Skip to main content

Tools

Build multi-agent systems in pure Python.

Prevention Pre-generation Fully autonomous Hybrid Stable Activity band D PromptEnvironment
Activity band details

Activity band A to F: a bin of a score that adds GitHub stars (log scale), a push to the upstream repository in the 12 months before `as_of`, the number of declared integration surfaces and, where the catalogue records them, citing papers and benchmark evaluations. It measures popularity and activity. It is not a level of evidence: no band means a paper cites the tool or that it was measured. Recency is judged as of 2026-11-22.

Computed band: D (raw score 4.35). Shown band: D .

Facets: documented_in=0evaluated_on=0integration_surfaces=0.5paper_citations=0recent_push=2stars=1.85

Source of truth: pipeline/maturity/score.py

Description

Agno (formerly Phidata) is a Python multi-agent framework with pluggable memory and knowledge modules. Canonical Pythonic alternative to CrewAI/AutoGen for agent orchestration, with a focus on speed of iteration.

Why it's included

Python multi-agent framework cell. Complements autogen by a pure-Python + module-plugin design.

Addresses failure modes

These tags are the catalog's claim about what agno is built to catch or prevent. A tag is not a test result. SAICA-Bench has not measured agno, so none of these tags is tested here.

  • Scope creep — Actions outside declared task boundary.

Records evidence of

agno can record evidence of these failures (traces, or checks you configure yourself), but it does not detect or prevent them on its own. They are not counted as failure modes it addresses.

Techniques

multi-agentmemory-modulesknowledge-modules

View raw YAML on GitHub →