agno
The programming language for agentic software.
Decision gist · record as of 2026-08-14
Yes. Agno is actively maintained, permissively licensed, has low install friction, and addresses a real need for developers building agent platforms. The framework is production-ready (Development Status 5) and offers a complete stack from agent definition through deployment and management. Start with it if you're building agents that need to run as services with multi-user control and observability.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Low install friction with a pure-Python wheel and no compiled dependencies.
- Actively maintained with a release 1 day old and 41712 repository stars.
- Supports Python 3.9 through 3.13.
License · maintenance · safety
permissive license (permissive) — Apache-2.0 permissive license allows commercial use, modification, and redistribution with minimal restrictions—suitable for proprietary applications.
last release 2026-08-13 (1 days) · last repo commit 2026-08-14 · 41,712 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 2,272,799 downloads/mo, #3,177 on PyPI
Alternatives
Verify before relying
pip install agno
from agno import Agent
agent = Agent()
response = agent.run("Your task here")- Whether the 50+ API endpoints and 100+ integrations mentioned in the description are current as of version 2.9.0
- Performance characteristics and scaling limits for concurrent agent runs
- Whether telemetry can be fully disabled and what data is actually collected per run
What it is and what it does
Agno is a framework for building agent platforms—systems where AI agents perform tasks autonomously or with human oversight. It provides an SDK to define agents, a runtime (AgentOS) to execute them as services, and a web UI to manage the platform. The package includes 10 runtime dependencies (pydantic, httpx, pyyaml, rich, and others) that handle configuration, HTTP communication, and data validation.
The framework is designed to give you control over your agent stack: you own the data, memory, and security model (JWT-based role-based access control). It supports scheduling, human approval workflows, observability via OpenTelemetry, and deployment to any container platform. Agents can be exposed via REST API, Slack, Telegram, Discord, and other interfaces. The package sends telemetry per agent run (model provider signals only, not prompts or outputs) unless disabled via environment variable.
Use it for
- Build a customer support agent that handles tickets autonomously with human approval for sensitive actions
- Deploy a multi-tenant agent platform where different teams manage their own agents via a web UI
- Create scheduled background jobs and cron tasks without external infrastructure
- Integrate agents with Slack, GitHub, and Postgres using pre-built toolkits
- Monitor agent runs with audit logs and OpenTelemetry tracing for compliance
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
Agno is actively maintained, permissively licensed, has low install friction, and addresses a real need for developers building agent platforms. The framework is production-ready (Development Status 5) and offers a complete stack from agent definition through deployment and management. Start with it if you're building agents that need to run as services with multi-user control and observability.
Install
agno on PyPI
Before you install
Low install friction with a pure-Python wheel and no compiled dependencies. Actively maintained with a release 1 day old and 41712 repository stars. Supports Python 3.9 through 3.13.
License in practice
Apache-2.0 permissive license allows commercial use, modification, and redistribution with minimal restrictions—suitable for proprietary applications.
Quickstart
pip install agno
from agno import Agent
agent = Agent()
response = agent.run("Your task here")Verify before relying
- Whether the 50+ API endpoints and 100+ integrations mentioned in the description are current as of version 2.9.0
- Performance characteristics and scaling limits for concurrent agent runs
- Whether telemetry can be fully disabled and what data is actually collected per run
Package facts
| License | permissive license permissive |
| Python support | Supports the current Python release <4,>=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 10 packagesagnoctldocstring-parserh11httpxpackagingpydantic-settingspydanticpyyamlrichtyping-extensions |
| Maintenance | Actively maintained 1 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 2,272,799 / month, #3,177 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.9Topic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: agno-2.9.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “agentic software platform”
- agnoAgno is a framework and runtime for building, deploying, and managing…
- aigieAigie is the Python SDK for Kytte, a runtime reliability platform…
- agentscopeAgentScope is a production-ready framework for building multi-agent…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also agnoctl · opentelemetry-instrumentation-agno · praisonaiagents · tower · PraisonAI · ag2 · openinference-instrumentation-agno · agentscope · nvidia-nat-core · autogen