Harness LLMs with Multi-Agent Programming
Repository Index
71,372 visible repositories in the index
265–288 of 808 · Most stars
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.
- apple-silicon
- local-llm
- macos
- mlx
:smiley_cat: A tool designed to shorten steps needed to import and optimize models into VRChat. Compatible models are: MMD, XNALara, Mixamo, DAZ/Poser, Blender Rigify, Sims 2, Motion Builder, 3DS Max and potentially more
- mmd
- vrchat
- blender
- mixamo
Agent harness to make your slop code well-engineered and beautiful.
- agent-harness
A tool (and pre-commit hook) to automatically upgrade syntax for newer versions of the language.
- python
- pre-commit
- linter
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
This repository consists of all the material required for cracking the coding rounds and technical interviews during placements.
- placements
- placement
- placement-preparation
- placement-preparation-portal
A ~9M parameter LLM that talks like a small fish.
Deepchecks: Tests for Continuous Validation of ML Models & Data. Deepchecks is a holistic open-source solution for all of your AI & ML validation needs, enabling to thoroughly test your data and models from research to production.
- machine-learning
- ml
- model-validation
- data-validation
[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing
喵币助手：双十一天猫（淘宝）、京东任务一键完成。电脑版，支持Android和HarmonyOS Next
Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents.
:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
- speech-synthesis
- text-to-speech
- tensorflow2
- melgan
Simple PyTorch Tutorials Zero to ALL!
- deeplearning
- pytorch
- python
- tutorial
Windrecorder is a memory search app by records everything on your screen in small size, to let you rewind what you have seen, query through OCR text or image description, and get activity statistics, like Microsoft's Windows Recall or Rewind.
- ffmpeg
- streamlit
- productivity
- rewind
Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.
Hook and simulate global keyboard events on Windows and Linux.
- python
- keyboard-events
- keyboard-hooks
- keyboard-state
A highly specialized reverse-engineering pipeline designed to structurally transplant original Vanilla character models into the EverQuest Online Adventures: Frontiers (PS2) game engine, resolving complex Vector Unit 1 (VU1) shader bugs, Emotion Engine (EE) memory overflows, and PS2 CDVDman hardware faults.
- assets
- eqoa
- eqoa-frontiers
- game
FinRL-X: An AI-Native Modular Infrastructure for Quantitative Trading
- deep-reinforcement-learning
- stock-trading
- a2c-algorithm
- ppo
ansible-lint checks playbooks for practices and behavior that could potentially be improved and can fix some of the most common ones for you
- ansible
- ansible-lint
- pre-commit-hook
- hacktoberfest
AllenAI's post-training codebase
Create Python GUIs with Qt in minutes
- pyqt5
- pyinstaller
- python3
- pyside2
An API Client package to access the APIs for NBA.com
- nba
- stats
- nba-stats
- nba-api
A Book about Pythonic Application Architecture Patterns for Managing Complexity. Cosmos is the Opposite of Chaos you see. O'R. wouldn't actually let us call it "Cosmic Python" tho.