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.

Lightweight markdown-based workflow for collaborating with AI coding assistants using spec-driven development methodology

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: every model call, every tool, each subagent on its own context window and its own model, and what the session produced. Local and read-only — your session content never leaves the machine.

🌊 Lagune is your security copilot as you build, your Blue Team when you audit, whether you're a developer or not (no API key needed).

A disciplined methodology for AI-assisted software development. Covers architectural constraints, validation hooks, session governance, and PAG (Pattern Abstract Grammar) for structured AI collaboration. Copy claude-setup/ into your project to start.

Git. Ship. Done - Core

Skills, MCP servers, Custom Agents, Agents.md for SDKs to ground Coding Agents

Fast, flexible, and open tooling for building intelligent workflows with Cypress.

Lightweight coding agent written in Rust, optimized for memory footprint and performance

A minimal Rails API template for creating MCP (Model Context Protocol) servers with robust tool execution capabilities and examples.

Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.

An atelier for your Agent: spec-driven workflows, deep thinking, and code quality.

Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

Rails Engine with MCP compliant Spec.

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

Protocol-layer harness for DeepSeek: Python witness stack — posterior verification that keeps the protocol honest. dsh doctor --node probes included.

Open-source adversary emulation for AI agents and MCP servers.

Deterministic safety solutions for probabilistic AI agents

🏗️ Claude Code Plugin for smart blueprint-driven development

Goal-based planning and proof gate for AI coding agents

Graph-based long-term memory skill for AI (LLM) coding agents — faster context, fewer tokens, safer refactors