====== Agno ======
**Agno** (formerly Phidata) is a high-performance runtime for building, deploying, and managing [[agentic_software|agentic software]] at scale. With approximately **39K GitHub stars**, Agno claims **5,000x faster agent instantiation** and **50x less memory** than [[langgraph|LangGraph]], positioning itself as the performance leader among agent frameworks.(("Agno GitHub Repository." [[https://github.com/agno-agi/agno|github.com/agno-agi/agno]]))(([[https://agno.com|Official Website]]))(([[https://github.com/agno-agi/agent-ui|Agent UI]]))

{{tag>framework python agents multi-agent performance runtime}}

===== Overview =====
Agno was rebranded from Phidata in January 2025, shifting from a data engineering tool to a dedicated [[agentic_ai|agentic AI]] runtime. The framework treats multi-[[agent_orchestration|agent orchestration]], streaming, and production deployment as native platform concerns rather than bolted-on features. Its core pitch is performance: agent creation in approximately 2 microseconds using just 3.75 KiB of memory per agent, enabling thousands of concurrent sessions on modest hardware. Agno provides AgentOS as an operating system abstraction for agents, with built-in support for teams, workflows, and multi-[[modal|modal]] capabilities.

===== Key Features =====
  * **AgentOS** — Operating system abstraction for centralized knowledge management and agent lifecycle
  * **[[agent_teams|Agent Teams]]** — Multi-agent collaboration with async streaming via AsyncIterator returns
  * **Workflows** — Parallel execution with queue-based real-time event streaming
  * **Multi-[[modal|Modal]] Support** — Native support for Gemini 2.5+, [[claude|Claude]], and reasoning models with thinking capabilities
  * **Performance** — ~2us agent instantiation (5,000x faster than [[langgraph|LangGraph]]), ~3.75 KiB per agent (50x less memory)
  * **Concurrent Memory** — Automatic memory initialization on dedicated threads for improved startup
  * **Toolkit Ecosystem** — Gmail, [[google|Google]] Calendar, Jira, SurrealDb, OCR ([[deepseek|DeepSeek]]-OCR), and more
  * **Culture (Experimental)** — Shared cognitive spaces for emergent multi-agent learning

===== Architecture =====
Agno's architecture is organized around a layered runtime:

<mermaid>
graph TD
    A[Event Streaming: PostHook / SessionSummary / RunContent] --> B[Agent: Single]
    A --> C[Teams: Multi-Agent Collab]
    A --> D[Workflows: Parallel Execution]
    B --> E[Knowledge / Memory Layer]
    C --> E
    D --> E
    E --> F[Core Memory]
    E --> G[Archival Memory]
    E --> H[Concurrent Memory]
</mermaid>

===== Code Example =====
Building a multi-agent team with Agno:

<code python>
from agno.agent import Agent
from agno.team import Team
from agno.tools.duckduckgo import DuckDuckGoTools
from agno.tools.newspaper4k import Newspaper4kTools
from agno.models.[[openai|openai]] import OpenAIChat

# Create specialized agents
researcher = Agent(
    name="Researcher",
    model=OpenAIChat(id="gpt-4o"),
    tools=[DuckDuckGoTools()],
    instructions="Search the web for current information.",
)

writer = Agent(
    name="Writer",
    model=OpenAIChat(id="gpt-4o"),
    tools=[Newspaper4kTools()],
    instructions="Write clear, engaging content from research.",
)

# Combine into a team
team = Team(
    name="Research Team",
    agents=[researcher, writer],
    instructions="Research topics and produce well-written summaries.",
)

# Run the team
result = team.run("Latest breakthroughs in quantum computing")
print(result.content)
</code>

===== Performance: The 5,000x Claim =====
Agno's performance claims are based on agent instantiation benchmarks:(("Agno Documentation." [[https://docs.agno.com|docs.agno.com]]))

^ Metric ^ Agno ^ [[langgraph|LangGraph]] ^
| **Agent Instantiation** | ~2 microseconds | ~10 milliseconds |
| **Memory per Agent** | ~3.75 KiB | ~187 KiB |
| **Speedup Factor** | 5,000x faster | Baseline |
| **Memory Efficiency** | 50x less | Baseline |

These benchmarks focus on instantiation overhead, not end-to-end inference (which is dominated by LLM API latency). Agno achieves this through a stateless, horizontally scalable runtime with minimal abstractions. [[langgraph|LangGraph]]'s higher overhead stems from its graph-based state machine architecture with built-in persistence.

===== Recent Updates (2025-2026) =====
  * Concurrent memory creation on dedicated threads
  * arun() returns AsyncIterator for real-time team streaming
  * Graph-based workflows with queue-based parallel event streaming
  * Culture feature (experimental) for emergent multi-agent learning
  * Knowledge search API, health endpoint with instantiation time metrics
  * Bigtable toolset, OAuth flows, embedding model selection

===== See Also =====
  * [[ag2|AG2]]
  * [[amazon_agi|Amazon AGI]]
  * [[ag_ui_protocol|AG-UI Protocol]]
  * [[agentic_saas|Agentic SaaS]]
  * [[arc_agi|ARC-AGI]]

===== References =====