OOpen SourceObservabilitymedium

TheYgent

by Community

Private, self-hosted, no-code AI agent builder. Design agents on a visual canvas; run them on built-in local inference (llama.cpp, MLX, vLLM) or any OpenAI-compatible API. MCP tool

Visit site View repo Submit your build →

OSS

TheYgent

Added 16 Oct 2026

#ai-agents#ai-orchestration#apple-silicon#human-in-the-loop#llamacpp#llm#llm-agents#local-first

Catalogue record, not a reviewed recommendation. This record can include automatically collected descriptions and setup details. Confirm important claims with the original source. Explore source-reviewed tools.

Overview

TheYgent is a self-hosted, no-code AI agent builder with a visual canvas for designing agents. It runs agents on local inference engines (llama.cpp, MLX, vLLM) or any OpenAI-compatible API, and supports MCP tools, RAG, human-in-the-loop, and durable runs. The project is community-maintained and sends no telemetry.

Best for

Best for
Teams that want a private, self-hosted visual agent builder without telemetry.

Use cases

Design agent workflows visually without writing code
Run agents fully offline using local models
Connect agents to MCP tools and external OpenAI-compatible APIs

Notes

4 stars on GitHub. Last updated 2026-10-15.

Pros

Private by default: self-hosted with no telemetry
Flexible model support: local inference or any OpenAI-compatible API
Includes RAG, MCP tools, and human-in-the-loop out of the box

Cons

Community project with a small user base and limited support
Requires self-hosting and infrastructure maintenance
No-code canvas may be limiting for complex, custom logic

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

← Back to Open Source Submit your own entry →