AGNO:

Agno is a lightweight library for building Agents with memory, knowledge, tools and reasoning.

Here are some key features:

• Model Agnostic: Agno Agents can connect to 23+ model providers, no lock-in.
• Lightning Fast: Agents instantiate in ~3μs and use ~5Kib memory on average (see performance for more details).
• Reasoning is a first class citizen: Make your Agents “think” and “analyze” using Reasoning Models, ReasoningTools or our custom chain-of-thought approach.
• Natively Multi-Modal: Agno Agents are natively multi-modal, they can take in text, image, audio and video and generate text, image, audio and video as output.
• Advanced Multi-Agent Architecture: Agno provides an industry leading multi-agent architecture (Agent Teams) with 3 different modes: route, collaborate and coordinate.
• Agentic Search built-in: Give your Agents the ability to search for information at runtime using one of 20+ vector databases. Get access to state-of-the-art Agentic RAG that uses hybrid search with re-ranking. Fully async and highly performant.
• Long-term Memory & Session Storage: Agno provides plug-n-play Storage & Memory drivers that give your Agents long-term memory and session storage.
• Structured Outputs: Agno Agents can return fully-typed responses using model provided structured outputs or json_mode.
• Pre-built FastAPI Routes: Agno provides pre-built FastAPI routes to serve your Agents, Teams and Workflows.
• Monitoring: Monitor agent sessions and performance in real-time on agno.com.

Level 1: Basic

Build a basic “Hello World” agent Develop a single agent (no tools) powered by an LLM

Sample interaction:

User: What are the principles of OOPS?
AI: (whatever answer we get from LLM)

Level 2: Conversational Memory

Solve and learn conversation state through agents

Sample interaction:

User: My name is Sakhi, and I am an engineering student interested in compiler design and ML. What are some good career options?
AI: (some answer from LLM)
User: What are some relevant textbooks that align with my interests?
AI: (based on prior info.... )

Level 3: Tools

Integrate web search (e.g., Google Search) with agentic flow (like Perplexity)

Sample interaction:

User: What is the latest on US tariffs?
AI: (performs the search and returns the results relevant to the search - but not as a list of search results but relevant answer to the question)

Level 4: Vector Store

Create a vector store (e.g., Compiler Design book) and push content into it Vectorize a resume and extract structured info Design sequential or parallel agent workflows Enable agent-to-tool calling Enable OCR (traditional or GenAI) to read scans as well

Sample interaction:

User: What is my AIR? What is my CGPA?
AI: (based on the resume - the ans should be provided)

Level 5: Notebook LM mimic

Implement a multi-agent, multi-tool system (PDFs, YouTube urls, Web Page urls, copy & paste text) Create a Google NotebookLM like feature to generate a mind map from large data dumps within this program create a NotebookLM style audio podcast

🎥 Demo

Check out a demo video of the project here.