C

claude-code

Local-first AI agent memory and context engine for Claude Code, Codex, Gemini and MCP: cited Markdown recall, code search, hooks and cross-machine serving.

Draft and create structured GitHub or GitLab issues using repository context, project conventions, and explicit user approval.

Yet another software engineering agent orchestration system. This time with a mythical theme. Originally designed for Claude Code, now with support for OpenCode, Github Copilot, and OpenAI Codex.

Ephemeral self-managed GitLab simulations on Google Compute Engine for LLM-mediated work.

Claude Code in a Docker image built on aicodebox, with an HTTP API, an OpenAI-compatible endpoint, an MCP server, a Telegram bot and a cron scheduler, in minimal or full-toolchain variants.

Otōto is an MCP server for Claude Code and OpenCode. You can hand off LLM tasks (and other jobs!) to Ototo saving tokens and context.

Sign-in and approvals through messaging apps for your website or app. No passwords, no forms, no SMS codes - zero typing, even on screens without a keyboard.

The user scans a QR code shown on a computer, TV or any other screen - or taps a button on their phone - and confirms with a single tap in a messaging app they already trust: Telegram, WhatsApp or another supported channel. Veriqa plugs into your application as a standard OIDC provider, with no frontend SDK. Open source under MPL-2.0.

A structured second brain for AI-enabled product work. This guide teaches your AI assistant how to help you organize, track, and sustain work on any product — software, business plans, research projects, or anything else that benefits from structured context and incremental progress.

GitLab's official AI skills vendored for GDK-free environments, plus a no-GDK contribution spine. Sibling of gitlab-simulation.

Go-REST-API-Backend für MOSAIK Campus – die datenschutzfokussierte Web-App zur Digitalisierung der Elternbeirats-Organisation. PostgreSQL-Datenhaltung, Scope-Isolation & feldweise Verschlüsselung personenbezogener Daten.

Long-running campaigns for herdr: threads of agent work, addressed as estate/campaign, that outlive every conversation.

Agent skills for Ultralytics YOLO, covering models, datasets, training, tuning, inference, tracking, and export.

GitHub: https://github.com/ultralytics/skills

https://www.ultralytics.com

A fast, local workspace for Claude Code, Codex, Gemini CLI, Kimi Code, Qwen Code, DeepSeek, OpenRouter, and your shell.

GitHub: https://github.com/ultralytics/lite

https://github.com/ultralytics/lite/releases/latest

Populates an empty Git repository with scaffolding files and folders for development of CLI tools, libraries, and (micro) services for C++, Go, and Java. The pre-populated repository is prepared for specification driven development with support of an AI coding assistant (Claude Code and GitHub Copilot, albeit to a lesser degree).

Local agent-session record lake: Parquet + DuckDB over harness transcripts. Cost analytics, correction mining, simulation priors.

Specification graph manager for AI-augmented projects, on the nomograph-claim substrate.

Chain Daddy plugins for coding agents (Claude Code, Codex, Cursor): skills and MCP servers for putting a game, app or dApp on crypto with Chain Daddy.

Connect AI coding assistants (Claude, ChatGPT, Cursor, VS Code, Codex) to the keyless bitHuman docs MCP server, plus the bithuman-integrate skill.

A self-hosted bookmark manager built with Django, basic HTML templates, CSS & vanilla JavaScript.

Organize bookmarks into folders, import/export browser bookmarks, and optionally share your collection via a public link — usable as a browser start page with quick access to editing.

Browser bookmark sync is tied to each vendor's ecosystem, and third-party plugins don't cover every browser. This is a simple, self-hosted alternative — one Docker container, one SQLite file, accessible from any browser on any device.

A self-hosted AI platform — inference, tool use, browser automation, image generation, speech synthesis, transcription, object storage, agentic code execution, and more — behind a single OpenAI-compatible endpoint. One docker-compose up.