The Deep Agents CLI stores data in two directory hierarchies:
~/.deepagents/ — Deep Agents-specific data (agent memory, skills, sessions)~/.agents/ — Tool-agnostic data (skills shared across AI CLI tools)
Directory Structure
~/.deepagents/
├── sessions.db # SQLite database for conversation checkpoints
├── history.jsonl # Command input history
└── {agent}/ # Per-agent directory (default: "agent")
├── AGENTS.md # User customizations to agent instructions
├── skills/ # User-level skills
│ └── {skill-name}/
│ └── SKILL.md
└── agents/ # Custom subagent definitions
└── {subagent-name}/
└── AGENTS.md
~/.agents/ # Tool-agnostic alias (shared across AI CLIs)
└── skills/ # Skills available to any compatible tool
└── {skill-name}/
└── SKILL.md
{project}/ # Project-level (in git repo root)
├── AGENTS.md # Project instructions (root-level)
└── .deepagents/
│ ├── AGENTS.md # Project instructions (preferred location)
│ ├── skills/ # Project-specific skills
│ │ └── {skill-name}/
│ │ └── SKILL.md
│ └── agents/ # Project-specific subagents
│ └── {subagent-name}/
│ └── AGENTS.md
└── .agents/ # Tool-agnostic project skills
└── skills/
└── {skill-name}/
└── SKILL.md
What Goes Where
| Data | Location | Read/Write | Notes |
|---|
| Sessions | ~/.deepagents/sessions.db | R/W | SQLite checkpoint database |
| Input history | ~/.deepagents/history.jsonl | R/W | JSON-lines, up/down arrow recall |
| Base instructions | Package default_agent_prompt.md | R | Immutable, updated with CLI upgrades |
| User customizations | ~/.deepagents/{agent}/AGENTS.md | R/W | Appended to base instructions |
| Project instructions | .deepagents/AGENTS.md or AGENTS.md | R | Both loaded if present |
| User skills | ~/.deepagents/{agent}/skills/ | R/W | Agent-specific skills |
| Shared skills | ~/.agents/skills/ | R | Tool-agnostic, cross-CLI |
| Project skills | .deepagents/skills/ or .agents/skills/ | R | Project-scoped |
| Custom subagents | ~/.deepagents/{agent}/agents/ | R/W | User-defined subagents |
| Project subagents | .deepagents/agents/ | R | Project-defined subagents |
Precedence Rules
When the same item exists in multiple locations, higher precedence wins completely (no merging).
Skills
Precedence order (lowest to highest):
~/.deepagents/{agent}/skills/ — User deepagents~/.agents/skills/ — User tool-agnostic.deepagents/skills/ — Project deepagents.agents/skills/ — Project tool-agnostic (highest)
When a skill is loaded, the CLI verifies that the resolved file path stays within one of these directories. Symlinks that resolve outside all skill roots are rejected. To allow symlink targets in additional directories, see [skills].extra_allowed_dirs.
Subagents
Precedence order (lowest to highest):
~/.deepagents/{agent}/agents/ — User-level.deepagents/agents/ — Project-level (highest)
Each subagent is an AGENTS.md file with YAML frontmatter (name, description, optional model) and a markdown body for the system prompt. See Custom subagents for the full format reference.
Instructions
All instruction sources are combined (not overridden):
- Package base prompt (always loaded)
~/.deepagents/{agent}/AGENTS.md (appended).deepagents/AGENTS.md (appended)AGENTS.md at project root (appended)
.deepagents vs .agents
| Directory | Purpose | When to use |
|---|
.deepagents/ | Deep Agents CLI-specific | Skills and config that use CLI-specific features |
.agents/ | Tool-agnostic | Skills you want to share across different AI CLI tools |
Use .agents/skills/ for skills that work with any AI coding assistant.
Use .deepagents/skills/ for skills that rely on Deep Agents-specific tools or conventions.
Cleaning Up
| Need | Action |
|---|
| Reset all data | rm -rf ~/.deepagents |
| Clear sessions only | rm ~/.deepagents/sessions.db |
| Clear input history | rm ~/.deepagents/history.jsonl |
| Reset agent instructions | deepagents agents reset --agent {name} |
| Remove a skill | rm -rf ~/.deepagents/{agent}/skills/{skill-name} |
Deleting ~/.deepagents/sessions.db will remove all conversation history and checkpoints.
This cannot be undone.
