# lambdagent

**Lambda Calculus Agent DSL** — Every agent is a function. Every composition is function composition. Every loop is a Y combinator.

## What is lambdagent?

lambdagent is a Python DSL that models AI agents as Lambda calculus terms. It provides **11 composable constructs** with rigorous mathematical foundations.

**Core insight**: An LLM-Dataset Pair (M, D) is equivalent to a λ-term.

```
YAML Config ──→ from_config() ──→ Lambda Term ──→ Runtime ──→ Result
                 (compiler)        (Term tree)    (β-reduction)
```

## Install

```bash
pip install lambdagent
```

## Hello World

```python
from lambdagent import Lam

agent = Lam("greeter", "You are a friendly assistant. Say hello.")
result = agent("Hi there!")
print(result)
```

## Next Steps

- [Quick Start](quickstart.md) — build your first agent pipeline
- [Core Constructs](constructs.md) — the 11 Lambda calculus constructs
- [YAML Configuration](yaml-config.md) — declare agents in YAML
- [Multi-Agent](multi-agent.md) — group chat, handoff, channels
- [AgentPaaS](agentpaas.md) — deploy agents as a service