Inférence, déploiement et exécution
tiktoken — Fast tokenization
openai/tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models
★ 19K⑂ 1,6KRust
ToolAI.io · Chaîne GitHub
Répertoire de projets AI sur GitHub
Parcourez le répertoire complet de projets AI open source de ToolAI sur GitHub, organisé par sujet, langage et licence.
Données du dépôt public
Index du projet
AI multimodale
Janus — Unified multimodal understanding and generation
deepseek-ai/Janus
Janus-Series: Unified Multimodal Understanding and Generation Models
★ 17,8K⑂ 2,2KPython
Réglage fin, entraînement et données
Megatron-LM
NVIDIA/Megatron-LM
Ongoing research training transformer models at scale
★ 17,2K⑂ 4,3KPython
Agents et multi-agents
Qwen-Agent — Tool-using and RAG agents
QwenLM/Qwen-Agent
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc
★ 17K⑂ 1,7KPython
Agents et multi-agents
SkillOpt — Skill optimization for agents
microsoft/SkillOpt
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts
★ 16,2K⑂ 1,5KPython
Programmation AI et outils pour développeurs
openai-node
openai/openai-node
Official JavaScript / TypeScript library for the OpenAI API
★ 11,1K⑂ 1,5KTypeScript
Programmation AI et outils pour développeurs
kimi-cli
MoonshotAI/kimi-cli
Kimi Code CLI is your next CLI agent.
★ 10,8K⑂ 1,3KPython
Agents et multi-agents
kimi-code
MoonshotAI/kimi-code
Kimi Code CLI — The Starting Point for Next-Gen Agents
★ 5,1K⑂ 742TypeScript
Inférence, déploiement et exécution
Model-Optimizer
NVIDIA/Model-Optimizer
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
★ 3,3K⑂ 513Python
AI multimodale
HY-World-2.0
Tencent-Hunyuan/HY-World-2.0
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
★ 2,4K⑂ 209Python
Programmation AI et outils pour développeurs
PaddleScience
PaddlePaddle/PaddleScience
PaddleScience is SDK and library for developing AI-driven scientific computing applications based on PaddlePaddle.
★ 448⑂ 236Python
Agents et multi-agents
OpenGeni
cloudgeni-ai/opengeni
An open, self-hostable agentic runtime for organizations that provides durable, replayable agent sessions, human approvals, governed credentials and memory, and flexible compute targets including managed sandboxes and enrolled user hardware.
★ 56⑂ 5TypeScript
Page 17 / 22 · 253 projets