AI GitHub
Agno for agents, teams and workflow services
Build agents with tools and knowledge sources, then organize them into teams or workflows.
Key Takeaways
- Agno provides application components for defining agents and serving runs.
- A service can use separate components for model access, knowledge and sessions.
- Start with an agent that queries a tiny knowledge base, then try the same question in a second session.
- Persistence and knowledge stores are deployment dependencies with distinct access rules.
How it works
Agno provides application components for defining agents and serving runs. Session storage and knowledge integration are separate pieces you can configure around the model.
What you need
A service can use separate components for model access, knowledge and sessions. Choose where each component stores data before testing concurrent users.
What to try first
Start with an agent that queries a tiny knowledge base, then try the same question in a second session. Inspect retrieval and session behavior before introducing additional agents.
Add a failed retrieval call to the fixture and record the final result. Observe whether the workflow reports missing context or continues to answer without it.
Where to look for failures
Persistence and knowledge stores are deployment dependencies with distinct access rules. Verify which user can retrieve which records and what data the model provider receives.
Related Franklin pages
Compare who owns each step and which tools are available at a handoff. A shorter trace with the same validated result can be easier to operate than a larger team of agents.
- Assign model-backed roles and tasks within a coordinated workflow. CrewAI for role-based agent workflows
- Build Python agents that use tools, pass control and expose traces of a run. OpenAI Agents SDK for tools and handoffs
Browse Franklin for concrete examples of tools and services exposed through MCP. Franklin’s MCP directory
Project documentation
Try it for your workflow
Explore the project’s documentation for setup and usage, or save this page to a collection for later.
Read the project documentation ↗