Research that compiles.

My Nix system configs!

Superseded by coding-agent-toolkit — see README. Preserved for reference: Claude-Code-only patterns from earlier iteration.

Evidence-based learning engine — first-principles curricula, free-recall verification with receipts, FSRS-scheduled memory, and explorable artifacts. Learn anything; keep it.

Unified execution environment for Python code, shell commands, and programmatic MCP tool calls.

Persistent Linux workspaces for agentic development.

The agentic workspace where people and agents work together in the loop.

The operations layer for agentic engineering — portable skills and contracts connecting intent, agents, software factories, and independent judgment.

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

A reusable agent workflow kit with personas, skills, rules, and memory files.

Hand off tasks to Devin — a plugin/skill for Claude Code, Codex, Cursor, and any coding agent

Multi-agent codebase review for PRs, CI, and downstream fork syncs.

flow + prompt = flompt - Visual AI Prompt Builder. Decompose, edit as flowchart, recompile into optimized machine-readable prompts

Governance standard and reference toolset for LLM-maintained knowledge corpora

AI-powered cascading development framework. Decompose complex projects into parallel executable tasks with auto-generated PRDs, design docs, and multi-agent collaboration (Claude Code, Codex, Aider).

A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw

Research-grade investment decision engine for AI agents: isolated multi-agent committee, auditable verdicts, backtests with lookahead protection, published negative results

Open-source deep research for AI agents: 40 channels, 10+ Chinese sources.

Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-first methods, powered by TypeScript and Bun.

A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

The OKF toolkit for Claude Code — author, maintain, validate & visualize Open Knowledge Format bundles. Plugin, agent skills, and a GitHub Action.

Query, monitor, and manage Unraid servers via GraphQL API through MCP tools. Supports system info, Docker, VMs, array/parity, notifications, plugins, rclone, and live telemetry.

PyWry is a cross-platform app factory, rendering engine and UI toolkit for Python that produces native desktop, web, and notebook experiences from a single API.

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence