ToolAI.io · Chaîne GitHub

Nouveaux projets AI sur GitHub

Découvrez les nouveaux projets AI open source ajoutés sur GitHub, avec les informations du dépôt, les instructions de configuration, les licences et les ressources associées.

Données du dépôt public

Index du projet

76 Projets
Agents et multi-agents

Microsoft Agent Framework

microsoft/agent-framework

An open-source framework for building, orchestrating, and evaluating AI agents across Python and .NET.

★ 14K⑂ 2,4KPython
MITQ84
Agents et multi-agents

smolagents

huggingface/smolagents

A lightweight Python library for building agents that use tools and execute code to solve tasks.

★ 29,8K⑂ 3,1KPython
Apache-2.0Q84
Agents et multi-agents

CrewAI

CrewAIInc/crewAI

A Python framework for coordinating role-based AI agents and structured task workflows.

★ 59,5K⑂ 8,7KPython
MITQ84
LLM et modèles de fondation

Outlines

dottxt-ai/outlines

A library for generating structured, constrained outputs from language models.

★ 15,9K⑂ 901Python
Apache-2.0Q84
Ingénierie des prompts

DSPy

stanfordnlp/dspy

A framework for programming and optimizing language-model pipelines instead of hand-tuning prompts.

★ 38,6K⑂ 3,4KPython
MITQ84
Réglage fin, entraînement et données

TRL

huggingface/trl

A library for post-training transformer models with supervised fine-tuning and preference-optimization methods.

★ 19,5K⑂ 3,1KPython
Apache-2.0Q84
Programmation AI et outils pour développeurs

TypeSafe Python SDK

typesafe-ai/typesafe-sdk-python

Connect Python services to the TypeSafe API using typed questions and results. The repository provides the client library rather than model weights.

★ 218⑂ 30Python
MITQ92
Robotique et Edge AI

NVIDIA Warp: Python kernels for CPU and GPU simulation

NVIDIA/warp

Compiles typed Python functions into compute kernels with geometry, physics and differentiable programming capabilities for simulation and machine learning.

★ 7,1K⑂ 621Python
Apache-2.0Q92
Robotique et Edge AI

MuJoCo: A Physics Simulation Engine for Robotics and Control Experiments

google-deepmind/mujoco

A multijoint contact dynamics engine maintained by Google DeepMind, providing model description, physics stepping, an interactive viewer, and a Python interface. It is suitable for developing robotics, control, and reinforcement learning environments.

★ 15,1K⑂ 1,7KC++
Apache-2.0Q92
Réglage fin, entraînement et données

Hydra: Managing Training Configurations, Parameter Combinations, and Experiment Runs

hydra-ecosystem/hydra

A configuration framework for Python applications that manages experiments through configuration composition, command-line overrides, and multirun execution. It is suitable for organizing data, model, and training parameters into reusable configuration structures.

★ 10,6K⑂ 977Python
MITQ92

Page 1 / 7 · 76 projets

Récemment mis à jour

ComfyUIComfy-Org/ComfyUI★ 136,7K CrewAICrewAIInc/crewAI★ 59,5K Microsoft Agent Frameworkmicrosoft/agent-framework★ 14K TRLhuggingface/trl★ 19,5K mcp-usemcp-use/mcp-use★ 10,7K OpenLITopenlit/openlit★ 2,8K

Les plus étoilés

ECCaffaan-m/ECC★ 248,8K Hermes Agentnousresearch/hermes-agent★ 227,1K tensorflowtensorflow/tensorflow★ 198,8K AutoGPTSignificant-Gravitas/AutoGPT★ 187,1K ollamaollama/ollama★ 180,2K markitdown — Document conversion and extractionmicrosoft/markitdown★ 174,9K