Clotho
From its catalog listing
Spin every future of a Hermes task before any of it happens. Every side effect is captured in a ledger instead of performed, you review one report, untick what you don't want, and Apply replays exactly the effects you kept with no model calls. `hermes clotho fork` runs the same task as several timelines under different models, compares their effect ledgers and applies the one you keep; `cron` rehearses a scheduled job; `demo` replays a recorded real fork with no API key.
Good to know before installing
during a rehearsal, read-only tools run for real (file reads and search, skills, session search, web_search, clarify, todo, delegate_task in `hermes clotho run`), so a web search reaches its search provider and may be metered, and a skill_view bumps Hermes' skill usage counters as a normal read does; page fetches (web_extract, vision_analyze and similar) are held. File writes go to an APFS copy-on-write clone of your workspace under <HERMES_HOME>/plugin-data/clotho/; a write or patch to a file outside the workspace works on a copy in a private temp folder that is removed when the rehearsal ends, and the rehearsal keeps only what changed (its diff is made from the live file). A file-tool write, patch, delete or move aimed at a path Hermes' own write guard refuses, inside the workspace or outside it, is refused before anything is copied: the tool does not run, the agent gets Hermes' refusal, and the report shows a BLOCKED row that cannot be applied; that guard is Hermes' credential and system-file deny-list, so a write to Hermes' own config.yaml, which Hermes' file tools refuse separately, is rehearsed on a copy and can be applied if you name it with --only. Shell commands and execute_code run inside that clone under macOS sandbox-exec with no network, no writes outside it and a short allowlist of environment variables, so a rehearsed `env` shows none of the keys Hermes runs with; on Linux, or without sandbox-exec, they are captured without a preview. Messages, web requests, MCP and other plugins' tools, cron changes and memory writes are captured, never run; the agent is told the reply is unknown and carries on, so its final text may say things happened that did not (the report is the truth), and captured calls still fire other plugins' post_tool_call hooks with status ok. Hermes' background memory and skill review can run during a rehearsal and spends model tokens; its writes are captured and cannot be applied. Reads outside the workspace are allowed except Hermes' own read deny-list for file reads, and, for shell commands, a deny-list of credential stores (the SSH, GnuPG, AWS, Kubernetes and Docker folders, the GitHub CLI login, .netrc, git credentials, the keychains, every .env file, and Hermes' own .env and auth.json); the ledger and report store command output and file contents in plain text under plugin-data, so they can hold whatever the rehearsed commands printed. Every effect is ticked by default, messages and web requests included, except tools Clotho does not know, held fetches, commands it cannot preview, and effects outside the workspace (with the whole command that made one), which run only if you name them with --only. Apply runs the kept effects through Hermes' real tools in your terminal, where Hermes auto-approves its own dangerous-command prompt in non-interactive use, so your tick is the approval; a single plain curl or wget call is re-run as that exact command. Apply stops before any change when a file changed since the rehearsal, when a folder on an effect's path became a symlink, or when a ticked effect certainly depends on an unticked one (--force applies anyway); it also stops before any change when an effect would write a path Hermes' own write guard refuses, and --force does not change that. It never re-sends what it already sent. Fail closed: a plugin error during a rehearsal blocks the tool call, and `hermes clotho run` refuses to start the model unless its tool middleware runs ahead of every other middleware, and refuses ACP providers and any Claude-subscription provider whose native tools it cannot verify are off. `/clotho on` in a live session keeps its state in memory only, so a gateway restart or failed plugin reload ends the rehearsal and later calls run for real. `fork` starts one `hermes clotho run` process per timeline at the same time, each making real model calls up to --max-calls. `demo` makes no model calls: it clones Hermes' runtime copy-on-write into a temp folder with no keys, runs a local sink, proxy trap and stand-in model endpoint on 127.0.0.1, and leaves that folder in place. No network calls of its own, no telemetry, no stored credentials. Each rehearsed command's process group is killed when it returns, and so is a child that started its own session; one that clears its environment and leaves the rehearsal's folders lives on, still inside the sandbox.
From its catalog listing.
How to install
- Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install clotho - Said no? Turn it on later:
hermes plugins enable clotho - Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide (opens in a new tab).
- Category
- AI models & providers · Automation & multi-agent
- Maintained by
- NicWeinbrecht (Community)
- Needs
- No API keys declared
- Adds hooks
pre_tool_call- Works on
- macos
- Needs Hermes
- 0.23.0 or newer
- Version
- 0.1.0
- In the catalog
- 2026-11-17
Using the Hermes desktop app? See where plugins live

Full setup & settings ↗Source code ↗
More in ai models & providers
All ai models & providers plugins
New Hermes Agent updates every day on X. Follow @HermesWatcher