Storage Reference

Ante persists configuration and state on the local filesystem. This page is a reference for every location Ante reads or writes.

Locations

Location	Purpose
~/.ante/settings.json	User preferences (model, provider, theme, MCP servers)
~/.ante/catalog.json	Custom provider/model catalog
~/.ante/AGENTS.md	Global instructions injected into every project session
~/.ante/skills/	User-level skills
~/.ante/agents/	User-level sub-agents
~/.ante/sessions/<session-id>/	Persisted sessions (for /resume and --resume)
~/.ante/projects/<project-id>/memory/	Per-project auto-memory
~/.ante/cache/<project-id>/	Per-project temporary files
~/.ante/tip_history.json	Show history for spinner tips (delete to reset the rotation)
AGENTS.md	Project instructions injected alongside global instructions
.ante/	Project-local configuration (skills, sub-agents)
.agents/, .claude/	Additional project-local skill/sub-agent directories

<project-id> is a sanitized form of the project's absolute path. The ANTE_HOME environment variable overrides ~/.ante.

settings.json

Stores user preferences. All fields are optional.

{
  "model": "claude-sonnet-4-6",
  "provider": "anthropic",
  "theme": "default",
  "permission_mode": "strict",
  "permissions": {
    "allow": ["Bash(npm run *)"],
    "deny": ["Bash(rm *)"]
  },
  "channel": "stable",
  "has_completed_onboarding": true,
  "status_line": ["model-name", "current-dir"],
  "model_effort": {
    "claude-sonnet-4-6": "medium",
    "gpt-5.4": "high"
  },
  "provider_model": {
    "anthropic": "claude-sonnet-4-6"
  },
  "mcp_servers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"]
    }
  }
}

See Preferences for the full field reference and the precedence rules between this file, environment variables, and CLI flags.

catalog.json

Adds or overrides providers and models on top of the built-in catalog. Both top-level keys are optional and keyed by id — the providers map key is the provider id you pass to --provider. An entry whose key matches a built-in (e.g. openai) replaces it, a new key adds a provider, and a models entry patches that model's fields wherever it is defined.

{
  "providers": {
    "my-provider": {
      "display_name": "My Provider",
      "base_url": "https://api.example.com/v1",
      "wire_style": "OpenAiCompatible",
      "auth": { "bearer": { "env_key": "MY_PROVIDER_API_KEY" } }
    }
  },
  "models": {
    "claude-sonnet-4-6": { "effort": "high", "max_tokens": 64000 }
  }
}

Malformed provider or model entries are skipped individually and reported at startup. Valid entries in the same file still load.

See the Catalog Reference for the full schema, authentication forms, and resolution rules, and Providers for customization recipes.

AGENTS.md

Stores persistent instructions for the agent. ~/.ante/AGENTS.md applies globally, and a project AGENTS.md applies to that repository. When both exist, Ante includes both in the first user message of a session.

See AGENTS.md for usage guidance and precedence details.

Layout

User-level (~/.ante/)

~/.ante/
├── settings.json       # User preferences
├── catalog.json        # Custom provider/model catalog
├── AGENTS.md           # Global instructions
├── skills/             # User-level skills
├── agents/             # User-level sub-agents
├── sessions/           # Persisted sessions (for /resume)
├── projects/           # Per-project state (memory, etc.)
│   └── <project-id>/
│       └── memory/
│           └── MEMORY.md
└── cache/              # Per-project temporary files
    └── <project-id>/

Project-local

AGENTS.md               # Project instructions

.ante/
├── skills/             # Project-specific skills
└── agents/             # Project-specific sub-agents

.agents/
├── skills/             # Project-specific skills
└── agents/             # Project-specific sub-agents

.claude/
├── skills/             # Project-specific skills (Claude Code compatibility)
└── agents/             # Project-specific sub-agents (Claude Code compatibility)

Related

• Preferences — full settings.json reference and environment variables
• Catalog Reference — catalog.json schema, built-in providers, and model IDs
• Providers — choosing a provider and customization recipes
• Skills — skill directory layout
• Sub-agents — sub-agent directory layout
• Memory — auto-memory format