abfddfe7b9
* feat: update documentation and add new tutorials for memory blocks and agent collaboration - Updated navigation paths in docs.yml to reflect new tutorial locations. - Added comprehensive guides on shared memory blocks and attaching/detaching memory blocks. - Enhanced existing documentation for memory blocks with examples and best practices. - Corrected API key references in prebuilt tools documentation. These changes aim to improve user understanding and facilitate multi-agent collaboration through shared memory systems. * Add comprehensive documentation for built-in tools - Restructure Tool Use section with Base Tools and Utilities - Add Base Tools page documenting memory management and communication tools - Add Web Search documentation with Exa integration details - Add Code Interpreter documentation covering supported languages and limitations - Add Fetch Webpage documentation with fallback extraction methods - Update Utilities overview page to link to detailed tool docs
95 lines
2.4 KiB
Plaintext
95 lines
2.4 KiB
Plaintext
---
|
|
title: Utilities
|
|
subtitle: Pre-built tools for web access, code execution, and data fetching
|
|
slug: guides/agents/prebuilt-tools
|
|
---
|
|
|
|
Letta provides pre-built tools that enable agents to search the web, execute code, and fetch webpage content.
|
|
|
|
## Available Utilities
|
|
|
|
### [Web Search](/guides/agents/web-search)
|
|
|
|
Search the internet in real-time using [Exa](https://exa.ai)'s AI-powered search engine.
|
|
|
|
```python
|
|
agent = client.agents.create(
|
|
tools=["web_search"],
|
|
memory_blocks=[{
|
|
"label": "persona",
|
|
"value": "I use web_search for current events and external research."
|
|
}]
|
|
)
|
|
```
|
|
|
|
**Key features:**
|
|
- AI-powered semantic search
|
|
- Category filtering (news, research papers, PDFs, etc.)
|
|
- Domain filtering
|
|
- Date range filtering
|
|
- Highlights and AI-generated summaries
|
|
|
|
**Setup:** Works out of the box on Letta Cloud. Self-hosted requires `EXA_API_KEY`.
|
|
|
|
[Read full documentation →](/guides/agents/web-search)
|
|
|
|
---
|
|
|
|
### [Code Interpreter](/guides/agents/run-code)
|
|
|
|
Execute code in a secure sandbox with full network access.
|
|
|
|
```python
|
|
agent = client.agents.create(
|
|
tools=["run_code"],
|
|
memory_blocks=[{
|
|
"label": "persona",
|
|
"value": "I use Python for data analysis and API calls."
|
|
}]
|
|
)
|
|
```
|
|
|
|
**Key features:**
|
|
- Python with 191+ pre-installed packages (numpy, pandas, scipy, etc.)
|
|
- JavaScript, TypeScript, R, and Java support
|
|
- Full network access for API calls
|
|
- Fresh environment per execution (no state persistence)
|
|
|
|
**Setup:** Works out of the box on Letta Cloud. Self-hosted requires `E2B_API_KEY`.
|
|
|
|
[Read full documentation →](/guides/agents/run-code)
|
|
|
|
---
|
|
|
|
### [Fetch Webpage](/guides/agents/fetch-webpage)
|
|
|
|
Fetch and convert webpages to readable text/markdown.
|
|
|
|
```python
|
|
agent = client.agents.create(
|
|
tools=["fetch_webpage"],
|
|
memory_blocks=[{
|
|
"label": "persona",
|
|
"value": "I fetch and read webpages to answer questions."
|
|
}]
|
|
)
|
|
```
|
|
|
|
**Key features:**
|
|
- Converts HTML to clean markdown
|
|
- Extracts article content
|
|
- Multiple fallback extraction methods
|
|
- Optional Exa integration for enhanced extraction
|
|
|
|
**Setup:** Works out of the box everywhere. Optional `EXA_API_KEY` for enhanced extraction.
|
|
|
|
[Read full documentation →](/guides/agents/fetch-webpage)
|
|
|
|
---
|
|
|
|
## Related Documentation
|
|
|
|
- [Custom Tools](/guides/agents/custom-tools)
|
|
- [Tool Variables](/guides/agents/tool-variables)
|
|
- [Model Context Protocol](/guides/mcp/overview)
|