"hyperparameter-optimization"

📦 projects

andrewrk/poop

poop — Performance Optimizer Observation Platform

Zig★ 2k⑂ 91other

☆

deepspeedai/DeepSpeed

DeepSpeed — DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Python★ 42.7k⑂ 4.9kai-ml

☆

facebookarchive/prepack

prepack — A JavaScript bundle optimizer.

JavaScript★ 14.1k⑂ 412web

☆

hpcaitech/ColossalAI

ColossalAI — Making large AI models cheaper, faster and more accessible

Python★ 41.4k⑂ 4.5kai-ml

☆

chenfei-wu/TaskMatrix

TaskMatrix —

Python★ 34.1k⑂ 3.2kother

☆

facebook/zstd

zstd — Zstandard - Fast real-time compression algorithm

C★ 27.4k⑂ 2.5kother

☆

deepset-ai/haystack

haystack — Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

MDX★ 25.9k⑂ 2.9kai-ml

☆

vectordotdev/vector

vector — A high-performance observability data pipeline.

Rust★ 22.2k⑂ 2.2kdevops

☆

pjreddie/darknet

darknet — Convolutional Neural Networks

C★ 26.5k⑂ 21.1kai-ml

☆

heygen-com/hyperframes

hyperframes — Write HTML. Render video. Built for agents.

TypeScript★ 34k⑂ 3.2kai-ml

☆

xai-org/x-algorithm

x-algorithm — Algorithm powering the For You feed on X

Rust★ 26.4k⑂ 4.5kother

☆

hiyouga/LlamaFactory

LlamaFactory — Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Python★ 73.1k⑂ 8.9kai-ml

☆

vuejs/petite-vue

petite-vue — 6kb subset of Vue optimized for progressive enhancement

TypeScript★ 9.7k⑂ 397web

☆

krahets/hello-algo

hello-algo — 《Hello 算法》：动画图解、一键运行的数据结构与算法教程。支持简中、繁中、English、日本語，提供 Python, Java, C++, C, C#, JS, Go, Swift, Rust, Ruby, Kotlin, TS, Dart 等代码实现

Java★ 127.7k⑂ 15.2kother

☆

yifanfeng97/Hyper-Extract

Hyper-Extract — Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.

Python★ 1.9k⑂ 210ai-ml

+124 ★☆

aristocratos/btop

btop — A monitor of resources

C++★ 33.4k⑂ 1.1kother

☆

karpathy/autoresearch

autoresearch — AI agents running research on single-GPU nanochat training automatically

Python★ 90.6k⑂ 13kai-ml

☆

vwxyzjn/cleanrl

cleanrl — High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Python★ 10k⑂ 1.1kai-ml

☆

FoundationAgents/MetaGPT

MetaGPT — 🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Python★ 69.3k⑂ 8.8kai-ml

☆

microsoft/BitNet

BitNet — Official inference framework for 1-bit LLMs

Python★ 39.6k⑂ 3.6kai-ml

☆

allenai/olmocr

olmocr — Toolkit for linearizing PDFs for LLM datasets/training

Python★ 18.5k⑂ 1.5kai-ml

+334 ★☆

BVLC/caffe

caffe — Caffe: a fast open framework for deep learning.

C++★ 34.6k⑂ 18.5kai-ml

☆

recommenders-team/recommenders

recommenders — Best Practices on Recommendation Systems

Python★ 21.8k⑂ 3.3kai-ml

☆

OpenRLHF/OpenRLHF

OpenRLHF — An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

Python★ 9.7k⑂ 973ai-ml

☆

vllm-project/vllm

vllm — A high-throughput and memory-efficient inference and serving engine for LLMs

Python★ 85.8k⑂ 19.2kai-ml

☆

ultralytics/ultralytics

ultralytics — Ultralytics YOLO 🚀

Python★ 59.3k⑂ 11.3kai-ml

☆

MemTensor/MemOS

MemOS — Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

TypeScript★ 10k⑂ 913ai-ml

☆

camel-ai/owl

owl — 🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Python★ 19.9k⑂ 2.3kai-ml

☆

affaan-m/ECC

ECC — The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

JavaScript★ 227.8k⑂ 34.8kai-ml

☆

0voice/interview_internal_reference

interview_internal_reference — 2025年最新总结，阿里，腾讯，百度，美团，头条等技术面试题目，以及答案，专家出题人分析汇总。

Python★ 37.2k⑂ 9.4kbackend

☆

ashishpatel26/500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code

500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code — 500 AI Machine learning Deep learning Computer vision NLP Projects with code

★ 35.3k⑂ 7.3kai-ml

☆

fastify/fastify

fastify — Fast and low overhead web framework, for Node.js

JavaScript★ 36.7k⑂ 2.8kbackend

☆

highlight/highlight

highlight — highlight.io: The open source, full-stack monitoring platform. Error monitoring, session replay, logging, distributed tracing, and more.

TypeScript★ 9.3k⑂ 670devops

☆

binhnguyennus/awesome-scalability

awesome-scalability — The Patterns of Scalable, Reliable, and Performant Large-Scale Systems

★ 72.3k⑂ 7kai-ml

☆

hyperdxio/hyperdx

hyperdx — Resolve production issues, fast. An open source observability platform unifying session replays, logs, metrics, traces and errors powered by ClickHouse and OpenTelemetry.

TypeScript★ 9.7k⑂ 422devops

☆

algorithm-visualizer/algorithm-visualizer

algorithm-visualizer — :fireworks:Interactive Online Platform that Visualizes Algorithms from Code

JavaScript★ 48.6k⑂ 7.6kdata

☆

CMU-Perceptual-Computing-Lab/openpose

openpose — OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

C++★ 34.3k⑂ 8kai-ml

☆

hellzerg/optimizer

optimizer — The finest Windows Optimizer

C#★ 18.3k⑂ 1.2kother

☆

ray-project/ray

ray — Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Python★ 43.2k⑂ 7.8kai-ml

☆