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
Harness LLMs with Multi-Agent Programming
Generate clean 2D game sprites & animation atlases — component-row pipeline: state rows, alpha cleanup, frame extraction, runtime atlases. Codex/Claude skill.
[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank.
Open-source framework for the research and development of foundation models.
An open-source framework for training large multimodal models.
Pyramid - A Python web framework
Bird frame for Raspberry Pi or your homelab - real-time bird detection by audio, fully local AI, rendered as real, hand-cut 1800s bird illustrations. On an e-ink panel, a TV, or any screen.
- bird-detection
- birding
- birdnet
- birdnet-go
Code and hyperparameters for the paper "Generative Adversarial Networks"
A ~9M parameter LLM that talks like a small fish.
Free Python Games
Snoop — инструмент разведки на основе открытых данных (OSINT world)
- osint
- termux
- username-search
- username-checker
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.
Task-Aware Agent-driven Prompt Optimization Framework
Deformable DETR: Deformable Transformers for End-to-End Object Detection.
Reverse engineering framework in Python
A minimal Python framework for building custom AI inference servers with full control over logic, batching, and scaling.
A股多Agent投研框架 — 适配A股数据源(龙虎榜/游资/解禁等),7位分析师基于A股规则的辩论决策,基于TradingAgents深度改造,适配大A。A-share multi-agent investment research framework — 7 AI analysts, bull/bear debate, risk assessment。
Mastering Diverse Domains through World Models
Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support
Visual profiler for Python
Snips Python library to extract meaning from text
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
Mesa is an open-source Python library for agent-based modeling, ideal for simulating complex systems and exploring emergent behaviors.
- mesa
- agent-based-modeling
- agent-based-simulation
- simulation-framework