID } from 'crypto';

const runId = randomUUID();
Expand Down Expand Up @@ -258,7 +264,7 @@ Traces are **100% compatible** with Python SDK traces - use the same tools to an
### Google Search (6 lines of code)

```typescript
import { SentienceBrowser, SentienceAgent, OpenAIProvider } from 'sentience-ts';
import { SentienceBrowser, SentienceAgent, OpenAIProvider } from 'sentienceapi';

const browser = await SentienceBrowser.create({ apiKey: apiKey });
const llm = new OpenAIProvider(openaiKey, 'gpt-4o-mini');
Expand All @@ -278,7 +284,7 @@ await browser.close();
### Using Anthropic Claude Instead of GPT

```typescript
import { SentienceAgent, AnthropicProvider } from 'sentience-ts';
import { SentienceAgent, AnthropicProvider } from 'sentienceapi';

// Swap OpenAI for Anthropic - same API!
const llm = new AnthropicProvider(
Expand Down Expand Up @@ -315,7 +321,7 @@ await agent.act("Click the 'Add to Cart' button");

```bash
# Install core SDK
npm install sentience-ts
npm install sentienceapi

# Install LLM provider (choose one or both)
npm install openai # For GPT-4, GPT-4o, GPT-4o-mini
Expand Down Expand Up @@ -747,7 +753,7 @@ const browser = new SentienceBrowser();
await browser.start();

// With agent
import { SentienceAgent, OpenAIProvider } from 'sentience-ts';
import { SentienceAgent, OpenAIProvider } from 'sentienceapi';

const browser = new SentienceBrowser(
'your-api-key',
Expand Down Expand Up @@ -784,7 +790,7 @@ Inject pre-recorded authentication sessions (cookies + localStorage) to start yo

```typescript
// Workflow 1: Inject pre-recorded session from file
import { SentienceBrowser, saveStorageState } from 'sentience-ts';
import { SentienceBrowser, saveStorageState } from 'sentienceapi';

// Save session after manual login
const browser = new SentienceBrowser();
Expand Down
8 changes: 4 additions & 4 deletions package-lock.json

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion package.json
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
{
"name": "sentience-ts",
"name": "sentienceapi",
"version": "0.90.0",
"description": "TypeScript SDK for Sentience AI Agent Browser Automation",
"main": "dist/index.js",
Expand Down