mirror of
https://github.com/zhayujie/chatgpt-on-wechat.git
synced 2026-07-21 22:27:13 +08:00
docs: init docs
This commit is contained in:
68
docs/en/memory.mdx
Normal file
68
docs/en/memory.mdx
Normal file
@@ -0,0 +1,68 @@
|
||||
---
|
||||
title: Memory
|
||||
description: CowAgent long-term memory system
|
||||
---
|
||||
|
||||
# Long-term Memory
|
||||
|
||||
The memory system enables the Agent to remember important information over time, continuously accumulating experience, understanding user preferences, and achieving autonomous thinking and growth.
|
||||
|
||||
## How It Works
|
||||
|
||||
The Agent proactively stores memory in these scenarios:
|
||||
|
||||
- **When users share important information** — Automatically identifies and stores preferences, decisions, facts, and other key information
|
||||
- **When conversations reach a certain length** — Automatically extracts summaries to prevent information loss
|
||||
- **When retrieval is needed** — Intelligently searches historical memory and combines it with context
|
||||
|
||||
## Memory Types
|
||||
|
||||
### Core Memory
|
||||
|
||||
Stored in `~/cow/memory/core.md`, containing long-term user preferences, important decisions, key facts, and other information that doesn't fade over time.
|
||||
|
||||
### Daily Memory
|
||||
|
||||
Stored in the `~/cow/memory/daily/` directory, organized by date, recording daily conversation summaries and key events.
|
||||
|
||||
## First Startup
|
||||
|
||||
On first startup, the Agent proactively asks the user for key information and records it in the workspace (default `~/cow`):
|
||||
|
||||
| File | Description |
|
||||
| --- | --- |
|
||||
| `system.md` | Agent system prompt and behavior settings |
|
||||
| `user.md` | User identity and preferences |
|
||||
| `memory/core.md` | Core memory |
|
||||
| `memory/daily/` | Daily memory directory |
|
||||
|
||||
<Frame>
|
||||
<img src="https://cdn.link-ai.tech/doc/20260203000455.png" width="800" />
|
||||
</Frame>
|
||||
|
||||
## Memory Retrieval
|
||||
|
||||
The memory system supports hybrid retrieval:
|
||||
|
||||
- **Keyword Search** — Matches historical memory based on keywords
|
||||
- **Vector Search** — Semantic similarity search that finds related memories even with different wording
|
||||
|
||||
The Agent automatically triggers memory retrieval during conversations, incorporating relevant historical information into the context.
|
||||
|
||||
## Configuration
|
||||
|
||||
Adjust memory-related parameters in `config.json`:
|
||||
|
||||
```json
|
||||
{
|
||||
"agent_workspace": "~/cow",
|
||||
"agent_max_context_tokens": 40000,
|
||||
"agent_max_context_turns": 30
|
||||
}
|
||||
```
|
||||
|
||||
| Parameter | Description | Default |
|
||||
| --- | --- | --- |
|
||||
| `agent_workspace` | Workspace path where memory files are stored | `~/cow` |
|
||||
| `agent_max_context_tokens` | Maximum context tokens, affects short-term memory capacity | `40000` |
|
||||
| `agent_max_context_turns` | Maximum context turns, older conversations are discarded when exceeded | `30` |
|
||||
Reference in New Issue
Block a user