mirror of
https://github.com/pocketpaw/pocketpaw.git
synced 2026-05-21 09:14:59 +00:00
57b807c117
Comprehensive SEO optimization across 80 documentation pages: Title optimization (all pages): - Replaced generic titles like "Architecture", "Discord", "Slack" with search-intent titles like "PocketPaw Architecture: Event-Driven Message Bus", "Discord Bot Setup: Add PocketPaw to Your Server" - All titles now 50-70 characters with qualifying keywords Meta descriptions: - Expanded 7 short descriptions (under 145 chars) to 150-160 chars - Roadmap description expanded from 76 to 196 chars - Troubleshooting, Codex CLI, OpenCode, WebMCP all expanded H1 heading fixes: - Ensured single H1 per page matching the frontmatter title - All H1 headings updated to match new optimized titles Internal cross-links: - Added Related CardGroup sections to 60+ individual pages - Each links to 2-3 related pages within and across sections - Channels link to channel guides, backends link to Ollama guide, etc. Em dash cleanup: - Replaced em dashes with colons, periods, or double hyphens across multiple files in tools/, channels/, integrations/ Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
127 lines
3.8 KiB
Plaintext
127 lines
3.8 KiB
Plaintext
---
|
|
title: "PocketPaw Memory: Sessions & Long-Term Storage"
|
|
description: "PocketPaw's two-tier memory system combines file-based session storage for conversation history with optional Mem0 semantic memory for auto-learned long-term knowledge."
|
|
section: Core Concepts
|
|
ogType: article
|
|
keywords: ["memory architecture", "session storage", "semantic memory", "mem0", "knowledge base"]
|
|
tags: ["memory", "architecture"]
|
|
---
|
|
|
|
# PocketPaw Memory: Sessions & Long-Term Storage
|
|
|
|
PocketPaw has a two-tier memory system: **file-based session storage** for conversation history, and optional **Mem0 semantic memory** for long-term recall.
|
|
|
|
## Session Storage (File Store)
|
|
|
|
The default memory backend stores sessions as JSON files in `~/.pocketpaw/memory/`:
|
|
|
|
```
|
|
~/.pocketpaw/memory/
|
|
├── _index.json # Session index (titles, timestamps)
|
|
├── session_abc123.json # Individual session files
|
|
├── session_def456.json
|
|
└── ...
|
|
```
|
|
|
|
### Session Index
|
|
|
|
The `_index.json` file provides fast lookups without reading every session file:
|
|
|
|
```json
|
|
{
|
|
"session_abc123": {
|
|
"title": "Python script for prime numbers",
|
|
"created_at": "2024-01-15T10:30:00Z",
|
|
"updated_at": "2024-01-15T11:45:00Z",
|
|
"message_count": 12,
|
|
"channel": "web"
|
|
}
|
|
}
|
|
```
|
|
|
|
The index supports:
|
|
- **Searching** sessions by title or content
|
|
- **Listing** recent sessions
|
|
- **Grouping** sessions by time (Today, Yesterday, This Week, etc.)
|
|
- **Auto-rebuild** if the index is missing or corrupted
|
|
|
|
### Session Files
|
|
|
|
Each session file contains the full conversation history:
|
|
|
|
```json
|
|
{
|
|
"session_id": "session_abc123",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "Write a Python script for prime numbers",
|
|
"timestamp": "2024-01-15T10:30:00Z"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "Here's a Python script...",
|
|
"timestamp": "2024-01-15T10:30:15Z"
|
|
}
|
|
],
|
|
"facts": ["User prefers Python", "Uses Linux"],
|
|
"metadata": {
|
|
"channel": "web",
|
|
"agent_backend": "claude_agent_sdk"
|
|
}
|
|
}
|
|
```
|
|
|
|
## Mem0 Semantic Memory
|
|
|
|
For long-term recall, PocketPaw integrates with [Mem0](https://mem0.ai) — a semantic memory layer that learns from conversations.
|
|
|
|
### How It Works
|
|
|
|
1. **Auto-learn**: After each agent response, PocketPaw feeds the conversation to Mem0 in a background task
|
|
2. **Semantic search**: When building context for a new message, Mem0 is queried to find relevant memories
|
|
3. **Context injection**: Matching memories are injected into the system prompt
|
|
|
|
### Configuration
|
|
|
|
```bash
|
|
# Enable auto-learning
|
|
export POCKETPAW_MEM0_AUTO_LEARN=true
|
|
|
|
# LLM provider for Mem0's processing
|
|
export POCKETPAW_MEM0_LLM_PROVIDER="ollama"
|
|
export POCKETPAW_MEM0_LLM_MODEL="llama3.2"
|
|
|
|
# Embedder for semantic search
|
|
export POCKETPAW_MEM0_EMBEDDER_PROVIDER="ollama"
|
|
export POCKETPAW_MEM0_EMBEDDER_MODEL="nomic-embed-text"
|
|
|
|
# Vector store
|
|
export POCKETPAW_MEM0_VECTOR_STORE="qdrant"
|
|
```
|
|
|
|
### Supported Providers
|
|
|
|
| Component | Providers |
|
|
|-----------|-----------|
|
|
| LLM | Ollama, Anthropic, OpenAI |
|
|
| Embedder | Ollama, OpenAI |
|
|
| Vector Store | Qdrant (default), Chroma |
|
|
|
|
<Callout type="info">
|
|
If using Ollama as the LLM provider for Mem0, no API key is needed. This is the recommended setup for fully local operation.
|
|
</Callout>
|
|
|
|
## Context Building
|
|
|
|
The `AgentContextBuilder` assembles the agent's context from multiple sources:
|
|
|
|
1. **Identity** — System prompt with agent personality and capabilities
|
|
2. **User profile** — From `~/.pocketpaw/identity/USER.md`
|
|
3. **Session history** — Recent messages from the current session
|
|
4. **Long-term facts** — Extracted facts from previous sessions
|
|
5. **Semantic memories** — Relevant memories from Mem0 (based on the current query)
|
|
6. **Skills** — Loaded skill definitions from `~/.claude/skills/` (and legacy paths)
|
|
|
|
The context builder ensures the total context fits within the model's context window by truncating older messages first.
|