> ## Documentation Index
> Fetch the complete documentation index at: https://docs.praison.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Context Files
> Inject markdown context files into your agent's instructions automatically
Context files allow you to automatically inject markdown content into your agent's instructions using AGENTS.md-style files.
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
subgraph "Context Injection Flow"
A[📄 Context Files] --> B[📝 Load Content]
B --> C[🔗 Merge Instructions]
C --> D[🤖 Enhanced Agent]
end
classDef file fill:#6366F1,stroke:#7C90A0,color:#fff
classDef process fill:#F59E0B,stroke:#7C90A0,color:#fff
classDef output fill:#10B981,stroke:#7C90A0,color:#fff
class A file
class B,C process
class D output
```
## Quick Start
Create markdown files with context information:
```markdown theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# AGENTS.md
## Company Guidelines
- Always be professional and helpful
- Focus on customer satisfaction
- Use clear, concise language
## Product Information
Our main products include:
- AI Assistant Platform
- Workflow Automation Tools
- Data Analytics Dashboard
```
Use `context_paths` to inject the content:
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent
from praisonai.integration import configure_host
agent = Agent(
name="Customer Support",
instructions="Help customers with their questions"
)
configure_host(
agents=[agent],
context_paths=["AGENTS.md", "STYLE.md"],
style="dashboard"
)
```
***
## How It Works
Context files are merged into agent instructions during host configuration:
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
sequenceDiagram
participant User
participant Host as configure_host()
participant Loader as Context Loader
participant Agent as Agent Instance
User->>Host: context_paths=["AGENTS.md"]
Host->>Loader: load_context_files()
Loader->>Loader: Read markdown files
Loader-->>Host: Combined context text
Host->>Agent: Prepend to instructions
Note over Agent: {instructions}\n\nContext:\n{context}
```
The content is merged using this pattern:
```
{original_instructions}
Context:
{context_file_content}
```
***
## Configuration Options
### Default File Discovery
If no `context_paths` specified, these files are automatically checked:
| Path | Description |
| ------------------- | -------------------------- |
| `AGENTS.md` | Primary agent context file |
| `agents.md` | Alternative naming |
| `.agents/AGENTS.md` | Hidden directory structure |
### Custom Context Paths
Specify your own context files:
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
configure_host(
context_paths=[
"docs/guidelines.md",
"config/style-guide.md",
"knowledge/product-info.md"
]
)
```
### Context Loading Behavior
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Silent fallback when module unavailable
try:
from praisonai.integration.context_files import load_context_files
context = load_context_files(paths)
except ImportError:
# No-op when context_files not available
context = ""
```
***
## File Structure Examples
### Basic AGENTS.md
```markdown theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Agent Context
## Role Definition
You are a customer support specialist with deep knowledge of our products.
## Communication Style
- Be friendly and professional
- Use active voice
- Keep responses under 150 words unless detailed explanation needed
## Knowledge Areas
- Product features and pricing
- Technical troubleshooting
- Account management procedures
```
### Multi-File Setup
```
project/
├── AGENTS.md # Primary context
├── STYLE.md # Communication guidelines
├── docs/
│ └── products.md # Product information
└── .agents/
└── internal.md # Internal guidelines
```
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
configure_host(
context_paths=[
"AGENTS.md",
"STYLE.md",
"docs/products.md",
".agents/internal.md"
]
)
```
***
## Common Patterns
### Environment-Specific Context
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
import os
context_files = ["AGENTS.md"]
# Add environment-specific context
env = os.getenv("ENVIRONMENT", "development")
if env == "production":
context_files.append("production-guidelines.md")
else:
context_files.append("dev-guidelines.md")
configure_host(context_paths=context_files)
```
### Conditional Context Loading
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
def get_context_files(agent_type):
base_files = ["AGENTS.md"]
if agent_type == "support":
base_files.append("support-protocols.md")
elif agent_type == "sales":
base_files.append("sales-playbook.md")
return base_files
configure_host(
context_paths=get_context_files("support")
)
```
### Hierarchical Context
```markdown theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# base-context.md
## Universal Guidelines
All agents should follow these principles...
# specialized-context.md
## Support-Specific Guidelines
When handling support tickets...
# team-context.md
## Team Information
Our support team includes...
```
***
## Best Practices
Structure your context files for maintainability:
```
context/
├── base/
│ ├── guidelines.md # Universal principles
│ └── style.md # Communication style
├── roles/
│ ├── support.md # Role-specific context
│ └── sales.md # Role-specific context
└── knowledge/
├── products.md # Product information
└── policies.md # Company policies
```
Keep context files focused and well-organized:
```markdown theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Context File Template
## Core Role
Brief description of the agent's primary function
## Guidelines
- Key behavioral guidelines
- Communication principles
- Quality standards
## Knowledge Areas
Relevant domain knowledge the agent should reference
## Examples
Sample interactions or responses when helpful
```
Version control your context files:
```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Track context changes
git add AGENTS.md STYLE.md
git commit -m "Update agent communication guidelines"
# Review context impact
git diff HEAD~1 context/
```
Validate context injection in development:
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Test context loading
from praisonai.integration.context_files import load_context_files
context = load_context_files(["AGENTS.md", "STYLE.md"])
print("Loaded context length:", len(context))
print("Preview:", context[:200])
```
***
## Related
Configure context injection
Deployment patterns