Explore the directory

Igniter is an Elixir code-generation and project-patching framework that provides mix tasks to install dependencies, upgrade them with codemods, and refactor code such as renaming a function across a project.

• Libraries

Cataclysm is a Python library that generates and executes code at runtime for any undefined function call, inferring an implementation from the function's name, arguments and surrounding context through an LLM.

• Libraries

Floci UI is the web console for the Floci local cloud-emulator ecosystem, giving a unified Cloud Explorer and Console Home over locally emulated AWS, Azure and GCP services, showing only real data.

• Hosting

A Claude Code skill that records the reasoning behind non-trivial code decisions in the repository itself, so later AI sessions see why past choices were made instead of repeating or breaking them.

• Agent skills
• Agent memory

A self-hosted AI workspace where conversations are shared team rooms for people, native actors, and bridged remote agents, with governed access to plugins, MCP tools, memory, and local devices.

• Agent frameworks

A curated, regularly updated collection of resources on Azure OpenAI and large language models, covering RAG, agents, prompt engineering, and LLMOps, organized by topic and by publication date.

• Curated lists

A cycle-level simulator for LLM serving infrastructure that models heterogeneous accelerators, disaggregated memory tiers, and multi-instance parallelism to study serving performance without real hardware.

• Inference

A platform that lets MCP-capable AI agents run declared infrastructure actions on a host through policy checks and an outbound-only runner, with approvals and an audit trail.

• MCP servers
• Hosting

An open-source backend scaffold for admin and management systems, built on Spring Boot 4 and Java 25, with role-based permissions, dynamic menus, code generation, and a Vue 3 frontend.

• Web frameworks
• Backend

A research framework where language models create persistent symbolic dialects (LSFs) for exchanging reasoning between speaker and listener models, then routes among them under accuracy, token, and reliability constraints.

• Agent frameworks
• Papers

A curated collection of papers, datasets and benchmarks for multimodal large language models applied to remote sensing, built around a survey of the field.

• Curated lists
• Papers

A desktop and mobile session manager for running multiple coding agents such as Claude Code, Codex, Cursor Agent and Aider in parallel, turning git worktrees into a one-shortcut workflow instead of a manual command sequence.

• Coding agents

Git-native, deterministic memory for AI coding agents such as Claude Code, Codex, Cursor and Gemini CLI, storing project knowledge as reviewable Markdown in the repository instead of a vendor account.

• Agent memory

A structured skill framework for Claude Code with more than 130 professional skills covering deployment, security, databases, content and marketing, activated automatically as needed, plus persistent memory and a local dashboard.

• Agent skills
• Agent memory

A cross-platform, AI-native terminal that combines a multi-protocol remote-access client, supply-chain vulnerability scanning and more than a dozen autonomous security agents for penetration testing, red-team work and CTF challenges.

• Terminals
• Security

Awesome Loop Models is a curated, interactively browsable list of papers and long-form technical posts about loop models, architectures that reuse a shared learned layer or block within a single forward pass.

• Papers

A production-ready Laravel admin panel and headless CMS starter kit with role-based access control, a modular architecture, a CRUD generator, and a built-in MCP server for AI agents.

• Web frameworks
• Backend

A tool that gives AI coding agents a consistent way to investigate how software works, from app behavior down to native binaries, so a feature can be understood, evidenced and rebuilt for another project.

• Agent skills
• Debugging

Hand-written PyTorch implementations of modern open-source LLM architectures such as Llama, Qwen, DeepSeek and Gemma, built one model at a time for clarity and learning rather than production use.

• Models
• Tutorials

A native iOS companion app for the herdr agent-first terminal runtime, giving a status-sorted console of every coding agent running across a person's machines, with a real terminal, QR device pairing and push notifications when an agent needs attention.

• Coding agents

A modular Go toolkit for building AI agent applications with long-term memory, knowledge retrieval and voice, usable as a library, a background daemon, or a real-time pipeline, without tying the code to one model provider.

• Agent frameworks

A composable, view-based memory plugin for DeepSeek Harness, giving an agent three tiers of memory, runtime facts, searchable documents, and durable memory spaces, through pluggable sources and strategies.

• Agent memory

An e-commerce data-warehouse question-answering agent built as a teaching project for learning LangGraph, combining a metadata knowledge base, hybrid retrieval, and staged natural-language-to-SQL generation with execution and streaming results.

• RAG
• Tutorials

An LLM-powered multi-agent framework for simulating interactive, evolving story worlds, where characters perceive, plan and act on their own while a player can also give direct instructions and steer the plot.

• Agent frameworks