Menú
本地 Mem0 记忆插件安装与故障排查 - Hermes 跨会话记忆系统
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
高德地图综合服务，支持POI搜索、路径规划、旅游规划、周边搜索和热力图数据可视化
Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and sequential image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".
Generate professional infographics with 21 layout types and 21 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics. Use when user asks to create "infographic", "visual summary", "信息图", "可视化", or "高密度信息大图".
Darwin Skill (达尔文.skill): autonomous skill optimizer inspired by Karpathy's autoresearch. Evaluates SKILL.md files using an 8-dimension rubric (structure + effectiveness), runs hill-climbing with git version control, validates improvements through test prompts, and generates visual result cards. Use when user mentions "优化skill", "skill评分", "自动优化", "auto optimize", "skill质量检查", "达尔文", "darwin", "帮我改改skill", "skill怎么样", "提升skill质量", "skill review", "skill打分".
从 DESIGN.md 生成预览图并截图的工作流 - 解决 Playwright 浏览器路径问题和 YAML 解析
Cron jobs auto-deliver final responses to configured targets — send_message to the same target gets deduplicated and skipped. Print report content directly as final response instead.
| name | local-mem0-setup |
| description | 本地 Mem0 记忆插件安装与故障排查 - Hermes 跨会话记忆系统 |
| trigger | local_mem0 启用 / local mem0 安装 / 记忆插件问题 |
/opt/hermes/plugins/memory/local_mem0/
└── __init__.py # 374 行
hermes config set memory.provider local_mem0
# 然后重启 Hermes gateway
问题: 代码尝试导入 HermesState，但实际类名是 SessionDB
位置: /opt/hermes/plugins/memory/local_mem0/__init__.py 第 170-171 行
修复:
# 错误
from hermes_state import HermesState
self._db = HermesState()
# 正确
from hermes_state import SessionDB
self._db = SessionDB()
问题: v8 迁移代码存在，但 memories 表未创建
症状: search_memories 返回 "no such table: memories"
修复: 手动创建表
import sqlite3
conn = sqlite3.connect('/opt/data/hermes/state.db')
cursor = conn.cursor()
cursor.execute('''
CREATE TABLE IF NOT EXISTS memories (
id INTEGER PRIMARY KEY AUTOINCREMENT,
content TEXT NOT NULL,
vector BLOB NOT NULL,
user_id TEXT DEFAULT 'default',
session_id TEXT,
created_at REAL DEFAULT 0
)
''')
cursor.execute('CREATE INDEX IF NOT EXISTS idx_memories_user ON memories(user_id)')
cursor.execute('CREATE INDEX IF NOT EXISTS idx_memories_created ON memories(created_at)')
conn.commit()
import os
os.environ['HERMES_HOME'] = '/opt/data/hermes'
from plugins.memory.local_mem0 import LocalMem0MemoryProvider
p = LocalMem0MemoryProvider()
# 测试存储
p.handle_tool_call('local_mem0_conclude', {'fact': '测试记忆'})
# 测试搜索
p.handle_tool_call('local_mem0_search', {'query': '测试'})
# 测试查看全部
p.handle_tool_call('local_mem0_profile', {})
| 路径 | 大小 | 用途 |
|---|---|---|
| /opt/data/hermes/state.db | ~70KB | local_mem0 (memories 表) |
| /opt/data/state.db | ~90MB | 历史对话 (messages + message_embeddings) |
local_mem0_search - 语义搜索记忆local_mem0_profile - 查看所有记忆local_mem0_conclude - 手动存储记忆local_mem0_delete - 删除记忆使用 Ollama 的 herald/dmeta-embedding-zh，输出 768 维向量（不是 1024 维）。