搜索

PythonReactSEOPDF
OpenClaw

session-memory

Write session summaries to daily memory files and search session history so OpenClaw can recall and cite past conversations.

breezezephyr0 来源安装数☆ 0 仓库 Starsv1.0.0

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求,再添加到工作流。

SkillHub CLI

skillhub install breezezephyr/session-memory-workspace

打开来源仓库,查看说明和兼容环境后,按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent,让它先读取说明、核对依赖,并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

session-memory

Use this skill when the user asks to remember yesterday’s (or a date’s) chat, to summarize a day’s sessions into memory, or to search past conversations (by keyword or date). It bridges session logs and the memory store so OpenClaw can answer “what did we talk about on …?” and use session context in replies.

When to use

  • User asks: “把昨天的聊天记到记忆里” / “总结一下 2 月 27 日的对话并写入 memory”
  • User asks: “查一下之前我们说过关于 XXX 的对话” / “搜索会话里关于 discord/股票 的内容”
  • User wants past chats to be searchable via memory/citations → run the summarize script for that day first, then normal memory search will include it.

Paths (default agent)

  • Sessions: ~/.openclaw/agents/main/sessions/
    • sessions.json = index; <session-id>.jsonl = full transcript.
  • Memory: <workspace>/memory/
    • Daily file: memory/YYYY-MM-DD.md. Create or append a ## Session summary section.

Run scripts from the workspace root (e.g. ~/.openclaw/workspace), or pass --workspace so memory/ is resolved correctly.

1. Summarize a day’s sessions → memory (session-to-memory)

Writes a session summary for the given date into memory/YYYY-MM-DD.md (creates the file or appends a section). Memory citations and RAG will then include that day’s chat.

node skills/session-memory/scripts/session-to-memory.js --date YYYY-MM-DD

Optional:

  • --date YYYY-MM-DD — date to summarize (default: yesterday in local time).
  • --workspace /path/to/workspace — workspace root; memory dir is <workspace>/memory (default: cwd or ~/.openclaw/workspace).
  • --sessions-dir /path — override sessions dir (default: ~/.openclaw/agents/main/sessions).
  • --append — append a “Session summary” section if the file exists; otherwise replace (default: append).
  • --max-messages 200 — cap messages per session when building summary (default: 200).

Example:

cd ~/.openclaw/workspace
node skills/session-memory...

来源信息

Source
github
Repository
openclaw/skills
Path
skills/breezezephyr/session-memory-workspace
Version
1.0.0
Commit
6450bd95c87265eac46accb3d8bc62d97b107296
分类来源
rules
状态
active
可见性
public

这些信息来自收录时的来源分析,可能滞后;使用前请核对最新来源文件。

README

session-memory

OpenClaw skill: write session summaries into daily memory files and search session history so the agent can recall and cite past conversations.

Features

  • Session → memory: Run session-to-memory.js for a date to generate or update memory/YYYY-MM-DD.md with a "Session summary" section. OpenClaw’s memory/citation search will then include that day’s chat.
  • Session search: Run session-search.js with a query (and optional date range) to get JSON snippets from past sessions. Use this to answer “what did we say about X?” or to prepare context.

Requirements

  • Node.js (no extra npm deps)
  • Sessions at ~/.openclaw/agents/main/sessions/ (default agent)
  • Workspace with memory/ directory (e.g. ~/.openclaw/workspace/memory/)

Usage (agent)

From the workspace root:

# Summarize 2026-02-27 into memory/2026-02-27.md
node skills/session-memory/scripts/session-to-memory.js --date 2026-02-27 --append

# Search sessions for "discord"
node skills/session-memory/scripts/session-search.js --query "discord" --since 2026-02-26 --limit 10

See SKILL.md for full usage and when the agent should use this skill.

Version

1.0.0

来源内容

SKILL.md
# session-memory

Use this skill when the user asks to **remember yesterday’s (or a date’s) chat**, to **summarize a day’s sessions into memory**, or to **search past conversations** (by keyword or date). It bridges session logs and the memory store so OpenClaw can answer “what did we talk about on …?” and use session context in replies.

## When to use

- User asks: “把昨天的聊天记到记忆里” / “总结一下 2 月 27 日的对话并写入 memory”
- User asks: “查一下之前我们说过关于 XXX 的对话” / “搜索会话里关于 discord/股票 的内容”
- User wants past chats to be **searchable via memory/citations** → run the summarize script for that day first, then normal memory search will include it.

## Paths (default agent)

- **Sessions**: `~/.openclaw/agents/main/sessions/`  
  - `sessions.json` = index; `<session-id>.jsonl` = full transcript.
- **Memory**: `<workspace>/memory/`  
  - Daily file: `memory/YYYY-MM-DD.md`. Create or append a `## Session summary` section.

Run scripts from the **workspace root** (e.g. `~/.openclaw/workspace`), or pass `--workspace` so `memory/` is resolved correctly.

## 1. Summarize a day’s sessions → memory (session-to-memory)

Writes a **session summary** for the given date into `memory/YYYY-MM-DD.md` (creates the file or appends a section). Memory citations and RAG will then include that day’s chat.

```bash
node skills/session-memory/scripts/session-to-memory.js --date YYYY-MM-DD
```

Optional:

- `--date YYYY-MM-DD` — date to summarize (default: yesterday in local time).
- `--workspace /path/to/workspace` — workspace root; memory dir is `<workspace>/memory` (default: cwd or `~/.openclaw/workspace`).
- `--sessions-dir /path` — override sessions dir (default: `~/.openclaw/agents/main/sessions`).
- `--append` — append a “Session summary” section if the file exists; otherwise replace (default: append).
- `--max-messages 200` — cap messages per session when building summary (default: 200).

Example:

```bash
cd ~/.openclaw/workspace
node skills/session-memory...
README
# session-memory

OpenClaw skill: write session summaries into daily memory files and search session history so the agent can recall and cite past conversations.

## Features

- **Session → memory**: Run `session-to-memory.js` for a date to generate or update `memory/YYYY-MM-DD.md` with a "Session summary" section. OpenClaw’s memory/citation search will then include that day’s chat.
- **Session search**: Run `session-search.js` with a query (and optional date range) to get JSON snippets from past sessions. Use this to answer “what did we say about X?” or to prepare context.

## Requirements

- Node.js (no extra npm deps)
- Sessions at `~/.openclaw/agents/main/sessions/` (default agent)
- Workspace with `memory/` directory (e.g. `~/.openclaw/workspace/memory/`)

## Usage (agent)

From the workspace root:

```bash
# Summarize 2026-02-27 into memory/2026-02-27.md
node skills/session-memory/scripts/session-to-memory.js --date 2026-02-27 --append

# Search sessions for "discord"
node skills/session-memory/scripts/session-search.js --query "discord" --since 2026-02-26 --limit 10
```

See `SKILL.md` for full usage and when the agent should use this skill.

## Version

1.0.0

相关技能

OpenClaw

ai-maestro

23blocks-os

AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agent-to-agent messaging. Manage Claude, Codex or any AI Agent from one dashboard. Move Agents between c...

OpenClaw

registry-broker-skills

hashgraph-online

AI agent skills for the Universal Registry - search, chat, and register 72,000+ agents across 14+ protocols. Works with Claude, Codex, Cursor, OpenClaw, and any AI assistant.

OpenClaw

skills-manager

rito-w

A cross-platform skills manager for AI IDEs. Search marketplace, download locally, and install to Claude, Cursor, Windsurf, and more with one click.