Vendor-agnostic orchestration for training, inference and agentic workloads across NVIDIA, AMD, TPU, and Tenstorrent on clouds, Kubernetes, and bare metal.

A native macOS AI chat app powered by MLX. 100% local inference on Apple Silicon, no cloud required. Built with ShipSwift.

Shunt Claude Code agents to any model — selective, per-agent inference-layer routing proxy

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.

Persistent session memory for AI coding agents — local-first, with on-device inference, associative recall, and drift detection. Works with Claude Code, Cursor, and Codex.

LLM exposed as a 9P filesystem

A comprehensive toolkit for deploying production-ready Generative AI infrastructure on Amazon EKS. Includes pre-configured components for: 🚀 AI Gateway (LiteLLM) 🤖 LLM Serving (vLLM, SGLang, Ollama) 📊 Vector Databases, 🔍 Embedding Models (TEI) 📈 Observability (Langfuse, Phoenix) etc. Fast-track your GenAI deployment with Kubernetes

A workflow framework for statistical package development

Context-Engine MCP - Agentic Context Compression Suite

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm

A ready-to-fork Claude Code template for academics using LaTeX/Beamer + R. Multi-agent review, quality gates, adversarial QA, and replication protocols.

Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

Agent-native Stata CLI for AI coding agents (Codex, Claude Code, Cursor). Run .do files, inspect data, and return econometric results as JSON via PyStata.

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

J-Space Cognition Suite V3.7 - AI cognitive-enhancement Skills based on Anthropic's J-space global workspace research. | 哔哩哔哩：Tiger380 (UID 3494375382321675) — https://space.bilibili.com/3494375382321675

Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.

Auto-retry Claude Code on subscription rate limits, API overload (529/5xx) and safeguard false positives — waits for the printed reset, exponential backoff, tmux-based