How It Works
The Agent proactively stores memory in the following scenarios:- When user shares important information — Automatically identifies and stores preferences, decisions, facts, and other key information
- When conversation reaches a certain length — Automatically extracts summaries to prevent information loss
- When retrieval is needed — Intelligently searches historical memory, combining context for responses
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~/cow/memory/daily/ directory, organized by date, recording daily conversation summaries and key events.
First Launch
On first launch, the Agent will proactively ask the user for key information and save it to the workspace (default~/cow):
| File | Description |
|---|---|
system.md | Agent system prompt and behavior settings |
user.md | User identity information and preferences |
memory/core.md | Core memory |
memory/daily/ | Daily memory directory |

Memory Retrieval
The memory system supports hybrid retrieval modes:- Keyword retrieval — Match historical memory based on keywords
- Vector retrieval — Semantic similarity search, finds relevant memory even with different wording
Configuration
| Parameter | Description | Default |
|---|---|---|
agent_workspace | Workspace path, memory files stored under this directory | ~/cow |
agent_max_context_tokens | Max context tokens, affects short-term memory capacity | 40000 |
agent_max_context_turns | Max context turns, oldest conversations discarded when exceeded | 30 |
