Agents IA
kuberna-labs
Build, deploy, and monetize autonomous agents across Web3.
★ 51 étoilesMIT
Voir le guide →// agents · NVIDIA-NeMo/labs-OO-Agents
labs-OO-Agents
labs-OO-Agents est un projet de agents IA open source, créé par NVIDIA-NeMo (NVIDIA-NeMo/labs-OO-Agents sur GitHub). Il compte 2 270 étoiles sur GitHub et 306 forks, il est publié sous la licence NOASSERTION et a été mis à jour pour la dernière fois sur GitHub le 7 octobre 2026.
NVIDIA's object-oriented, Pythonic approach to building AI agents.
★ 2,3 k étoiles⑂ 306 forksNOASSERTIONmis à jour oct. 2026
▦ visuel — le README de ce projet ne contient aucune capture intégrable,
voici donc un emplacement réservé. Le guide ci-dessous est complet malgré tout.
voici donc un emplacement réservé. Le guide ci-dessous est complet malgré tout.
// détails du projet
Détails du projet
- Étoiles GitHub
- 2 270
- Forks
- 306
- Licence
- NOASSERTION
- Dernière mise à jour sur GitHub
- 7 octobre 2026
- Catégorie
- Agents IA
- Type de fiche
- Guide d'installation complet
// fonctionnement
Comment ça marche
- Pick a use case
Start with one concrete task rather than a grand architecture.
- Fetch the source
Clone the repo and check the examples folder for a quickstart.
- Configure it
Install packages, set environment variables, and point it at your model.
- Run and iterate
Execute the demo workflow, then adapt it to your own data.
// fonctionnalités
Pourquoi on l'adore
Object-oriented
Agents as classes with state and behavior.
Pythonic
Idiomatic Python design.
NVIDIA labs
Experimental work from the NeMo team.
Composable
Build complex agents from objects.
Active experiments
Pushed in October 2026.
Learning resource
Study NVIDIA's agent design idioms.
Advertisement
// lancez-le
Lancez-le vous-même
- Step 1 - Clone the repo
Download the source and move into the project folder.
git clone https://github.com/NVIDIA-NeMo/labs-OO-Agents.git cd labs-OO-Agents - Step 2 - Install dependencies
Create a virtual environment and install the requirements.
python -m venv .venv && source .venv/bin/activate pip install -r requirements.txt - Step 3 - Run an example
Treat these as starting points - the README documents the exact commands.
python examples/quickstart.py
// cas d'usage
Ce que vous pouvez créer
- Prototype agents in clean OO Python.
- Teach agent concepts through classes.
- Experiment with NVIDIA's agent patterns.
- Compare OO vs functional agent designs.
Advertisement
// faq
Questions fréquentes
Who maintains this project?
NVIDIA-NeMo/labs-OO-Agents is its home on GitHub, with 306 forks so far. The contributors tab and recent commits show how actively it is maintained.
Is labs-OO-Agents free to use?
GitHub does not assert a license for this repo, so treat the code as all rights reserved until the author adds one.
Do I need a paid API to use it?
The framework itself is free - but you will need a model to drive it, which usually means your own API key or a local model.
How does it compare to other Python frameworks?
Most frameworks are functional or graph-based; this one is explicitly object-oriented. If OO design clicks for you, it may be the most natural fit - otherwise pick by ecosystem.
How do I get started?
Follow the README quickstart, then browse the examples directory for patterns that match what you want to build.
// continuez l'exploration
Outils similaires
Agents IA
NemoClaw
NVIDIA's reference stack for running AI agents more securely inside OpenShell sandboxes
★ 22,7 k étoilesApache-2.0
Voir le guide →Agents IA
agenta
A team workspace for building AI agents together.
★ 4,8 k étoilesNOASSERTION
Voir le guide →Agents IA
OmAgent
Python library for building multimodal language agents — VLM, video and mobile, fast to prototype and ship
★ 2,7 k étoilesApache-2.0
Voir le guide →Agents IA
invariant
Guardrails for building secure, robust agents.
★ 467 étoilesApache-2.0
Voir le guide →Agents IA
coze-studio
A visual all-in-one platform for building, debugging, and deploying AI agents.
★ 21,7 k étoilesApache-2.0
Voir le guide →// alternatives
Alternatives en Agents IA
Les autres projets de la catégorie Agents IA avec le plus d'étoiles du catalogue LibreAI — la sélection réaliste d'alternatives si labs-OO-Agents ne vous convient pas.
- openclaw★ 391,6 k
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294,9 k
An agentic skills framework & software development methodology that works.
- ECC★ 275,2 k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252,0 k
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245,5 k
DeepSeek's plugin-based agent harness where everything is a plugin.
// plus en agents
Plus en Agents IA
Projets de la catégorie Agents IA proches dans le catalogue, les plus proches en étoiles de labs-OO-Agents — continuez à explorer de part et d'autre.
- magic-context★ 2,3 k
Self-managing, unbounded context and long-term memory for coding agents: one session, for life.
- dash★ 2,3 k
Agno's self-learning data agent: grounded text-to-SQL answers over your database that improve with use.
- memanto★ 2,3 k
A memory agent for your agent fleet: it curates, reconciles, and expires shared memories across tools.
- Unla★ 2,2 k
Unla MCP Gateway: turn existing APIs and MCP servers into MCP endpoints with zero code changes.
- agent-vault★ 2,3 k
Infisical's credential vault and HTTP proxy, so AI agents call APIs without ever holding your real secrets.
- open-kritt★ 2,2 k
Self-hosted AI vulnerability research: agents find, validate, deduplicate, and rank real security issues.
Obtenir labs-OO-Agents
Gratuit et ouvert : récupérez le code source, mettez une étoile au dépôt et commencez à créer.