### Install Core Library

Source: https://github.com/codifyiq/context-driven-llm-scheduler/blob/dev/README.md

Installs the main context-driven-llm-scheduler package. This is the basic installation required to use the library.

```bash
pip install context-driven-llm-scheduler

```

--------------------------------

### Install and Run Commands

Source: https://github.com/codifyiq/context-driven-llm-scheduler/blob/dev/CLAUDE.md

Commands for synchronizing dependencies, running linters, executing behavior-driven tests, and building the project.

```bash
uv sync --extra sqlite --extra scheduler --extra dev
```

```bash
uv run ruff check .
```

```bash
uv run behave --tags="not @integration-test"
```

```bash
uv build
```

--------------------------------

### Install Optional Extras

Source: https://github.com/codifyiq/context-driven-llm-scheduler/blob/dev/README.md

Installs the library with optional dependencies for enhanced functionality, such as LiteLLM, SQLite support, and scheduler integrations. Choose these based on your project's needs.

```bash
pip install "context-driven-llm-scheduler[litellm,sqlite,scheduler]"

```

--------------------------------

### Python Pulse Manager Setup

Source: https://github.com/codifyiq/context-driven-llm-scheduler/blob/dev/README.md

Initializes the PulseManager with a file store for state and a LiteLLMAdapter for LLM interaction. This is the entry point for managing pulses in your Python application.

```python
from context_driven_llm_scheduler import PulseManager, FileStore, LiteLLMAdapter

manager = PulseManager.from_dir("pulses", FileStore("./state"))
adapter = LiteLLMAdapter("anthropic/claude-sonnet-4-6")

```

--------------------------------

### Pulse Definition Example

Source: https://github.com/codifyiq/context-driven-llm-scheduler/blob/dev/README.md

Defines a scheduled task (pulse) with its schedule, memory rules, LLM model, and instructions in a markdown file. Use this for configuring recurring LLM agents.

```markdown
---
id: inbox-triage
schedule: "*/15 * * * *"
throttle: { notify: 1h }
keep: { notes: 20, seen: 500 }
model: anthropic/claude-sonnet-4-6
---

You are my inbox triage assistant.

For each new urgent email:
- Decide if it genuinely needs my attention.
- If yes and the `notify` throttle allows, alert me and record the throttle.
- Always mark the email as `seen`.

Be conservative. Never notify about the same thing twice.

```

--------------------------------

### Pulse Definition and Execution in Python

Source: https://github.com/codifyiq/context-driven-llm-scheduler/blob/dev/README.md

Defines a Python function to handle a specific pulse, recalling context, proposing memory operations via an LLM adapter, and persisting the results. Use this to integrate your pulse logic with the manager.

```python
@manager.pulse("inbox-triage")
def triage(pulse, extra=None):
    prompt = pulse.recall(extra={"emails": fetch_urgent_emails()})
    ops = adapter.propose_memory_ops(prompt)
    return pulse.persist(ops)

```

--------------------------------

### Triggering a Pulse in Python

Source: https://github.com/codifyiq/context-driven-llm-scheduler/blob/dev/README.md

Manually triggers a specific pulse by its ID. This function is intended to be called by an external scheduler like cron or APScheduler.

```python
manager.trigger("inbox-triage")   # Call from cron, scheduler, Lambda, etc.

```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.