Documentation
Get from zero to a learning agent in under 5 minutes.
Install the SDK, wrap your agent, and watch it remember, reflect, and improve. Everything you need is below.
First working example
The canonical pattern.
Same shape as any LLM call. Three primitives: capture, dream, critique.
python
# pip install "wisdom-layer[ollama]"
from wisdom_layer import WisdomAgent, AgentConfig
from wisdom_layer.llm.ollama import OllamaAdapter
from wisdom_layer.storage.sqlite import SQLiteBackend
llm = OllamaAdapter(model="llama3.2")
agent = WisdomAgent(
agent_id="support-agent",
config=AgentConfig(name="Support Agent"),
llm=llm,
backend=SQLiteBackend("./agent.db"),
)
await agent.initialize()
await agent.memory.capture("conversation", {"user": msg})
report = await agent.dreams.trigger()
review = await agent.critic.evaluate(response)Full reference
The complete docs live in the public SDK repo.
GitHub renders the markdown cleanly. Two clicks from here gets you to integration guides, the API surface, telemetry behavior, and the underlying concepts.
Browse the docs on GitHub Twenty markdown files: install, integrations (LangGraph, MCP, Claude Agent SDK, OpenAI Agents SDK), API reference, telemetry, troubleshooting, and the underlying concepts.
View on PyPI Install metadata, version history, and the long-form README for the wisdom-layer package.