{
  "sources": [
    {
      "url": "https://raw.githubusercontent.com/medomohamed22/hermes-ark/a23e529c1f636aa49d974576cdc5cb15fc8242d3/README.md",
      "quote": "- A **safety snapshot** is taken before every restore, so a restore can itself be undone.\n- Every blob is fetched and integrity-checked **before the first write** — a damaged backup never leaves a half-restored home.\n- Writes are atomic and never leave the Hermes home (no `..`, no drive letters, no symlink escapes, no setuid bits).\n- The sessions database is only restored while the gateway is stopped. Hermes credential files (`.env`, `auth.json`, vault, pairing) are"
    },
    {
      "url": "https://raw.githubusercontent.com/Bruno-coder21/fluent/182c4301f2437e784e9022f1f38576e1d68c3f5f/README.md",
      "quote": "Hermes already checks the code it writes. **fluent checks the shell commands it runs**,\nagainst the real `--help` and `man` pages of the program installed on *your* machine,\nbefore they run."
    },
    {
      "url": "https://raw.githubusercontent.com/merdoks/trust-ladder/fae4e9df58767e5e3832c8f65936b97868bc98fc/README.md",
      "quote": "When you tell an agent \"never push straight to main\", the correction usually lives in a prompt or\na memory note, and the agent forgets it three sessions later. trust-ladder turns the correction into\nsomething the agent *cannot* repeat: a deterministic guard that Hermes checks before every tool\ncall, with a ledger that shows you each time it saved you."
    },
    {
      "url": "https://raw.githubusercontent.com/Joko-F/hermes-fine-print/7b574f1b5c8dc8eafe3ea9f87ae6b0111853f0ba/README.md",
      "quote": "**Hermes changes what your model sees. Fine Print shows you: with numbers, a note to the model where\nnobody else tells it, and the fix.**"
    },
    {
      "url": "https://raw.githubusercontent.com/0xbyt4/hermes-canvas/d6eeff0d6f7ec653262537bdd7bb001cc6d3c7f8/README.md",
      "quote": "Hermes Canvas is a plugin for [Hermes Agent](https://github.com/NousResearch/hermes-agent) and\nHermes Desktop. The agent draws its plan as hand-drawn boxes on a canvas next to the chat. Each\nbox is bound to files and a check command. Box status comes from hooks, not from the model: a box\nis \"doing\" when the agent writes one of its files, and \"done\" or \"failed\" when its check command\nexits. You steer the build by editing the canvas, before and during the build."
    },
    {
      "url": "https://raw.githubusercontent.com/opeblow/kata/cc59b08f1bbeeb02524c060faac04edb34de0564/kata/executor.py",
      "quote": "\"\"\"Deterministic execution of a compiled kata."
    },
    {
      "url": "https://raw.githubusercontent.com/jeremiebergel/context-manager-intelligence/399468f0687c051476961e4bb045eb84263be6b1/README.md",
      "quote": "CMI sits between you and the AI and **folds the old pages**. Recent work stays open. Old things become a\nshort note, like a sticky note on a folder. If the AI needs one of them again, it unfolds it and gets the\noriginal back, exactly as it was. Nothing is thrown away."
    },
    {
      "url": "https://raw.githubusercontent.com/robbyczgw-cla/hermes-ui-cards/c40df4d41cd5439cf4902995fd4a9e5505483f25/README.md",
      "quote": "- **Answered cards lock.** An answered card shows a receipt and locks in that window. The plugin's\n  backend records answers too, so the Webapp, the Desktop app and a second computer on the same Hermes\n  lock the card once they have checked (its buttons wait for that first check). This is eventual, not\n  exactly-once: two clients that answer before either has synced can both send; the backend keeps the\n  first answer and tells the model about the second.\n- **Undo be"
    },
    {
      "url": "https://raw.githubusercontent.com/RaYYeR220/housemate/09c1a1d0a88bfa8762cee6b3ccf94271b0f172c5/README.md",
      "quote": "**Hands-free Hermes in every room. Say the wake word, ask, and hear the answer in the same room <!-- num:latency_p50 -->2.6 s<!-- /num --> after you stop talking.**"
    },
    {
      "url": "https://raw.githubusercontent.com/cineglobe/hermes-gemini-live/b6c2f24354aeed1a8b5651b62944d14ed96a472d/README.md",
      "quote": "Full-duplex voice calls with your Hermes agent, powered by the Gemini Live API. Talk naturally,\ninterrupt any time, and let the voice hand real work to Hermes while you keep talking. It can watch\nand steer your other threads, bot chats and subagents, recall your memory, check the server, and\ntell you when the work is done."
    },
    {
      "url": "https://raw.githubusercontent.com/vijaygopalbalasa/hermes-necromancer/0ff7bec40aba10091a84f94025d4471984fd7386/README.md",
      "quote": "Lock the tests that define done with one command. When Hermes says it's finished, the plugin runs them itself and\nsends Hermes back with the failure named. Edits to locked tests are blocked, and a pass ends the reply with a receipt\nanyone can re-check."
    },
    {
      "url": "https://raw.githubusercontent.com/akinduroifedayo/shadow/38173bc9c696df3b1f87b5b9b60ccecd36a260ab/README.md",
      "quote": "Shadow is a Hermes plugin. It replays recent saved turns on the model you want to try and your current model. A judge compares the answers. The result leads with the numbers: turns won, lost, and tied, and the cost difference per turn. It also shows the win rate with its 95% range, speed, tool steps, and broken calls. You can inspect individual turns and switch models with undo. If the test doesn't back the switch, Shadow warns you first and switches only if you con"
    },
    {
      "url": "https://raw.githubusercontent.com/0xNoramiya/hypnos/0a809b9085fdeaed63fd909b927afcc41de512de/README.md",
      "quote": "During the day Hypnos watches how you work with Hermes: what you approve, what you deny, what you correct,\nand which commands pass or fail. At night it sleeps. It replays the day, dreams up variations of its\nmistakes and practises them in a sandbox, then consolidates what it learned into the weights of a small\npersonal model, a LoRA brain. In the morning the brain takes an exam. If it beats the brain it replaces,\nHermes routes the turns it has mastered to it, and th"
    },
    {
      "url": "https://raw.githubusercontent.com/miracle352/hermes-ariadne/128c95967a0761ad24d3d224441d1502c43bbb69/README.md",
      "quote": "Ariadne sits on Hermes's public middleware. While recording, it saves every model call, tool call\nand user turn to a cassette. During a replay it answers the model calls and tool calls from that\ncassette, so nothing runs and nothing is billed, while the rest of Hermes (prompt building,\ntool-call parsing, compaction, hooks, subagents) runs for real. Any difference from the recording\nis a change in Hermes."
    },
    {
      "url": "https://raw.githubusercontent.com/bettersandeep/grimoire/4824773040b131f3179e5896d71d1435908758a7/engine.py",
      "quote": "\"\"\"Read-only DuckDB engine over the files the user attaches."
    },
    {
      "url": "https://raw.githubusercontent.com/PedValme/foreman/c15453cb2fc07fa674d6f7b548a553b3ce9e6f5d/plugin/README.md",
      "quote": "Foreman is a [Hermes Agent](https://github.com/NousResearch/hermes-agent) plugin for people who let Hermes write\ncode in a git repository. A coding agent under pressure can make the check pass by skipping a test, deleting it,\nloosening an assertion or editing what the check runs. Foreman reads the real diff before every commit, push, pull\nrequest and merge, and blocks those shortcuts; a second model reviews what rules cannot see; and Foreman never\nmerges for the age"
    },
    {
      "url": "https://raw.githubusercontent.com/akinduroifedayo/living-spaces/e6145ccbd028edf55417822020426f4830343eb6/src/living-spaces/README.md",
      "quote": "Upkeep uses the private `cron.jobs` and `cron.executions` modules. Desktop session cleanup uses the raw `window.hermesDesktop` bridge to retain the original backend target. These integrations carry compatibility risk and catalog-review warnings. This is not an all-public-SDK or catalog-approved package."
    },
    {
      "url": "https://raw.githubusercontent.com/breadcrumbs-agency/hermes-breadcrumb-plugin/b8975645e5174edbcc00d5dc86a78e536bce938b/breadcrumbs/summarize.py",
      "quote": "    def __call__(self, prompt):\n        argv = self.argv()\n        with _MODEL_LOCK:\n            p = subprocess.run(argv, input=prompt.encode(\"utf-8\"), capture_output=True, timeout=self.timeout)\n        if p.returncode:\n            m = _TOO_LONG.search(p.stderr)\n            if m:\n                raise PromptTooLong(int(m.group(1)), int(m.group(2)))\n            raise RuntimeError(\"llama-completion exit %d: %s\" % (p.returncode, p.stderr[-300:].decode(\"utf-8\", \"replace"
    },
    {
      "url": "https://raw.githubusercontent.com/otsoa-dubief/tenure/f4a62855e592b9e170ab0c54d9278aabef05f370/tenure/classify.py",
      "quote": "HERMES_VAR = re.compile(r\"\\$(?:HERMES_HOME|\\{HERMES_HOME\\})(?:/+\\.?)*/*\")   # `$HERMES_HOME` alone: a level\nGLOB = re.compile(r\"[*?\\[]\")\nUSER_HOMES = re.compile(r\"/(?:home|users)/[^/]+|/root|/var/root\")\n_TARGETS: dict = {}                                      # per process: Hermes' executables and package folders"
    },
    {
      "url": "https://raw.githubusercontent.com/Pratiikpy/workroom-for-hermes/c5f6bf334c1163951e203dc7c5777faadfe49795/adapters/snapshotter.py",
      "quote": "_CD = re.compile(r\"(?:^|[;&|\\n])\\s*(?:cd|pushd|Set-Location)\\s+(?:/d\\s+)?(\\\"[^\\\"]+\\\"|'[^']+'|[^\\s;&|]+)\", re.I)"
    }
  ]
}