Import from Other Agents

hermes import-agent imports your existing OpenClaw, Claude Code, OpenAI Codex CLI or Cursor setup into Hermes with one command. You always see a per-item plan before anything is written, and --dry-run never touches disk.

The command comes from the official agent-importers plugin from the plugin catalog, maintained by Nous Research in NousResearch/hermes-official-plugins.

The easy way: hermes setup

On a fresh install, hermes setup checks for ~/.openclaw (or legacy ~/.clawdbot / ~/.moltbot), ~/.claude, ~/.codex and ~/.cursor before anything else. When it finds one it asks "Import your setup from Claude Code?" (naming what it found); with several found you then pick which from a checklist, all checked. Say yes and setup installs the agent-importers plugin from the catalog, unless you already have it, and runs the import below for each pick, preview and confirmation included. For OpenClaw it passes --migrate-secrets, as Hermes' old built-in OpenClaw step did, so your API keys and bot tokens come over and the provider and messaging sections that follow are already filled in. If you then pick Quick Setup and the import brought a model along with its key, setup asks whether to keep that model (the default) or switch to Nous Portal. Say no, or have none of these folders, and nothing is installed. Already set up? Use the commands below.

By hand

Install the plugin once per profile:

hermes plugins install agent-importers

hermes import-agent                    # auto-detect ~/.openclaw, ~/.claude, ~/.codex or ~/.cursor
hermes import-agent openclaw           # import from ~/.openclaw (see the OpenClaw guide)
hermes import-agent claude-code        # import from ~/.claude
hermes import-agent codex              # import from ~/.codex
hermes import-agent cursor             # import from ~/.cursor
hermes import-agent claude-code --dry-run          # preview only
hermes import-agent codex --source /path/to/.codex # custom location
hermes import-agent claude-code --overwrite --yes  # replace conflicts, skip prompts

What gets imported

OpenClaw (~/.openclaw)

OpenClaw has its own guide, Migrate from OpenClaw, with the full mapping (persona, memory, skills, model providers, messaging platforms, agent behaviour, MCP servers and more), the --preset, --migrate-secrets, --workspace-target and --skill-conflict flags, the pre-migration backup and hermes claw cleanup. The older spelling hermes claw migrate still works and runs the same import.

Claude Code (~/.claude)

Claude Code	Hermes
CLAUDE.md (global instructions)	Memory entries in ~/.hermes/memories/MEMORY.md
settings.json → permissions.allow (Bash(...) rules)	command_allowlist in config.yaml
settings.json → permissions.deny (Bash(...) rules)	approvals.deny in config.yaml
mcpServers (from ~/.claude.json and settings.json)	mcp_servers in config.yaml
skills/<name>/ (dirs with SKILL.md)	~/.hermes/skills/claude-code-imports/<name>/
commands/*.md (slash commands)	Skipped with a note — convert them into skills

Claude's Bash(npm run test:*) prefix rules become npm run test* globs. Non-Bash permission rules (Read(...), WebFetch, ...) gate Claude-specific tools and are reported as unmapped rather than imported.

Codex CLI (~/.codex)

Codex CLI	Hermes
AGENTS.md (global instructions)	Memory entries in ~/.hermes/memories/MEMORY.md
config.toml → [mcp_servers.*]	mcp_servers in config.yaml
memories/*.md	Memory entries in ~/.hermes/memories/MEMORY.md
skills/<name>/ (dirs with SKILL.md)	~/.hermes/skills/codex-imports/<name>/

Cursor (~/.cursor)

Cursor	Hermes
AGENTS.md (global instructions)	Memory entries in ~/.hermes/memories/MEMORY.md
rules/*.md, rules/*.mdc (User Rules)	Memory entries in ~/.hermes/memories/MEMORY.md
mcp.json → mcpServers	mcp_servers in config.yaml
skills/**/<name>/ (dirs with SKILL.md, category folders allowed)	~/.hermes/skills/cursor-imports/<name>/

.mdc frontmatter (description, globs, alwaysApply) is routing metadata for Cursor's rule engine and is stripped; only the rule body is imported. A skill is the folder holding SKILL.md, so skills/shipping/land-it/ imports as cursor-imports/land-it/; two skills with the same name in different folders are reported as a conflict.

What is never imported

API keys and credentials. (OpenClaw is the one exception: its allowlisted API keys and bot tokens come over only when you pass --migrate-secrets.) Credential files (~/.claude/.credentials.json, ~/.codex/auth.json, ~/.cursor/cli-config.json) are never read, and MCP server environment variables or headers with secret-looking names (*_TOKEN, *_API_KEY, Authorization, ...) are stripped and listed in the report so you can re-add them deliberately. Run hermes setup to configure providers, or add secrets to ~/.hermes/.env.

Behavior notes

• Preview first, always. The command prints the full plan before applying; in non-interactive sessions it stops at the preview unless you pass --yes.
• Merges, not replaces. Memory entries are deduplicated against your existing MEMORY.md; allowlist/denylist patterns merge with what's already in config.yaml.
• Conflicts are skipped by default. An MCP server or skill that already exists in Hermes is reported as a conflict; pass --overwrite to replace it.
• Malformed files don't abort the run. A broken settings.json or config.toml becomes a per-item error in the report while everything else still imports.

Keeping imports in sync

Every successful Claude Code, Codex CLI or Cursor import registers its source (and the digest of everything it read) in ~/.hermes/import-sync.json. When the other agent's setup changes later — new skills, edited CLAUDE.md/AGENTS.md, added MCP servers — pull the changes in with:

hermes import-agent --sync            # re-import every changed source
hermes import-agent --sync --dry-run  # preview what a sync would do

Sync is prompt-free and cheap: sources whose files are unchanged are skipped by digest comparison, so it is safe to run on a schedule (e.g. a daily cron job). Rules:

• Memory and config merges stay deduplicating — a sync never duplicates entries or patterns you already have.
• Skills previously imported by import-agent are refreshed in place when the source copy changes.
• Skills you created or modified under the import category yourself are never clobbered — they keep normal conflict semantics (use --overwrite on a manual run to force).
• Credential files never trigger a sync — token refreshes in ~/.claude/.credentials.json or ~/.codex/auth.json are ignored by the digest, and secrets are still stripped from anything imported.

This mirrors ChatGPT Work's Settings > Import automatic updates, adapted to an explicit, inspectable command instead of a background service.

The manifest is per profile. A profile created with hermes profile create <name> --clone --sync-imports carries it over, so hermes -p <name> import-agent --sync keeps pulling from the same external trees (see Profiles).

Upgrading from a version with import-agent built in

hermes import-agent and hermes claw used to ship inside Hermes core. The commands, their flags and the import-sync.json manifest are unchanged in the plugin:

• Profiles with a registered sync source (an import-sync.json, which scheduled --sync runs read) get the plugin installed automatically by hermes update, or on the first start after updating (this honours security.allow_lazy_installs). If you later remove it (hermes plugins remove agent-importers), it stays removed.
• Everyone else installs it when they next need it: a fresh hermes setup that finds one of these agents offers it, and running hermes import-agent or hermes claw without the plugin prints the install command.