# Agents: A Self-Hosted, Observable Multi-Agent Workflow Orchestrator

> A self-hosted, observable agent orchestrator that supports running multi-agent workflows on code repositories. It enables collaboration and scheduling between agents through skill composition, memory management, and event triggering.

- 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm)
- 发布时间: 2026-05-31T19:15:43.000Z
- 最近活动: 2026-05-31T19:21:05.289Z
- 热度: 156.9
- 关键词: Multi-agent, Agent Orchestrator, Self-hosted, Observable, MCP, Claude Code, Codex, Workflow Automation, GitHub Integration, Token Budget, Local LLM
- 页面链接: https://www.zingnex.cn/en/forum/thread/agents
- Canonical: https://www.zingnex.cn/forum/thread/agents
- Markdown 来源: floors_fallback

---

## [Introduction] Agents: Core Introduction to the Self-Hosted, Observable Multi-Agent Workflow Orchestrator

This article introduces the Agents project—a self-hosted, observable agent orchestrator that supports running multi-agent workflows on code repositories. Its core features include skill composition, memory management, event-triggered collaborative scheduling, multi-backend model support (including local LLMs), fine-grained cost control, and reproducibility design. The project aims to enable developers to build and own their own agent universe without SaaS dependencies, ensuring data security and control.

## Project Background and Core Philosophy

The Agents project is maintained by eloylp, with source code hosted on GitHub (link: https://github.com/eloylp/agents, last updated: 2026-05-31). Its core vision is to enable developers to build their own agent universe, with three core philosophies:
1. **Self-hosted**: Code and prompts remain on the user's infrastructure, no SaaS dependencies, data never leaves the controlled environment;
2. **Observable**: Full event chain tracking, with real-time monitoring of the entire process from trigger to execution;
3. **Composable**: Modular design via Skills, Memory, and Triggers, supporting execution triggered by repository events, tags, cron schedules, or inter-agent scheduling.

## Architecture Design and Technical Implementation

Agents uses a daemon architecture, with the following execution pipeline:
1. **Prompt Composition**: Workspace guardrails + Skills + selected prompts + runtime context + Memory;
2. **Containerized Execution**: Launch containers from the `agents-runner` image, configure git identity, run AI CLI (Claude Code/Codex/local LLM), enforce JSON output, and enable repository tools;
3. **Response Parsing**: Extract outputs, scheduling requests, and update Memory;
4. **Persistence and Distribution**: Record tracking information, distribute scheduling requests, and write back to Memory. The design ensures isolated execution, parsability, and traceability.

## Three Interaction Modes

The project offers three interaction methods:
1. **Web Dashboard**: A graphical interface supporting workflow design (agent, prompt, skill management, etc.), real-time event streams, tracking, and memory viewing;
2. **MCP Server**: Terminal-based conversational interaction, controlling agents via MCP clients like Claude Code/Cursor;
3. **REST API**: A programmatic interface supporting script calls, on which the dashboard is built. The multi-mode design adapts to visual operations, automated scripts, and conversational development scenarios.

## Agent Collaboration and Security Mechanisms

**Agent Collaboration**: Supports reactive inter-agent scheduling with safety limits including depth (anti-recursion), fan-out (concurrency control), and deduplication (avoid repetition), enabling complex task division (e.g., code review + test generation).
**Security Design**:
- Built-in prompt guardrails: Resist indirect injection, cautious public operations, memory access restrictions, GitHub tool specifications;
- Layered authentication: Local admin creation, HttpOnly sessions (UI), revocable Bearer Tokens (MCP/API).

## Multi-Backend and Local Model Support

**Multi-Backend**: Each agent can choose Claude, Codex, or a custom backend; the same fleet can mix different providers.
**Local Models**: Supports llama.cpp, Ollama, vLLM, or OpenAI-compatible endpoints. An experimental built-in Anthropic-to-OpenAI translation proxy allows the `claude` CLI to connect to local LLMs, lowering the barrier to use.

## Cost Management and Versioned Reproducibility

**Cost Management**: Fine-grained Token budgets (daily/weekly/monthly UTC limits) supporting isolation scopes like global, cross-workspace (repo/agent/backend), and workspace+X; threshold alerts, Token consumption leaderboards, and multi-channel CRUD operations.
**Versioning**: Prompts/Skills/Guardrails are versioned by scope (global/workspace/repository). Edited versions are published as immutable, and exact used versions are tracked to ensure reproducibility, facilitating debugging and auditing.