Geny Executor — Data skill for Claude Code
Manifest-driven 21-stage agent pipeline for Python — 5 LLM backends (Anthropic / OpenAI / Google / vLLM / Claude Code CLI), tools, skills, memory, sandboxed CLI runs, MCP.
How to install Geny Executor
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open CocoRoF/geny-executor and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Geny Executor does
Manifest-driven 21-stage agent pipeline for Python — 5 LLM backends (Anthropic / OpenAI / Google / vLLM / Claude Code CLI), tools, skills, memory, sandboxed CLI runs, MCP. The engine behind Geny. Apache-2.0.
Alternatives in Data
- Private GPT — Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more 57.5k ★
- HTML Anything — ✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it 8.5k ★
- Claude Deep Research Skill — Enterprise-grade deep research skill for Claude Code with 8-phase pipeline, source credibility scoring, and au 1k ★
README
geny-executor
[](https://pypi.org/project/geny-executor/) [](https://pypi.org/project/geny-executor/) [](LICENSE) [](https://github.com/CocoRoF/geny-executor/actions/workflows/ci.yml)
**A harness-engineered agent pipeline library — 21 stages, 5 LLM providers, MCP-native, fully introspectable.**
geny-executor implements a **21-stage pipeline** with **dual-abstraction architecture** (stage slots × strategy slots). Inspired by Claude Code's agent loop and Anthropic's harness design principles. No LangChain. No LangGraph. Just an explicit, modular pipeline where every step is observable, mutatable, and swappable.
[한국어 README](README_ko.md) · [Architecture](docs/architecture.md) · [Providers](docs/providers.md) · [Error codes](docs/error_codes.md) · [Claude Code CLI host](docs/claude_code_cli.md)
The Geny ecosystem
These projects are built to work together. **Geny** is the product at the top of the stack; everything below is a building block you can also use on its own. **➡️ marks where you are.**
| Project | What it is | Role in the stack |
|---|---|---|
| **Geny** | Multi-agent VTuber + autonomous-worker platform | The product — uses every project below |
| ➡️ **geny-executor** | 21-stage, manifest-driven agent pipeline · PyPI · Apache-2.0 | The engine everything runs on |
| **GAPT** | Self-hosted AI DevOps platform — sandbox · edit · build · deploy | Where agents safely touch real repos |
| **geny-avatar** | 2D live-avatar editor with AI texture generation | Where Geny's faces are |
Related Skills
Anthropic Retrieval Demo
Lightweight demo using the Anthropic Python SDK to experiment with Claude's Search and Retrieval capabilities
Derrick B2b Data Enrichment Google Sheets Claude API Derrick
B2B data-enrichment engine providing professional emails, phone numbers, LinkedIn/company enrichment, tech-sta
UX Init
Bootstrap ux-skill v2 in the current project — detects your IDE, installs the right artifacts, validates that
DB LLM Skills
A globally-installed engine for letting an LLM access PostgreSQL safely: read-only role provisioning, a pg_cat
Social Leaker
Self-hosted social media OSINT and data collection panel built with Python, FastAPI, and SQLite. Features obje
LLM Analytics Apps
Node.js and Python examples for integrating LLM providers with PostHog's AI SDKs for observability and analyti
Related Agents
AI LLM Engineer
Use this agent when the user types /ai or asks for ai/llm engineer work — e.g., build a RAG pipeline over our
LLM Orchestrator
Use this agent for LLM integration work — prompt engineering, multi-provider abstraction (OpenRouter, Gemini,
AI ML
AI/ML 통합 전문가 + LLM API 최신 모델/SDK 코딩 가이드. RAG 시스템, 문서 분석, OpenAI/Anthropic/Gemini/Ollama 최신 API 보장. "AI integra