3.8 KiB
3.8 KiB
TypeAgent Quick Start
Get started with TypeAgent in 5 minutes.
Prerequisites
- Rust toolchain (1.75+)
- Anthropic API key
Setup
1. Set API Key
export ANTHROPIC_API_KEY=your-api-key-here
```text
### 2. Build TypeAgent
```bash
cd crates/typedialog-agent/typedialog-ag
cargo build --release
```text
### 3. Add to PATH (optional)
```bash
export PATH="$PWD/target/release:$PATH"
```text
## Your First Agent
### Create an Agent File
Create `hello.agent.mdx`:
```markdown
---
@agent {
role: friendly assistant,
llm: claude-3-5-haiku-20241022
}
@input name: String
---
Say hello to {{ name }} in a creative and friendly way!
```text
### Run It
```bash
typeagent hello.agent.mdx
```text
You'll see:
```text
🤖 TypeAgent Executor
✓ Parsed agent definition
✓ Transpiled to Nickel
✓ Evaluated agent definition
Agent Configuration:
Role: friendly assistant
Model: claude-3-5-haiku-20241022
Max tokens: 4096
Temperature: 0.7
name (String): Alice█
```text
Type a name and press Enter. The agent will execute and show the response!
## Next Steps
### Try the Examples
```bash
# Simple greeting
typeagent tests/fixtures/simple.agent.mdx --yes
# Creative haiku
typeagent tests/fixtures/haiku.agent.mdx
```text
### Validate Before Running
```bash
typeagent validate hello.agent.mdx
```text
### See the Nickel Code
```bash
typeagent transpile hello.agent.mdx
```text
## Common Workflows
### Development Workflow
```bash
# 1. Write your agent
vim agent.mdx
# 2. Validate it
typeagent validate agent.mdx
# 3. Test with verbose output
typeagent agent.mdx --verbose
# 4. Run in production
typeagent agent.mdx
```text
### Quick Iteration
Use `--yes` to skip prompts during development:
```bash
# Edit agent.mdx
# Run without prompts
typeagent agent.mdx --yes
```text
## Advanced Features
### Context Injection
Import files into your agent:
```markdown
@import "./docs/**/*.md" as documentation
@shell "git log --oneline -5" as recent_commits
```text
### Output Validation
Ensure output meets requirements:
```markdown
@validate output {
must_contain: ["Security", "Performance"],
format: markdown,
min_length: 100
}
```text
### Conditional Logic
Use Tera template syntax:
```markdown
{% if has_description %}
Description: {{ description }}
{% endif %}
```text
## Troubleshooting
### "ANTHROPIC_API_KEY not set"
```bash
export ANTHROPIC_API_KEY=sk-ant-...
```text
### "Failed to parse agent MDX"
Check your frontmatter syntax:
```markdown
---
@agent {
role: assistant, # <- comma required
llm: claude-3-5-haiku-20241022
}
---
```text
### "Permission denied"
```bash
chmod +x ./target/release/typeagent
```text
## Learn More
- [CLI Documentation](typedialog-ag/README.md)
- [LLM Integration Guide](typedialog-ag-core/LLM_INTEGRATION.md)
- [Example Agents](typedialog-ag-core/tests/fixtures/)
## Support
- GitHub Issues: https://github.com/jesusperezlorenzo/typedialog/issues
- API Docs: `cargo doc --open --package typedialog-ag-core`
## Next Example: Architecture Agent
Create `architect.agent.mdx`:
```markdown
---
@agent {
role: software architect,
llm: claude-3-5-sonnet-20241022
}
@input feature_name: String
@input requirements?: String
@validate output {
must_contain: ["## Architecture", "## Components"],
format: markdown,
min_length: 200
}
---
# Architecture Design: {{ feature_name }}
You are an experienced software architect. Design a comprehensive architecture for:
**Feature**: {{ feature_name }}
{% if requirements %}
**Requirements**: {{ requirements }}
{% endif %}
Provide:
1. High-level architecture overview
2. Component breakdown
3. Data flow
4. Technology recommendations
Use clear markdown formatting with sections.
```text
Run it:
```bash
typeagent architect.agent.mdx
```text
The agent will prompt for inputs and generate a complete architecture design!