All plugins

devin

Delegate coding tasks to the Devin CLI, on your computer or in Devin Cloud, with live progress cards and change review in Hermes Desktop. Every launch goes through Hermes approval; Cloud runs need a separate Cloud-managed-permissions confirmation. Disclosure — spawns the vendor devin CLI from PATH or cli_path (devin acp, devin acp --cloud, devin --print, devin auth status, devin models list); the CLI edits files and runs shell commands in a folder the model picks (any folder unless allowed_roots is set) under the configured permission mode (accept-edits/smart auto-allow edits, dangerous auto-allows everything and needs allow_dangerous: true), and talks to Cognition's servers; Devin Cloud runs use Cognition-managed permissions that Hermes does not gate. Every model-initiated launch goes through Hermes approval; follow-ups typed on a Desktop run card and answers to Devin's prompts on the card start or allow actions on that click without a Hermes prompt (unanswered card prompts are denied after 300 s by default). Uses the existing Devin CLI login and stores no credentials; Hermes provider, bot and tool secrets are stripped from the child environment (extra_env is passed as set). Background runs continue after the turn up to their timeout and post Devin's output back into the conversation as a message when they finish. Run history (prompts, diffs, command output) and model preferences are saved under plugin-data/devin unless persist_runs is off. Independent community add-on, not affiliated with Cognition.

Adolanium1Toolsv0.1.1Updated 23 days ago

About

Delegate coding tasks to the Devin CLI, on your computer or in Devin Cloud, with live progress cards and change review in Hermes Desktop. Every launch goes through Hermes approval; Cloud runs need a separate Cloud-managed-permissions confirmation. Disclosure — spawns the vendor devin CLI from PATH or cli_path (devin acp, devin acp --cloud, devin --print, devin auth status, devin models list); the CLI edits files and runs shell commands in a folder the model picks (any folder unless allowed_roots is set) under the configured permission mode (accept-edits/smart auto-allow edits, dangerous auto-allows everything and needs allow_dangerous: true), and talks to Cognition's servers; Devin Cloud runs use Cognition-managed permissions that Hermes does not gate. Every model-initiated launch goes through Hermes approval; follow-ups typed on a Desktop run card and answers to Devin's prompts on the card start or allow actions on that click without a Hermes prompt (unanswered card prompts are denied after 300 s by default). Uses the existing Devin CLI login and stores no credentials; Hermes provider, bot and tool secrets are stripped from the child environment (extra_env is passed as set). Background runs continue after the turn up to their timeout and post Devin's output back into the conversation as a message when they finish. Run history (prompts, diffs, command output) and model preferences are saved under plugin-data/devin unless persist_runs is off. Independent community add-on, not affiliated with Cognition.

Devin does the coding. Hermes keeps the conversation.

Ask Hermes to hand a task to Devin. The plugin sends the brief through the
Devin CLI, streams progress and returns the result to Hermes.
Use it in Hermes Desktop, the CLI, the TUI or the messaging gateway.

  • Choose where Devin works. Local runs work in a folder on your computer.
    Cloud runs work in a remote environment with the account's available repositories.
  • Choose how Devin thinks. Desktop discovers the models and controls your session
    advertises, including Fusion where available. Local and Cloud keep separate selections.
  • Follow the work in Desktop. Live cards show Devin's plan, command output and file
    edits. Open Review changes or send a follow-up after a run finishes.
  • Approve launches through Hermes. Local runs enforce your configured permission
    mode. Cloud runs require a separate Cloud-managed-permissions confirmation.

The plugin uses devin acp for Local and devin acp --cloud for Cloud.
No separate Cloud API key, extra service or Devin Desktop installation is required.
Hermes and the Devin CLI each need their own authentication.

Local or Cloud

| | Local computer | Devin Cloud |
| --- | --- | --- |
| Workspace | Your selected folder | Remote repositories and platform choices |
| Models | Session-advertised models, Fusion pairings and supported thinking controls | Account-advertised Cloud presets and controls |
| Permissions | Your Local permission mode, with in-run approval where supported | Cloud-managed permissions, confirmed before launch |
| Stop | Cancel the task and clean up tracked Local processes | Request remote cancellation and show whether Devin confirmed it |

Cloud does not upload your local files or MCP servers. Stopping its local relay
does not prove remote work stopped. Read the Cloud guide
before your first Cloud run.

Quick start

  1. Install Hermes Agent
    and the Devin CLI. Configure Hermes' model provider.

  2. Sign in to Devin and install the plugin from the Hermes plugin catalog:

    devin auth login
hermes plugins install hermes-devin
hermes plugins enable devin

    The catalog installs the reviewed commit, and hermes plugins update devin
    moves you to the next one.

  3. Restart Hermes. In Desktop, enable the Desktop half under
    Capabilities → Plugins → Devin.

  4. For Local ACP, choose a supported permission mode such as accept-edits.
    Current Devin builds cannot honor the default normal mode over ACP, so the
    plugin refuses those runs. See installation and first-run settings.

  5. Run /devin doctor in a Hermes conversation, then ask:

    Have Devin add tests for src/utils.py in /path/to/project and run them.

Or open Devin → New Devin task in Desktop to choose a target and its model controls.

What it does on your computer

  • Runs the Devin CLI. Each run starts devin from your PATH (or cli_path) as a
    child process. Local runs let Devin read and edit files and run shell commands in the
    chosen folder, within the permission mode you configured. Background runs keep going
    after the conversation turn ends, up to their timeout.
  • Talks to Devin's services. Cloud runs and model discovery go through the Devin CLI
    to Cognition's servers. The plugin makes no other network calls and has no telemetry.
  • Uses Devin's own login. The plugin never reads or stores credentials. Devin's child
    process gets your environment without Hermes' provider, bot and tool keys. Add any
    variable Devin needs with extra_env.
  • Keeps run history. Run records, including prompts, plans, recorded diffs and
    command output, are saved under <hermes home>/plugin-data/devin/runs/. Set
    persist_runs: false and restart Hermes to keep history in memory only, and cap it
    with history_limit.

Documentation

Detailed setup and technical references live in Markdown files under docs/.

| Start here | |
| --- | --- |
| Installation | CLI setup, authentication and first-run configuration |
| Usage | Desktop workflow, chat examples, commands and tools |
| Local model controls | Model search, Fusion, thinking controls and defaults |
| Cloud sessions | Remote choices, permissions, Stop and reconnect checks |
| Configuration | Settings, defaults and limits |
| Safety and limitations | Approval rules and links to known limitations |
| All documentation | Development, run data, process cleanup and optional MCP setup |

Community, credits and license

Hermes Devin is an independent community add-on. It is not affiliated with,
endorsed by, sponsored by or officially associated with Nous Research or Cognition.

Hermes Agent, its name and marks
belong to Nous Research. Devin, its name and trioexagon mark
belong to Cognition. All rights to those products, names and marks remain
reserved to their respective owners.

The add-on's code is MIT licensed. That license does not grant rights to
third-party products or marks. See trademark credits and asset sources.

Want to contribute? Start with CONTRIBUTING.md.

README from the reviewed commit 45ae46b; it updates when the author re-pins.

More by Adolanium

25 plugins by Adolanium in the catalog.

AdolaniumgadgetTalk to your Hermes from small ESP32 devices with a screen, microphone and speaker: hold a button, ask, and hear the answer. Adds a gateway platform where each device is a chat, plus tools to list devices, show a card on a screen and run device actions (LEDs, relays). Disclosure — the gateway listens for devices on a WebSocket port (8765, all interfaces by default; plain ws:// unless tls_cert/tls_key are set). New devices need a Hermes pairing code unless listed in GADGET_ALLOWED_USERS; GADGET_ALLOW_ALL_USERS skips pairing (development only). A paired device answers the agent's command approvals for its own chat (allow once or deny), within Hermes's approval timeout. The first approved device becomes the platform's home channel by default. Session hooks feed a dashboard on paired devices with each agent session's platform, a short id and its state (idle, busy, waiting for approval); a device that can switch profiles also sees the offered profiles' sessions. Optional profile switching (off unless `profiles` is set in the default profile's gadget config) lets a device paired on the default profile talk to the listed profiles; each profile approves the device through its own pairing flow (the device shows the `hermes -p <profile> pairing approve` command), the plugin writes nothing into other profiles, and revoking the device in the default profile sends it back there. A paired gadget that draws faces gets the answering profile's face: its `gadget-face.bin`, or its Hermes avatar (`assets/avatar.*`) converted with Pillow when installed; the plugin only reads these files, and `profile_faces: false` turns this off. `platforms.gadget.extra.stt_language` sets the transcription language of gadget recordings through the `pre_transcription` hook; other platforms' audio is untouched. Spoken replies that are not WAV are converted with the local ffmpeg; Opus reply audio uses the host's libopus when installed (loaded with ctypes, not bundled). `hermes gadget update --latest` downloads firmware from this repository's GitHub releases, checks size and SHA-256 against the release manifest (files carry build provenance attestations) and sends it to the device. A device that advertises `camera.capture` returns stills that are saved as PNGs under `~/.hermes/gadgetpix/` and kept until removed by hand. A Hermes Desktop page (`desktop/plugin.js`, plugin SDK only) runs a gadget in the window that connects to the local gateway as a device of its own: its device key, and the gateway access token when one is required, are kept in the page's plugin storage, it pairs like any device, and it uses the microphone only while its talk button or Space is held. The plugin's dashboard routes, behind the dashboard's login, can approve the pairing code a device is showing and send a card or run an advertised action on a connected, paired device; the requests pass through files under plugin-data/gadget/desk/. Otherwise writes only under plugin-data/gadget/. Uses Hermes's own STT, TTS and image cache; no telemetry. Independent community project, not affiliated with Nous Research.Communityplatform518Adolaniumhermes-resetwatchTrack subscription quotas and reset times in Hermes Desktop. Disclosure — probe.py re-executes itself under the Hermes Python interpreter located via HERMES_PYTHON / VIRTUAL_ENV / the parent process or the Hermes installer's managed venv (HERMES_HOME/installs). Every credential read is read-only and nothing is refreshed or stored: it reads provider API keys from the process environment, the Hermes .env (through Hermes's get_secret helper, else read directly), the Vaultwarden plugin's local secret cache (cache/vaultwarden_cache.json, only when Vaultwarden is the sole enabled secret source, keyed by a hash of BW_SESSION, which is never sent) and Docker s6 container env files; Hermes's saved OAuth logins (the credential pool through Hermes's read_credential_pool helper, else auth.json directly, and HERMES_HOME/.anthropic_oauth.json); and other coding-assistant CLIs' local logins: Claude Code (credentials file, macOS keychain or Windows Credential Manager), Codex, Cursor (macOS keychain and the IDE's state.vscdb, opened read-only), Kimi, Grok, ZCode and Command Code. For GitHub Copilot (on by default) it tries COPILOT_GITHUB_TOKEN / GH_TOKEN / GITHUB_TOKEN (through Hermes get_secret, else the process environment), then the Copilot editor's apps.json / hosts.json, then runs gh auth token (prompts disabled, 3-second limit), trying each token in turn until GitHub accepts one. For Codex, a 401 or 403 is retried once with another saved login for the same account. It sends each key only to its own vendor's usage endpoint, presenting the vendor client's identity headers where a private endpoint expects them (Claude Code and Codex CLI user agents, the Grok CLI client headers, and for Copilot the VS Code / Copilot Chat editor headers on api.github.com/copilot_internal/user, which GitHub does not document); environment variables such as GROK_CLI_CHAT_PROXY_BASE_URL (honored only for https grok.com / x.ai hosts), CLAUDE_CONFIG_DIR, CODEX_HOME and GROK_HOME change which host or file it uses. Usage results are cached under HERMES_HOME/cache/resetwatch, never tokens. It exposes nothing to the model: it is a Desktop page only.CommunityDesktop app83Adolaniumhermes-rssRead RSS and Atom feeds and discuss articles in Hermes Desktop. Disclosure — feeds and full articles are fetched with curl through the gateway's shell.exec on the connected Hermes host (public-IPv4 SSRF guard); opt-in AI grading sends article excerpts to your configured model and creates HERMES_HOME/skills/rss-importance-grading/SKILL.md if missing; opt-in image loading fetches publisher images directly from Desktop.CommunityDesktop app65Adolaniumhermes-tailscaleBrowse Tailscale devices and connect to remote Hermes instances in Hermes Desktop.CommunityDesktop app60
All 25 by Adolanium

Developer Mode

Explore built-in Hermes toolsets and actions.

HermesAgent

Developer?

Create a Hermes extension for Desktop or agent workflows.

Developer Section