Robotique et Edge AI
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
Parole, audio et voix
PaddlePaddle/PaddleSpeech
A PaddlePaddle-based speech toolkit covering speech recognition, text-to-speech, punctuation restoration, and other audio tasks, with command-line, Python interface, and service examples.
★ 12,7K⑂ 2KPython
Apache-2.0Q92
Réglage fin, entraînement et données
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
Robotique et Edge AI
NVIDIA/Isaac-GR00T
NVIDIA’s robot models and reference code offer multimodal action prediction, demonstration-data adaptation, fine-tuning and deployment tooling.
★ 8,1K⑂ 1,5KPython
Apache-2.0Q92
Robotique et Edge AI
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
Agents et multi-agents
henrydaum/second-brain
Second Brain is an agentic framework that acts as an operating system, using local file intelligence, workflow automation, and LLMs to complete tasks and communicate over multiple modalities and messaging platforms.
★ 607⑂ 75Python
MITQ92
MCP et appels d’outils
artokun/comfyui-mcp
A local-first, agent-native control plane for ComfyUI that provides an MCP server and sidebar agent to generate images, video, and audio, author and run workflows, and edit live graphs using natural language across any LLM.
★ 599⑂ 93TypeScript
MITQ92
Agents et multi-agents
reyamira/models
A TUI and CLI tool for browsing AI models, benchmarks, coding agents, and provider statuses.
★ 492⑂ 19Rust
MITQ92
Inférence, déploiement et exécution
avifenesh/memra
A from-scratch LLM inference engine built in Rust and CUDA, specifically optimized for RTX 5090 (sm_120a) and H100 (sm_90a) architectures, delivering exactness-gated performance without relying on frameworks like ggml.
★ 314⑂ 35Rust
MITQ92
Programmation AI et outils pour développeurs
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
MCP et appels d’outils
bojieli/ai-agent-book
《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码
★ 40,2K⑂ 4,4KPython
Apache-2.0Q91
Inférence, déploiement et exécution
PaddlePaddle/Paddle-Lite
PaddlePaddle High Performance Deep Learning Inference Engine for Mobile and Edge (飞桨高性能深度学习端侧推理引擎)
★ 7,3K⑂ 1,6KC++
Apache-2.0Q91