Coding & Development

Boilerplate setup to deploy multi-agent streaming JSON interfaces over asynchronous WebSockets securely.

A battery-packed toolkit for building AI-native applications, giving agents straightforward structured entity-extraction skills.

Lightweight graph routing engine enabling localized model structures to hand off tasks upon failure.

Self-hosted AI coding assistant backend featuring low-latency code completion agent skills over internal corporate repos.

Open-source autopilot for VS Code and JetBrains. Connect any model to build unique architectural review agents inside your IDE.

aider is AI pair programming in your terminal. It lets you edit code in your local git repository directly through command-line chat.

Config routines giving specialized agents the ability to submit custom LoRA fine-tuning runs based on failed interactions.

Ultra-fast function calling definitions and JSON generation schemas tailored for edge-deployed multi-modal agents.

Client-side rendering modules converting real-time agent output strings directly into interactive interface previews.

Event driving connector modules linking asynchronous Python backend services directly to active agent memory channels.

Programmatic input mapping structures translating algorithmic criteria into reliable structured text generation directives.

Native system tool blueprints allowing agents to control operating file systems and basic network routing assets seamlessly.

Production configurations validating compound text outputs against complex business model rules during active loops.

Agentic templates allowing developers to turn issue descriptions directly into a proposed technical plan and pull request pull edits.

Direct IDE integrations providing agents the skill to rewrite codebase contexts safely based on natural language feedback.

Visual environment to track and audit the multi-agent design, coding, and testing loops inside virtual corporate workspaces.

Standardized graph tracking points managing common interaction states across cyclical multi-model processing environments.

Devika is an Advanced AI Software Engineer that can understand high-level human instructions, break them down into steps, research, and write code.

Algorithmic profile templates mapping traditional executive roles directly into discrete automated prompt structures.

Monitoring scripts tracking development bottlenecks and code refinement loops across complex multi-file codebase operations.

An open-source, locally running implementation of OpenAI's Code Interpreter. Let LLMs run code on your computer.

自分用の Agent Skills 集（SKILL.md 形式 / Claude Code 向け）

SKILL.md files for coding agents fo FXGL

Agent Skill that detects and rewrites the tells that make text read as AI-generated (SKILL.md + zero-dependency linter).