HotPlex — Unified access layer for AI Coding Agent.

Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deterministic spec passes, and there is no "done" without live acceptance evidence. Spec-first, verification-gated, forbidden-paths enforced.

One prompt. Full delivery.

Solweaver: a Codex software team with GPT-5.6 Sol orchestrating Terra and Luna workers.

Claude Code (Sub-agent, Custom Commands) for RIPER-5

Building a Senior Staff Engineer with Sub-Agent Teams in Claude Code

Your Intelligence, Orchestrated. Every builder. Every team. Every agent. For Everyone.

Best AI Coding Workflow Plugin Pipeline 2026

The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure

An MCP server that lets LLM agents play Civilization VI.

An Orchestrate multiple coding agent desktop app

Containment for AI agents - user isolation, sandboxed execution, network controls, backup/rollback. TLA+ verified.

A headless browser for AI agents that fetches modern web pages, runs JavaScript, manages sessions, and returns token-efficient Markdown.

Autonomous game development for Godot, Bevy, and Babylon.js with Claude Code and Codex

🐬DeepChat - A smart assistant that connects powerful AI to your personal world

Co-creation infrastructure for humans and code agents — visual environment, skills, continuous learning, and distribution.

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

GLM-5.3-Flash × J-Space capability realization — benchmark presentation of the J-Space Cognition Suite

Build big projects with Claude. Chief breaks your work into tasks and runs Claude Code in a loop until they're done.

AI agents and Nix: parametrable skills/instructions and tools, packaged together in a reproducible and modular fashion

A Git-native knowledge layer for your team — and a set of tool suite that keeps it alive.

A Claude Code plugin that makes Opus behave like Fable — completion, evidence, and verification enforced as procedure. Ships only what a Fable-vs-Opus comparison proved transferable.

Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.

Shared context, memory, and task coordination across AI coding agents. Single Go binary, local SQLite, hybrid keyword and semantic search.