lambdagent/docs/quickstart.md

Quick Start

Quick Start with Claude Code Max Plan (No API Key)

The fastest way to run an agent -- uses your Claude Code Max Plan subscription directly, no API key needed.

1. YAML config (agent-config.yml)

agentId: my-agent
name: my-agent
type: react

model:
  provider: claude-code
  name: sonnet
  temperature: 0.3
  maxTokens: 4096

systemPrompt: |
  You are a helpful assistant.

2. Run via PaaS CLI

# Create and chat
python3 -m agentpaas agent create --name my-agent --config agent-config.yml
python3 -m agentpaas chat my-agent

3. Run directly

python3 agentexample/agent67/run.py --claude

The --claude flag forces the Claude Code backend (claude -p --resume), bypassing any API-key provider in the config. Session persistence via --resume means the LLM retains full conversation history, eliminating hallucination from lost context.

--strict-mcp-config is passed automatically to isolate MCP tools -- the agent only sees tools declared in your YAML, not host-level MCP servers (Vercel, Gmail, etc.).

---

Simple Agent

from lambdagent import Lam

agent = Lam("summarizer", "Summarize the input concisely.")
result = agent("A very long article about quantum computing...")

Pipeline (Compose)

extract = Lam("extract", "Extract key facts.")
analyze = Lam("analyze", "Analyze the facts.")
report = Lam("report", "Write a report.")

pipeline = extract >> analyze >> report
result = pipeline("Raw data...")

ReAct Agent (Y Combinator)

from lambdagent import Lam, Loop, Tool

search = Tool("search", lambda q: web_search(q))

agent = Loop(
    body=Lam("think", "Reason about the question. Use tools if needed."),
    condition=lambda r, s: "DONE" in str(r) or s >= 9,
    max_steps=10,
)

From YAML (API-Key Providers)

For providers that require an API key (Anthropic, OpenAI, DashScope, etc.):

model:
  provider: anthropic          # or openai, dashscope, deepseek, moonshot, ollama
  name: claude-sonnet-4-20250514
  temperature: 0.3

from lambdagent import from_config

agent = from_config("agent-config.yml")
result = agent("Your question here")

Set the corresponding environment variable (ANTHROPIC_API_KEY, OPENAI_API_KEY, DASHSCOPE_API_KEY, etc.) before running.

Engine Selection

lambdagent supports dual execution engines. Add runtime.engine to your YAML to switch:

runtime:
  engine: cek    # recursive (default) | cek | adaptive

The cek engine provides step-level cost monitoring, pause/resume, and loop detection for complex agents.

One-Sentence Builder

python nl2agent.py "Build a research assistant with search tools" -t "Research AI agents"