Build and run AI agents using Docker Compose. A collection of ready-to-use examples for orchestrating open-source LLMs, tools, and agent runtimes.
- agentic-workflows
- ai-agents
- docker
- docker-compose
132,218 visible repositories in the index
2,041–2,064 of 3,447 · Most stars
Build and run AI agents using Docker Compose. A collection of ready-to-use examples for orchestrating open-source LLMs, tools, and agent runtimes.
PyTorch code for CVPR 2018 paper: Learning to Compare: Relation Network for Few-Shot Learning (Few-Shot Learning part)
The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.
Learning Lightweight Lane Detection CNNs by Self Attention Distillation (ICCV 2019)
Ladon 911 for Cobalt Strike & Cracked Download,Large Network Penetration Scanner, vulnerability / exploit / detection / MS17010 / password/brute-force/psexec/atexec/sshexec/webshell/smbexec/netcat/osscan/netscan/struts2Poc/weblogicExp
[TPAMI 2023] LibFewShot: A Comprehensive Library for Few-shot Learning.
This repository contains a PyTorch implementation of "AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis".
Dynamiq is an orchestration framework for agentic AI and LLM applications
Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)
Simple Android PDF viewer based on pdf.js and content providers. The app doesn't require any permissions. The PDF stream is fed into the sandboxed WebView without giving it access to content or files. CSP is used to enforce that the JavaScript and styling properties within the WebView are entirely static.
🐝 The First Self-Improving agents with RL / Prompting Optimization
Official PyTorch implementation of Superpoint Transformer [ICCV'23], SuperCluster [3DV'24 Oral], and EZ-SP [ICRA'26]
Deep learning toolkit-enabled VLSI placement
Composable, view-based context for DeepSeek Harness. Pluggable sources and strategies, with layered memory and self-evolving skills out of the box.
GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning
Visit PixelLib's official documentation https://pixellib.readthedocs.io/en/latest/
Real-time pose estimation accelerated with NVIDIA TensorRT
RFC6265 Cookies and CookieJar for Node.js
The most exhaustive list of reliable DNS resolvers.
An All-MLP solution for Vision, from Google AI
PyGame Learning Environment (PLE) -- Reinforcement Learning Environment in Python.
Essential Guide to keep up with AI/ML/DL/CV
Official Implementation of Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agents
Mastering Atari with Discrete World Models