Explore the directory

Ruby bindings for llama.cpp that run open-source language models such as Gemma, Qwen, Llama and GPT-OSS locally, directly inside a Ruby application, plus a standalone interactive CLI chat.

• Inference
• Libraries

A reference handbook for engineers building production AI systems, covering reference architectures, runnable labs and interview material for a set of recurring AI-infrastructure problems.

• Tutorials
• Books

A supervision layer that turns long-running or interactive terminal commands, including AI coding agents, into persistent sessions that can be detached from, monitored, and reattached to from anywhere.

• Coding agents
• Terminals

A local-first MCP context engine that indexes a repository into a graph, routes a prompt to the relevant symbols, and sends the model a compact evidence packet instead of whole files.

• MCP servers
• Agent memory

A plugin-based, declarative data-access layer where an AI agent or user describes the data it needs and mloda resolves how to fetch and transform it, tracing every result back to its source.

• Data engineering

An experimental, open-source terminal AI coding assistant written in Python that combines a streaming TUI, persistent local sessions, scheduled goal-based runs, MCP integrations and sandbox-aware permissions.

• Coding agents

Example scripts in Python and JavaScript that call Limina's REST API to find personally identifiable information in text and replace it with redaction markers, hashes, tokens or synthetic values.

• Security
• APIs

A research implementation that compiles a bounded document corpus into a navigable hierarchy of Anthropic Skills, so an LLM agent answers questions by browsing documents instead of querying a vector search service.

• Agent skills
• RAG

A skill-first, spec-driven development workflow for AI coding assistants that guides them through defining intent, planning demoable tasks, executing with checkpoints, and validating against the spec.

• Agent skills

An open-source, local-first agentic AI layer for Android, sideloaded as a single app, that acts on the phone through more than 65 tools while keeping personal data on the device.

• Agent frameworks

A fast, multithreaded CPU library of SIMD-optimized quantization and dequantization kernels for machine learning, more than twice as fast as PyTorch's built-in routines on tested hardware.

• Models
• Libraries

An MCP server that gives AI assistants tools for Arm architecture development, such as searching Arm documentation, scanning code for x86-to-Arm compatibility, and analyzing assembly performance.

• MCP servers
• Debugging

A collection of measured benchmark results for the Intel Arc Pro B70 GPU covering LLM inference speed and power draw, video generation, and dual-card scaling, from real single- and dual-card runs.

• Inference

A hands-on repository of projects and code examples for building multi-agent systems, RAG pipelines and automated workflows with LangGraph, AutoGen, MCP, n8n and related tools.

• Tutorials

A unified AI command-line and server platform that connects 14 LLM providers with failover, runs coordinated autonomous agents behind a ReAct engine, and also serves as a gRPC server and Kubernetes operator.

• Agent frameworks
• LLM gateways

A reflection-free JSON binding library for Java that generates conversion code at compile time through an annotation processor, as a lighter alternative to Jackson's ObjectMapper or Gson.

• Libraries

A Python package that converts JSON Schema definitions into Pydantic models automatically, built to simplify generating typed models for AI frameworks such as LangChain and CrewAI.

• Libraries

A set of skills that teach AI coding assistants current Deno development practices, from using Deno as a runtime and package manager to migrating a Node project and deploying to Deno Deploy.

• Agent skills

A proof-of-concept Model Context Protocol bridge that lets an LLM query a Velociraptor digital-forensics deployment in natural language, such as checking a named machine for suspicious processes.

• MCP servers
• Security

An Electron module for prototyping local-first apps that chat with local large language models, exposing an API modeled on Chromium's window.AI but supporting any GGUF model.

• Inference
• Desktop

An open-source memory system for AI agents that gives them persistent episodic, semantic and procedural memory, with cryptographic integrity proofs and automatic decay and conflict resolution over time.

• Agent memory

An on-device noise-suppression engine that removes background noise from audio entirely offline, with SDKs for Python, Android, iOS, C and the web across desktop, mobile and Raspberry Pi.

• Speech
• Libraries

Companion source code for a conference talk about how to build AI coding agents.

• Tutorials

A general-purpose system prompt for engineering, technical analysis and security research that pushes an LLM toward restrained, accurate answers over chatty or emotionally agreeable ones.

• Agent skills