← ClaudeAtlas

agnolisted

Build production AI agents with Agno (formerly Phidata) — define Agent with model/tools/instructions/memory/knowledge, compose Agent Teams with coordinator routing, add Storage for persistence, and integrate RAG via built-in KnowledgeBase with PDF/URL/text sources.
phamlongh230-lgtm/yamtam-engine · ★ 3 · AI & Automation · score 65
Install: claude install-skill phamlongh230-lgtm/yamtam-engine
# Agno — Production AI Agent Framework **Source:** agno-agi/agno (Mozilla PL) — formerly Phidata; full-stack agent framework ## Why Agno - **One unified API** for agents, teams, memory, knowledge, storage, tools - **Agent Teams**: coordinator routes tasks to specialized sub-agents - **Built-in RAG**: KnowledgeBase with PDF, URL, text, database sources - **Persistent storage**: PostgreSQL, SQLite, MongoDB for long-term memory - **Playground UI**: `agent.serve()` launches a ready-made web UI ## Install ```bash pip install agno pip install agno[anthropic] # Anthropic Claude pip install agno[openai] # OpenAI pip install agno[all] # everything ``` ## Minimal Agent ```python from agno.agent import Agent from agno.models.anthropic import Claude agent = Agent( model=Claude(id="claude-sonnet-4-5"), instructions="You are a helpful assistant.", markdown=True, ) agent.print_response("What is quantum computing?") # Or get structured response response = agent.run("Explain RAG in 3 bullets") print(response.content) ``` ## Agent with Tools ```python from agno.agent import Agent from agno.models.anthropic import Claude from agno.tools.duckduckgo import DuckDuckGoTools from agno.tools.yfinance import YFinanceTools from agno.tools.python import PythonTools agent = Agent( model=Claude(id="claude-sonnet-4-5"), tools=[ DuckDuckGoTools(), YFinanceTools(stock_price=True, analyst_recommendations=True), PythonTools(), ], i