Xpersona
agentCLAWHUBUnverified

hermes agent skill

突触式多智能体调度 + 主动记忆洞察 + GEPA 技能自进化 Skill: hermes agent skill Owner: briefness Summary: 突触式多智能体调度 + 主动记忆洞察 + GEPA 技能自进化 Tags: latest:1.0.3 Version history: v1.0.3 | 2026-04-17T08:22:51.747Z | user - Introduced a new hermes_config.py module for global configuration and privacy controls. - Added support for fully disabling persistence by default; data storage is now opt-in and user-controllable. - Enhanced privacy: defaults, docs, and structure updated t

OpenClaw
View on ClawHubHomepage

Rank

62

Safety

84

Downloads

1.5k

Updated

Oct 10, 2026

Version

1.0.3

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.5K 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
1.5K downloadsadoption · observed Oct 10, 2026
Latest release
1.0.3release · observed Apr 17, 2026
Handshake status
UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17fk50xgzfn3652z9b7awhjan8503tn:hermes-agent-skill
  1. Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
  2. 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-briefness-hermes-agent-skill/snapshot"

Documentation

CLAWHUB

18,457 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: Hermes Agent
description: 突触式多智能体调度 + 主动记忆洞察 + GEPA 技能自进化
author: OpenClaw
version: 1.0.3
tags: [hermes, multi-agent, scheduling, memory, evolution]
---

# Hermes Agent Skill

> Hermes 协议：极致的"执行效率"与"自我进化"

## 功能特性

- 🧠 **突触式多智能体调度**：100个Agent同时协同，通信成本降到最低，毫秒级分发
- 🧩 **主动记忆与自我建模**：自动提取用户偏好习惯，SQLite FTS5 全文检索快速翻旧账
- 🧬 **GEPA 技能自进化**：多次执行后自动提炼技能卡，越用越聪明
- ⚡ **极致轻量**：纯Python，零依赖，启动快内存占用低
- 🔧 **工程化友好**：完美集成 `sessions_spawn`，开箱即用
- 🔒 **隐私优先**：持久化默认关闭，数据存储完全可控

## 安装

在 OpenClaw 中：
```
/install-skill https://github.com/你的仓库/hermes-agent-skill
```

或者手动放到 `~/.openclaw/workspace/skills/` 即可。

## 快速开始

### 1. 导入

```python
from hermes_agent import (
    hermes,                 # 核心路由器
    hermes_workflow,        # 工作流调度
    hermes_sessions,        # sessions_spawn 集成
    hermes_insight,         # 记忆洞察数据库
    insight_extractor,      # 洞察提取器
    hermes_gepa,            # GEPA 技能进化
    hermes_skill_executor,  # 带自进化的执行器
    hermes_config           # 全局配置（控制持久化开关）
)
```

### 2. 多智能体任务分发

```python
# spawn 子智能体之后，自动注册 Hermes 订阅
hermes_sessions.on_agent_spawn(
    session_key="session-code-agent",
    agent_id="code-review-agent",
    hermes_topics=["task:code-review"]
)

# 提交任务，自动分发给所有订阅了该类型的 Agent
task_id = hermes_sessions.submit_task_to_agents(
    task_type="code-review",
    creator="user",
    session_id="main",
    payload={"pr": "https://github.com/openclaw/openclaw/pull/123"}
)
```

### 3. 主动记忆用户洞察

```python
# 从对话提取洞察
insights = insight_extractor.extract_from_conversation(
    "我喜欢用 Python 写脚本，更快，不喜欢重型框架",
    context="对话上下文"
)

# 存储
for ins in insights:
    hermes_insight.add_insight(ins)

# 全文检索
results = hermes_insight.search_memory("Python")
```

### 4. GEPA 技能自进化

```python
# 开始任务，自动记录
exec_id = hermes_skill_executor.start_task(
    "video-clip",
    {"input": "input.mp4", "start": 10, "end": 20}
)

# 一步一步执行，自动记录
hermes_skill_executor.step("load-video", load_video, path)
hermes_skill_executor.step("cut-segment", cut, start, end)
result = hermes_skill_executor.step("export-video", export, output)

# 完成，自动触发提炼
hermes_skill_executor.finish_task(True, result)

# 几次之后自动生成技能卡
skill = hermes_gepa.get_skill_card("video-clip")
print(f"推荐步骤: {skill.steps}")
print(f"成功率: {skill.success_rate:.1%}")
```

## 架构

```
hermes.py                     # 核心路由器（突触式通信）
├─ hermes_config.py           # 全局配置（持久化开关、隐私控制）
├─ hermes_openclaw.py         # 工作流调度（任务/进度/完成）
├─ hermes_sessions_integration.py  # sessions_spawn 自动集成
├─ hermes_agent_insight.py    # 主动记忆 + FTS5 全文检索
└─ hermes_skill_evolution.py  # GEPA 技能自进化
```

## 控制参数（避免 token 浪费）

GEPA 默认参数：
- `min_success_samples = 2`  - 最少 2 次成功才提炼
- `min_new_executions = 3`   - 已有技能后新增 3 次才重新提炼
- `max_refines_per_task = 10` - 单个任务最多提炼 10 次
- `min_improvement = 0.05`   - 成功率变化 < 5% 不提炼

自定义：
```python
from hermes_skill_evolution import GEPASkillEvolution
my_gepa = GEPASkillEvolution(
    min_success_samples=5,
    max_refines_per_task=5
)
```

## 数据存储

**默认关闭，需显式开启。**

```
# 方式一：环境变量
export HERMES_PERSISTENCE_ENABLE

_meta.json

{
  "ownerId": "kn71zja160wvka1tfd4j7sj8fx82m9nm",
  "slug": "hermes-agent-skill",
  "version": "1.0.3",
  "publishedAt": 1776414171747
}

skill-card.md

## Description:

Hermes Agent Skill helps OpenClaw agents coordinate work through topic-based routing, session integration, opt-in memory search, and GEPA-style workflow summaries.

This skill is ready for commercial/non-commercial use.

## Publisher:

[briefness](https://clawhub.ai/user/briefness)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agent builders use this skill to coordinate multiple OpenClaw subagents, distribute task events, track progress, search optional local memory, and summarize repeated successful workflows into reusable skill cards.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Shared agent routing and session integration can expose sensitive task payloads, tags, metadata, or step results across agents.

Mitigation: Review before installing in mixed-trust environments, avoid secrets in task data, and use the skill only with agents and sessions that are intended to share this information.

Risk: When persistence is enabled, local ~/.hermes databases can retain sensitive memory and execution data.

Mitigation: Keep persistence disabled unless needed, leave sensitive filtering enabled, and treat the local databases as sensitive files.

## Reference(s):

- [ClawHub Skill Page](https://clawhub.ai/briefness/skills/hermes-agent-skill)
- [Publisher Profile](https://clawhub.ai/user/briefness)

## Skill Output:

**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]

**Output Format:** [Markdown guidance with Python code examples and environment-variable configuration.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [May create local SQLite databases under ~/.hermes only when persistence is explicitly enabled.]

## Skill Version(s):

1.0.3 (source: server release metadata and SKILL.md frontmatter)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Related agents

Same protocol, similar job.

Github ReposUpdated 16h 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.

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/briefness/skills/hermes-agent-skill",
      "sourceUrl": "https://clawhub.ai/briefness/skills/hermes-agent-skill",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-10T09:26:54.940Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-briefness-hermes-agent-skill/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-briefness-hermes-agent-skill/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-10T09:26:54.940Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "1.5K downloads",
      "href": "https://clawhub.ai/briefness/hermes-agent-skill",
      "sourceUrl": "https://clawhub.ai/briefness/hermes-agent-skill",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-10T09:26:54.940Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "1.0.3",
      "href": "https://clawhub.ai/briefness/hermes-agent-skill",
      "sourceUrl": "https://clawhub.ai/briefness/hermes-agent-skill",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-04-17T08:22:51.747Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-briefness-hermes-agent-skill/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-briefness-hermes-agent-skill/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 1.0.3",
      "description": "- Introduced a new `hermes_config.py` module for global configuration and privacy controls. - Added support for fully disabling persistence by default; data storage is now opt-in and user-controllable. - Enhanced privacy: defaults, docs, and structure updated to clarify sensitive data handling and storage options. - Updated documentation to include new architecture file, usage, and environment variable configuration examples. - Minor version bump to 1.0.3.",
      "href": "https://clawhub.ai/briefness/hermes-agent-skill",
      "sourceUrl": "https://clawhub.ai/briefness/hermes-agent-skill",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-04-17T08:22:51.747Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 10, 2026.

Sponsored

Ads related to hermes agent skill and adjacent AI workflows.