Agno

In this catalog it is the Frameworks option when you need to compose multi-step agent loops and tool handoffs. Keep Agno on the observe/propose side of the loop: useful signals and drafts, with human or policy authority still required before anything irreversible runs.

Agno builds production-oriented Python agents with first-class tools, memory, and knowledge hooks without forcing a giant graph runtime.

1. Define an agent with model, tools, and optional memory/knowledge.
2. Run the agent on a user goal; it plans and calls tools.
3. Memory/knowledge reads inject context; writes update stores when configured.
4. Return structured or text results to the host.

Related: pydantic-ai · mem0 · topics/12-central-nervous-system

• Use when: Agno (evolved from the Phidata line) is a Python framework for building production-oriented agents with built-in patterns for tools, memory, and knowledge matches the bottleneck and you specifically need to compose multi-step agent loops and tool handoffs.
• Skip when: another pack already covers the need with less ops surface, or Agno would become a second place people retype truth.
• Prefer instead: compare Pydantic AI, mem0 before locking the cell.

• Ops: confirm license, hosting, and release cadence for Agno (agno-agi/agno) before relying on it in a live corridor.
• Integration: bad credentials, scopes, or schema drift produce empty retrievals or runaway tool/model spend without an obvious UI alarm.
• Scope: Frameworks components support agents; they are not the company ledger or the approval authority.