What makes agent-guild notable?

1.3K downloads. Trust evidence available

How should agent-guild be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

agent-guild

智能体协会（agent-guild）— cross-agent shared memory. 本机多个 AI agent 共享同一份身份、规则、记忆与交接消息 — 纯本地 Markdown/JSON，无服务器。触发（任何自然等价表达都算）： · 身份/习惯："我是谁" "我的偏好" "who am I" "my routine" · 回忆/历史："你记得吗" "上次我们聊过" "what did we discuss" · 写记忆："帮我记住" "记一下" "remember this" "记到日志" · 跨 agent："告诉其他 agent" "交接给" "hand off" · 当前状态："现在在做什么" "当前焦点" "current focus" · 数据卫生："整理协会" "清理过期数据" "groom" "cleanup" · 跨设备："换了台电脑" "这个工具在哪" "cross-device" · 加入："加入协会" "初始化" "join agent guild" 能力：共享身份/规则/焦点读写；收件箱交接；每日日志；会话闭环（ag recall / ag finish）；并发锁防丢写；学习台账；自动 groom 归档；跨设备三层作用域（shared/platform/host）。 Skill: agent-guild Owner: dqsjqian Summary: 智能体协会（agent-guild）— cross-agent shared memory. 本机多个 AI agent 共享同一份身份、规则、记忆与交接消息 — 纯本地 Markdown/JSON，无服务器。触发（任何自然等价表达都算）： · 身份/习惯："我是谁" "我的偏好" "who am I" "my routine" · 回忆/历史："你记得吗" "上次我们聊过" "what did we discuss" · 写记忆："帮我记住" "记一下" "remember this" "记到日志" · 跨 agent："告诉其他 agent" "交接给" "hand off" · 当前状态："现在在做什么" "当前焦点" "current focus" · 数据卫生："整理协会" "清理过期数据" "groom" "cleanup"

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.3k

Updated

Oct 10, 2026

Version

3.12.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.3K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.3K downloadsadoption · observed Oct 10, 2026
Latest release: 3.12.0release · observed Sep 30, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s171bam7r1t26623myew3k4qrn83xjbg:agent-guild

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-dqsjqian-agent-guild/snapshot"

Documentation

CLAWHUB

156,463 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: agent-guild
description: |
  智能体协会（agent-guild）— cross-agent shared memory. 本机多个 AI agent 共享
  同一份身份、规则、记忆与交接消息 — 纯本地 Markdown/JSON，无服务器。

  触发（任何自然等价表达都算）：
  · 身份/习惯："我是谁" "我的偏好" "who am I" "my routine"
  · 回忆/历史："你记得吗" "上次我们聊过" "what did we discuss"
  · 写记忆："帮我记住" "记一下" "remember this" "记到日志"
  · 跨 agent："告诉其他 agent" "交接给" "hand off"
  · 当前状态："现在在做什么" "当前焦点" "current focus"
  · 数据卫生："整理协会" "清理过期数据" "groom" "cleanup"
  · 跨设备："换了台电脑" "这个工具在哪" "cross-device"
  · 加入："加入协会" "初始化" "join agent guild"

  能力：共享身份/规则/焦点读写；收件箱交接；每日日志；会话闭环
  （ag recall / ag finish）；并发锁防丢写；学习台账；自动 groom 归档；
  跨设备三层作用域（shared/platform/host）。
slug: agent-guild
displayName: 智能体协会 Agent Guild
display_name: 智能体协会 Agent Guild
display_name_en: Agent Guild
description_zh: 跨 agent 共享记忆协议，本机多个 AI 共用一份身份/规则/记忆，可跨设备搬运
description_en: Cross-agent shared memory protocol — one identity, rules and memory for every AI on your devices
author: dqsjqian
category: productivity
protocol_version: "3.3"
version: "3.12.0"
platforms: ["macos", "windows", "linux", "android", "ios"]
license: MIT
homepage: https://github.com/dqsjqian/agent-guild
repository: https://github.com/dqsjqian/agent-guild
agent_created: true
---

# Agent Guild — Runtime Skill

> Local-first cross-agent shared memory. Join once, share identity/rules/focus
> across trusted agents with access to this machine's files. Data lives at
> `~/.agent-guild/` as plaintext, scoped shared / platform / host. The CLI
> does not upload memory; an agent's handling of text it reads depends on
> that agent's runtime. See the network and retention controls below.

`SKILL_DIR` = the directory containing this file. CLI:
`python3 <SKILL_DIR>/scripts/ag.py` (referred to as `ag`).
Python 3.9+ stdlib only. On Windows use `python` if `python3` is not on PATH.

## Quick verify — the basic memory loop

Three commands exercise the full loop (create guild → read context → write
log). Run them as-is; `demo-agent` is just an example name, any kebab-case
name works:

If the guild is not installed yet, use `scripts/ag.py` from the package you
are reading for the first `init`; it creates the central CLI used below.

```bash
ag() { python3 "$HOME/.agent-guild/skills/agent-guild/scripts/ag.py" "$@"; }

ag init demo-agent                                # 1. create the guild (idempotent)
ag bootstrap demo-agent                           # 2. read shared context
echo "first session: guild verified" | ag finish demo-agent   # 3. write today's log
```

Expected result: `init` prints the created directory layout, `bootstrap`
prints identity/rules/projects/focus, `finish` prints the log file path
(`log/daily/<date>-demo-agent.md`) — read that file back to confirm the
write landed. Two more one-liners worth trying:

```bash
ag recall verified        # repeat from another agent to verify shared recall
ag doctor                 # health check: links, paths, core files
```

## Task routing — when the user asks for X, do this

| The user says… | What to run |
|---|---

README.md

# Agent Guild

> 让多个本地 AI 助手复用同一份偏好、项目约定和工作交接。

[English](README_EN.md) | **中文**

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/dqsjqian/agent-guild/blob/main/LICENSE)
[![Protocol](https://img.shields.io/badge/protocol-v3.3-green)](references/SPEC.md)

Agent Guild 面向**同一用户使用的多个、受信任且能够读写本地文件的 AI 助手**。
它把共享上下文放进 `~/.agent-guild/` 的 Markdown / JSON 文件：你能查看、修改、备份，
切换助手时也能继续使用。运行时 skill 提供读写约定，Python CLI 处理并发写入、检索和归档。

## 先验证一次：A 记住，B 找到

安装并让两个助手接入后，用一条没有敏感内容的演示约定测试：

1. 对助手 A 说：
   > 请记住这条长期演示约定：演示项目的交付说明必须包含验证结果。
   > 保存到协会的 `memory/shared/demo.md`，登记到 `memory/shared/INDEX.md`，并告诉我保存路径。
2. 切换到助手 B，说：
   > 在协会里查找“演示项目”的交付约定，复述内容并引用来源文件。
3. 确认 B 找到同一条内容和文件。测试结束后，可以删除这条演示约定及其索引项。

这才是共享记忆的验收结果；磁盘上出现 skill 文件只是接入的第一步。
长期偏好和项目约定放在身份、规则或共享记忆中；`log/daily/` 记录会话经过，不代替长期记忆。
助手仍需按协议读取相关上下文，Agent Guild 不会自动把所有历史塞进每一次回答。

## 适合谁，有哪些边界

| 你的需求 | Agent Guild 的做法 |
|---|---|
| 经常切换两个或更多本地助手，不想重复交代约定 | 共享身份、规则、项目状态和可检索的记忆文件 |
| 想看清助手记了什么，并自行修正 | 使用普通 Markdown / JSON 文件，不依赖专有数据库 |
| 想交接未完成的工作 | 共享当前焦点、收件箱和当日日志；接收方读取后继续 |
| 想把个人工作上下文搬到另一台设备 | 区分共享、平台和本机信息；文件搬运由你选择 |
| 还想统一 skills、工具及其数据位置 | 可选择完整共享中心模式；无需为了试用记忆而先迁移这些资产 |

它不提供多人权限隔离、自动跨设备同步或后台任务执行。没有本地文件访问能力的助手，
不能直接使用这个目录；有文件访问能力但不能加载自定义 skill 的助手，可以手动读取协议，
不过需要在会话中提醒它使用，不等同于自动触发。

核心取舍是：**少量基础设施、可检查的文件，换取助手遵守读写约定和用户管理文件访问范围。**
CLI 需要 Python 3.9+，只使用标准库；没有服务端或常驻进程。

## 安装与接入

### 1. 建立中央目录

macOS / Linux / WSL / Git Bash（需要 Bash 和 curl）：

```bash
curl -fsSL https://raw.githubusercontent.com/dqsjqian/agent-guild/main/scripts/install.sh | bash
```

Windows（PowerShell 5.1+）：

```powershell
iwr -useb https://raw.githubusercontent.com/dqsjqian/agent-guild/main/scripts/install.ps1 | iex
```

安装器下载协议和 CLI、初始化模板，并打印接入口令。它不修改助手自己的目录。
要先检查源码，也可以下载并阅读安装脚本后再运行。

### 2. 让每个助手接入

初次试用建议只接入共享记忆，对助手说：

> 请读 `~/.agent-guild/ONBOARDING.md`，仅接入共享记忆，保留现有 skills 和工具目录。

需要统一管理更多资产时，可以明确选择完整共享中心：

> 请读 `~/.agent-guild/ONBOARDING.md`，按完整共享中心模式接入，报告迁移的目录和使用的安装方式。

完整模式会把可迁移资产放进协会，并尝试用目录链接连接助手的 skills 目录；不兼容时使用
逐 skill 链接、拷贝或手动读取。详情见 [接入流程](references/ONBOARDING.md)。
接入后运行上面的两助手验证，确认记忆能被实际找到。

### 从源码安装

将**项目源码**与**私人协会数据**分开放置。在你选择的源码工作目录运行：

```bash
git clone https://github.com/dqsjqian/agent-guild agent-guild-source
python3 agent-guild-source/scripts/ag.py init demo-agent
```

`demo-agent` 可换成你的助手名称；Windows 若使用 `python` 命令，相应替换 `python3`。
`init` 会在 `~/.agent-guild/` 创建运行目录并安装 skill，然后按上面的口令让助手接入。
不要把源码仓库直接克隆到私人数据目录。

## 你能控制什么

- **记忆内容**：身份、规则和项目文件由用户控制。助手只记录任务所需的摘要；不要把密码、token 等凭据写进共享记忆。
- **网络与更新**：安装需要下载文件。运行时默认在 `bootstrap` 后按设备最多每 24 小时检查一次三个公开版本源，不上传记忆内容。`UPGRADE.md` 中 `mode = check` 只提示，`mode = apply` 会下载并安装新版本，`mode = off` 关闭自动检查；手动 `upgrade` 仍可使用。
- **只查看上下文**：`bootstrap <agent> --no-maintenance` 跳过本次自动整理和升级检查，不改变已有策略。
- **自动归档**：`bootstrap` 默认按设备每 24 小时尝试一次 groom，将过期日志、焦点及已解决台账搬到归档，轮转审计；未读消息只报告。先用 `groom --dry-run` 看计划，保留期限在 `RETENTION.md` 调整。归档不等于删除，也不会缩小整个目录的历史总量。
- **共享范围**：`memory/<agent>/` 和 `private/` 是组织约定，不是权限或加密边界。能访问这些文件的程序仍可能读取它们；加入的助手应当是你信任的。
- **模型与备份**：数据文件由 Agent Gui

references/adapters/README.md

# Adapters

This directory hosts integration guides for specific AI agent products. Each file describes:

- How that agent discovers `~/.agent-guild/`
- Whether it supports symlinks (or needs a fallback)
- Where in its config the user should reference the central directory
- Any agent-specific quirks

## Contributing a new adapter

Copy `_template.md` to `<agent-name>.md`, fill it in, open a PR.

We **do not** ship per-agent code adapters — adapters are documentation only. The protocol is designed so any sufficiently capable agent can self-onboard from `~/.agent-guild/ONBOARDING.md`, then use `SKILL.md` as its runtime capability.

## Existing adapters

- (none yet — be the first)

_meta.json

{
  "ownerId": "kn72h3yzebmbfeccjwrz22rnfs83xf4g",
  "slug": "agent-guild",
  "version": "3.12.0",
  "publishedAt": 1790757055938
}

references/adapters/_template.md

# <Agent Name> Adapter

> Replace `<Agent Name>` with the actual agent (e.g. "Claude Code", "Cursor", "Aider").

## Agent home

- **Default home directory**: `~/.<agent-dir>/`
- **User-extensible skills directory**: `<the path the runtime is allowed to load third-party skills from — NOT the built-in/whitelisted dir>`
- **Skill mechanism**: <e.g. "reads `<user-skills-dir>/*` at session start", or "uses a Custom Skills setting in the UI", or "no skill mechanism — read SKILL.md directly each session">

## Symlink support

- [ ] Symlinks work
- [ ] Symlinks not supported — must `cp` and re-fetch periodically
- [ ] Other (explain)

## How to join

```bash
# Either rely on the global installer:
curl -fsSL https://raw.githubusercontent.com/dqsjqian/agent-guild/main/install.sh | bash

# Or do it manually:
mkdir -p <user-extensible-skills-dir>
ln -sfn ~/.agent-guild/skills/agent-guild <user-extensible-skills-dir>/agent-guild
```

Then start a new session with the agent and say:

> "Read `~/.agent-guild/ONBOARDING.md` and follow the joining flow."

(Onboarding is one-time. After joining, the agent uses `~/.agent-guild/skills/agent-guild/SKILL.md` automatically as its runtime capability.)

## Verification

After the agent reports having joined:

```bash
cat ~/.agent-guild/registry.json | grep -A 7 '"<agent-name>"'
ls ~/.agent-guild/log/daily/$(date +%Y-%m-%d)-<agent-name>.md 2>/dev/null
```

The registry entry should include `install_tier`, `install_verified`, and `skills_root`.

## Known quirks

- (none / list any)

## Author of this adapter

`@<your-github-handle>` — opened in PR #N

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.