Turn long-horizon goals into verifiable results. A local-first semantic control plane and research workbench for long-running agent teams, across sessions and runtimes.
Repository Index
65,764 visible repositories in the index
49–72 of 294 · Most stars
Model parallel transformers in JAX and Haiku
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
- ai-agent
- agent-os
- llm-orchestration
- agentic-ai
Chronos: Pretrained Models for Time Series Forecasting
- forecasting
- large-language-models
- llm
- machine-learning
The Harness of Harnesses • Super Agent: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.
Emulator for rapid prototyping of Software Defined Networks
- mininet
- openflow
- sdn
- emulator
Local-first healthcare AI: clinical NER and HIPAA PII de-identification on hardware you control. 2,200+ medical models, 35 model-backed PII languages, and Python, MLX, Android and browser runtimes. Apache-2.0 SDK.
- healthcare
- llm
- on-device
- on-premise
TranslatedTop free VPN (ClashX & V2Ray proxy) with subscription links. [Free VPN, free ladder, free "scientific internet access", free subscription links, free nodes, curated selection, ClashX & V2Ray tutorials]
- clash
- clashx
- clash-for-windows
- free-node
⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA
Dockerized OpenAI-compatible wrapper for Kokoro-82M text-to-speech w/multiplatform CPU, AMD, NVIDIA GPU PyTorch; multi-speaker, clone-tuning, caption timestamps, SSML, websockets, optional readalong web UI
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
- pytorch
- vqa
- pretrained-models
- multimodal
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
- games
- reinforcement-learning
- multiagent
- cpp
⚚ The ultrawork agent with AI coworkers wired into you
Agent Skill for generating 2D sprite sheets and map, transparent PNG frames, and animated GIFs from prompts.
- agent-skills
- codex
- pixel-art
- sprite-generator
Games: Create interesting games in pure python.
Legendary - A free and open-source replacement for the Epic Games Launcher
- epicgames-launcher
- epic-games
- epic-games-client
- epic-games-launcher
Probabilistic time series modeling in Python
- time-series
- deep-learning
- forecasting
- neural-networks
Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models
- pytorch
- resnet
- inception-resnet
- face-recognition
Cairn is a general-purpose AI state-space search engine, validated first on autonomous penetration testing. Sometimes misspelled as Carin.
TranslatedHermes Agent from Beginner to Expert · Orange Book Series · A Practical Guide to Nous Research's Open-Source AI Agent Framework
Time series forecasting with PyTorch
MlFinLab helps portfolio managers and traders who want to leverage the power of machine learning by providing reproducible, interpretable, and easy to use tools.
- machine-learning
- trading
- investing
- research
Mimesis is a Python library for generating fake but realistic data in multiple languages and locales.
- mimesis
- fake
- data
- generator
A heartfelt, interactive narrative mini-game built in Python for Rose Day. Features custom entities, a dynamic dialogue system, animated particle effects, and integrated audio to deliver a unique, romantic digital experience.
- game-development
- interactive-story
- mini-game
- narrative-game