Explore the directory

A Claude Code plugin that grounds Claude's answers about Reuven Cohen's RuvNet stack, including RuVector, Ruflo, AgentDB, RuLake and SPARC, in the stack's own source code through a single MCP search tool.

• MCP servers
• Agent skills

A native Rapid-MLX model provider for DeepSeek Harness that reads a model's context length, quantization and reasoning support directly from a running Rapid-MLX server instead of a hand-maintained settings file.

• Coding agents

A command-line runtime for loop engineering that repeatedly drives a coding agent through a portable directory of instructions called a ralph loop.

• Coding agents

A GitHub Action that runs the Pi coding agent inside GitHub-compatible CI/CD workflows, letting it work on issues and pull requests on GitHub, Codeberg or self-hosted Forgejo.

• Coding agents
• CI/CD

A TypeScript and Node.js multi-agent orchestrator that adds a shared, lockable blackboard, budgets and guardrails to coordinate parallel agents across 32 different agent frameworks.

• Agent frameworks

A tool that lets AI agents safely run shell commands, CLI tools and scripts as MCP tools, with YAML-defined tool configuration and CEL-based parameter validation.

• MCP servers

A local review workspace for AI coding agent output that pairs a faster agent runtime with code intelligence, exact-range reads and verification evidence, so a human can review revisions rather than another AI-written summary.

• Coding agents
• Code quality

The official TypeScript framework for building Model Context Protocol servers, clients and apps, handling protocol plumbing so a project can focus on its own tools, resources and prompts.

• MCP servers

A 15-chapter, hands-on Python course that builds a coding agent's harness one primitive at a time, proving each addition against a real local model rather than mocking it.

• Tutorials

Reproducible on-device LLM benchmarks for Apple Silicon, comparing Apple Core AI, MLX, LiteRT-LM and Core ML on the same models and harness, with every result tied to its quantization and capture session.

• AI evals

A SQL toolchain that compiles annotated .sql files into type-safe database access code for ten languages and ten databases, with linting, security auditing and pre-commit hooks.

• Code quality
• Databases

A GPU-accelerated LLM inference engine written entirely in Delphi that runs the full transformer forward pass for GGUF models on the GPU through Vulkan compute shaders, with no Python or CUDA toolkit.

• Inference

An operating layer for a pair of NVIDIA DGX Spark machines that lets several large models share the hardware as switchable lanes, plus on-demand model loading and QLoRA fine-tuning on the idle node.

• Models
• Inference

A local, offline-ready Rust command-line tool for retrieval-augmented document search and question answering, storing everything in a single SQLite index.

• RAG

A domain-agnostic multi-agent harness for Claude Code that designs and builds software from a plain description, researching the space and drafting a plan before any code is written.

• Coding agents

An LLM proxy with guardrails, rate limiting, multi-strategy routing, semantic caching, an MCP proxy and end-to-end request tracing, configured through a UI that turns a plain-English description into YAML.

• LLM gateways

A free, open-source desktop coding workbench for AI agents that keeps its own footprint small, running on an existing AI subscription or an API key.

• Coding agents

A diagnostic tool that traces why an LLM memory system produced a wrong answer, modeling extraction, retrieval and generation as an operation-variable execution graph.

• Agent memory
• Debugging

A reference training pipeline that grows a single architecture from a 2B dense seed to a 120B sparse mixture-of-experts model through four stages on a single eight-GPU node.

• Models

A Qt Creator plugin that adds local LLM-assisted text completion and chat, backed by a locally running llama.cpp server.

• Editors

A local-first, model-agnostic memory runtime for long-lived AI agents that treats the prompt as an activation signal spreading through a persistent knowledge graph rather than a plain retrieval query.

• Agent memory

A zero-dependency Python framework that adds persistent memory, reflection on past failures, prompt-injection safety and decision replay to any rule-based, reinforcement-learning or LLM-based agent.

• Agent frameworks
• Agent memory

A curated list of open-source tools and frameworks for securing autonomous AI agents, organized by security lifecycle stage from red teaming through runtime protection to governance.

• Security
• Curated lists

A Markdown-based task management system for humans and AI coding assistants, with a CLI, a web dashboard, AI skills and an MCP server, all running locally.

• Agent skills
• CLI tools