All plugins

hermes-cron

Operating skill for Hermes cron: lifecycle rules (pause vs disable vs remove, in 30m vs 30m), four ways to avoid needless LLM runs (no_agent, wakeAgent pre-check, monitor, [SILENT]), verify-after-change, a layered runbook and a read-only doctor that complements hermes cron doctor and reports one error across several jobs as one scheduler fault and a cron store that cannot be written. Portable Agent Plugins v1 package (plugin.json + skills/); no tools, hooks, middleware or env vars. Disclosure — skill only, no network; the bundled doctor reads ~/.hermes/cron/jobs.json, ticker stamps and executions.db (or a named profile's store with --profile) read-only, checks the cron directory's permissions and free space without writing, and runs the local hermes cron doctor (argument list, no shell), whose job loader may repair malformed jobs.json entries (--no-builtin skips it).

itpartypattaya6Automationv1.5.4Updated 15 days ago

About

Operating skill for Hermes cron: lifecycle rules (pause vs disable vs remove, in 30m vs 30m), four ways to avoid needless LLM runs (no_agent, wakeAgent pre-check, monitor, [SILENT]), verify-after-change, a layered runbook and a read-only doctor that complements hermes cron doctor and reports one error across several jobs as one scheduler fault and a cron store that cannot be written. Portable Agent Plugins v1 package (plugin.json + skills/); no tools, hooks, middleware or env vars. Disclosure — skill only, no network; the bundled doctor reads ~/.hermes/cron/jobs.json, ticker stamps and executions.db (or a named profile's store with --profile) read-only, checks the cron directory's permissions and free space without writing, and runs the local hermes cron doctor (argument list, no shell), whose job loader may repair malformed jobs.json entries (--no-builtin skips it).

hermes-cron

hermes-cron — safe cron jobs for Hermes Agent

A skill that teaches Hermes Agent to run its cron
scheduler like a careful operator: pick the right lifecycle action, keep jobs cheap and quiet, verify
every change and find the broken layer when a reminder does not arrive. It ships with a read-only
doctor script that complements the built-in hermes cron doctor.

Why

Cron failures in an agent look like success. The tool answers success: true, the record says
paused, last_status is ok — and the messages keep coming, or never arrive. Typical causes:

  • a bare 30m was meant as "in 30 minutes" but schedules a job every 30 minutes;
  • the prompt says "send a summary", so the agent sends it and the scheduler delivers it again;
  • deliver: origin points at the chat where the job was created, not at the person it is for;
  • a record with enabled: true and a pause marker never fires, yet the list shows it as scheduled;
  • a pinned model ignores hermes model and skips the fallback chain when its provider is down.

The skill turns each of these into a rule the agent follows, and the doctor makes them visible.

What you get

PartWhat it does
SKILL.mdWhen to use, lifecycle table, cheap modes, procedure, pitfalls, verification
scripts/cron-doctor.pyRead-only health check: scheduler, jobs, delivery, incidents
references/reference.mdCLI, cronjob tool fields, schedules, statuses, markers, cron: settings
references/troubleshooting.mdSymptom runbook: missed, late, duplicated, misrouted, silent jobs

Wake the model only when needed

Four ways a cron job avoids a needless LLM run

SituationModeHow it stays silent
Text is known in advance; alert watchdogno_agent: true + scriptempty stdout or {"wakeAgent": false}
Fresh data needed, real work is rarescript pre-checklast line {"wakeAgent": false}
"Tell me when this changes"monitor (script or URL)unchanged output skips the agent run
The model decides, but not always reportsLLM jobreply exactly [SILENT]

Debug by layers

Check the scheduler, the job record, the execution, the delivery and other writers in that order

When a job misbehaves, the skill walks the layers top to bottom instead of rewriting the schedule:
is the scheduler ticking, is the record consistent, was there an attempt, was the result delivered,
and did a sync or deployment overwrite the change.

Install

Pick one. Option 1 is the usual choice: the skill lands in ~/.hermes/skills/ and the agent picks it
up from its description.

1. As a regular skill (recommended)

hermes skills install itpartypattaya/hermes-cron/skills/hermes-cron

2. As a portable plugin (Agent Plugins v1 package: plugin.json + skills/)

hermes plugins install itpartypattaya/hermes-cron --no-enable
hermes plugins enable hermes-cron

Plugin skills are read-only and namespaced. They are not listed in the system prompt; the agent finds
them through skills_list and loads them with skill_view.

3. Manually

git clone https://github.com/itpartypattaya/hermes-cron.git
cp -r hermes-cron/skills/hermes-cron ~/.hermes/skills/

Use it

Ask the agent in plain words; the skill covers the rest.

  • "Remind me in 30 minutes to call the bank." → a one-shot in 30m, verified, with the exact time.
  • "Pause the morning digest until Monday." → pause, plus who resumes it on Monday — Hermes has no
    scheduled resume for recurring jobs — and no new duplicate job.
  • "Ping me only if the disk is over 90 %." → a script-only watchdog, tested for silence and for alert.
  • "Why didn't the 9 am report arrive?" → doctor first, then the layer that broke, then the fix.

The doctor

python3 ~/.hermes/skills/hermes-cron/scripts/cron-doctor.py              # all jobs
python3 ~/.hermes/skills/hermes-cron/scripts/cron-doctor.py --job <id>   # one job + recent runs
python3 ~/.hermes/skills/hermes-cron/scripts/cron-doctor.py --json       # for automation
python3 ~/.hermes/skills/hermes-cron/scripts/cron-doctor.py --no-builtin # skip `hermes cron doctor`
python3 ~/.hermes/skills/hermes-cron/scripts/cron-doctor.py --profile work # jobs of a named profile

Inside the skill the path is "${HERMES_SKILL_DIR}/scripts/cron-doctor.py", so it works wherever the
skill is installed. The doctor runs the built-in hermes cron doctor when the CLI is found (PATH,
~/.local/bin or HERMES_BIN) and adds what it does not check:

  • ticker heartbeat and last successful tick, with the PID that wrote the stamp, and the error of a
    failed tick (ticker_last_error);
  • a one-line count of jobs by state (summary in --json);
  • disabled, paused and half-paused jobs — the built-in check looks at active jobs only;
  • duplicate ids, malformed entries, unknown schedule kinds, no_agent without a script, failure streaks;
  • the delivery outcome of each job's latest completed run and open failure incidents from
    executions.db (ordered by the real instant, not by timestamp text);
  • the same error in three or more jobs within 24 hours, reported once as a scheduler or host fault
    (shared_failures in --json). Per-job fields hide it: they reset on the next good run, and a
    failed dispatch may open no incident at all. Run ids, timestamps, measured durations and PIDs are
    masked before grouping; interruptions by a gateway restart are not counted;
  • pinned models and thread-less delivery into chats that use threads;
  • a cron store this user cannot write, or one with less than 100 MB free: Hermes 0.21.6+ skips due
    jobs it cannot record. The check reads permission bits and free space and creates no file;
  • the sticky last_failure (0.21.6+) of a job that has recovered since, as a note;
  • a pause Hermes 0.22.4+ set itself after a fire it could not verify — resuming it by hand before
    reading hermes cron runs <id> may run the job twice;
  • agent jobs that a headless hermes cron tick skipped because no gateway was ready: two or more are
    one fault (skipped_fires in --json), and their overdue slots are not reported one by one;
  • a delivery still queued an hour after its run (0.22.4+ writes the outcome back once the gateway
    drains), as a note;
  • a bot-chat:<profile> delivery parked until the target profile runs, which Hermes books as
    delivery_failed, as a note instead of "not delivered";
  • a script that is a shell command line (echo hi), which 0.22.4+ refuses on create and update.

Without the CLI, and always for --job, it performs the basic checks itself: failed last run, undelivered
result, a missing or overdue next_run_at, a failed dispatch, a script outside the scripts directory or
missing (with a hint when it is a command line), a missing working directory. A built-in doctor that crashes, or a run history that exists but
cannot be read, is a finding, not a note. Exit codes: 0 healthy, 1 findings (--job
included), 2 unreadable runtime state, 3 invalid arguments or an unknown job; with --json, errors
are JSON too.

== Scheduler ==
  heartbeat: 12 s ago, PID 41873
  successful tick: 12 s ago

== Built-in hermes cron doctor ==
  ✓ Cron doctor found no issues
    Checked 5 active job(s).

== Jobs ==
  7 total · 4 enabled · 1 half-paused · 1 paused · 1 completed
  …

== Findings ==
  🔴 3f2a9c1d7e44 "Weekly report": enabled=true with a pause marker — Hermes will not run it,
     yet `cron list` shows it as scheduled; pause or resume it properly

== Notes ==
  ℹ️ 8b1e6d0a2f93 "Nightly digest": pinned model (model-x · provider-y) — does not follow
     `hermes model` and does not use the global fallback chain

Safety and privacy

  • Read-only. The doctor never ticks, runs, edits or removes a job.
  • No network access and no API keys. The only subprocess is the local hermes cron doctor, started
    as an argument list without a shell. Hermes' own job loader, like every scheduler tick, may repair
    malformed entries in jobs.json.
  • It reads ~/.hermes/cron/jobs.json, the ticker stamps and executions.db (opened read-only). It
    writes nothing and does not read the gateway's admission journals or parked deliveries. Like any
    SQLite reader of a WAL database it may create the -shm/-wal files Hermes itself uses; without
    write access to cron/ it reads the main file without locks and says so in its notes. A database
    that is locked by a writer is reported as unreadable, not read around.
  • The skill registers no tools, hooks or middleware and needs no environment variables.

Compatibility

Written against Hermes Agent 0.21.5 and checked against 0.21.6, 0.22.0, 0.22.2, 0.22.4 and 0.22.5:

  • in 30m is one-shot; 30m and every 30m repeat; every monday 9am and weekdays at 9am become
    cron expressions;
  • jobs follow cron.model or the main model at fire time unless pinned;
  • since 0.21.6, enabled_toolsets: [] means a job with no tools, not the default set; a restricted
    job goes back to the default set through the web dashboard or by recreating it;
  • the agent tool is cronjob_manage (old name cronjob) and is loaded on demand through tool_search;
  • one gateway serves every profile; a named profile's jobs live in ~/.hermes/profiles/<name>/ —
    --profile <name> points the doctor there;
  • a job runs only when enabled is true and it carries no pause marker;
  • the ticker heartbeat is <epoch> <pid> (older <epoch> stamps are still read);
  • since 0.22.4 agent jobs run through the gateway that owns the store: hermes cron tick from an external
    scheduler runs only no_agent jobs while no gateway is ready, and a fire Hermes cannot verify pauses
    the job until it is reconciled;
  • since 0.22.4 script must be a file under scripts/; a command line is refused.

On an older Hermes, check flags with hermes cron create --help before following the examples.

Scope

The skill covers the standard Hermes cron contract and assumes no repository, user, chat, timezone or
delivery target. GitOps snapshots, three-way merges, persistent configuration and organization-specific
alert routing are out of scope; keep them in a separate local skill loaded alongside this one.

Repository layout

plugin.json                      # Agent Plugins v1 manifest
skills/hermes-cron/
  SKILL.md
  scripts/cron-doctor.py
  references/reference.md
  references/troubleshooting.md
tests/test_cron_doctor.py        # stdlib unittest, no network
docs/                            # images used by this README

Development

python3 -m unittest discover -s tests -v

Issues and pull requests are welcome.

Author

Anton Vaskov — Telegram @passone, GitHub itpartypattaya.

License

MIT

README from the reviewed commit 6d03e78; it updates when the author re-pins.

More by itpartypattaya

4 plugins by itpartypattaya in the catalog.

itpartypattayaholographicLocal fact-store memory provider: SQLite with FTS5 keyword search (word forms in English, Russian, Spanish, French, Portuguese, Indonesian, German, Hindi, Arabic, Bengali, Italian, Turkish, Polish and Dutch; Russian and English words of the same root at a lower weight, from bundled DerivBase.Ru (Apache-2.0) and Open English Wordnet (CC BY 4.0) pairs; German compounds and German and Spanish irregular verb forms from bundled Wikidata Lexemes tables (CC0); Chinese, Japanese, Korean and Thai by character n-grams, Chinese also split into words with jieba's dictionary (MIT), Traditional and Simplified Chinese compared as one through a bundled OpenCC table (Apache-2.0), Japanese spelling variants through SudachiDict's (Apache-2.0); synonyms through keywords the agent gives when it stores a fact), trust scores, entities with aliases and HRR (holographic reduced representation) recall, with no API key, network or model calls unless an optional online feature is switched on: search by meaning (embeddings: on) or rescoring by a cross-encoder (rerank: on), both off by default. The provider that shipped in-tree as plugins/memory/holographic, with the same provider name, config (plugins.hermes-memory-store) and memory_store.db, so hermes update moves existing users onto it; a file without merges keeps history schema 1; the first merge raises it to schema 2, after which writers of 0.15-0.18 refuse it until 0.19.0 or a pre-merge backup is restored. Taken over from Nous Research's handoff copy (NousResearch/hermes-plugin-holographic) and maintained by itpartypattaya; since 0.1.1 it fixes probe/reason/related/contradict, non-atomic writes and the never-written retrieval_count, gates recall by relevance without repeats, flags duplicates and conflicts when a fact is added, and honours the provider contract (read-only subagent contexts, hermes_home, mirror metadata, backup_paths); since 0.8.0 it keeps the history of every fact (change / end / correct / revert, search and list as_of a date) and forget erases a fact with all its versions from the file; since 0.16.0 a name guessed from a fact's text must be shaped like one and stays provisional until a second fact or a person confirms it, and entities can be renamed or deleted (the facts stay). Since 0.18.0 an optional, experimental second stage reorders the recall candidates with a cross-encoder at a /v1/rerank endpoint that answers in Cohere's shape without a key, such as llama-server (rerank: on, off by default). It does not raise hits: on the maintainer's held-out set (126 questions) it cut non-target facts in the top five by about 40 % and lines per turn by about a third, and lost about one target per hundred questions. Disclosure — local only unless an optional online feature (search by meaning or rescoring) is switched on: reads and writes one SQLite file per profile ($HERMES_HOME/memory_store.db unless db_path says otherwise), or with scope: user / chat / thread one file per user or chat in holographic-users/ or holographic-chats/ next to it; each fact version records where it was written (platform, chat type, chat and thread id, session id, the turn author's id and display name, and whether the person said it or the agent inferred it; never chat titles), shown in full by list, history and export and not in recall unless recall_source: short (date, display name, this or another chat); each confirmation of a fact by a person keeps its time, session id and that person's id (no text); forget deletes that and the confirmations with the fact and keeps only an HMAC of the text, keyed by a random key stored in the same file, as a tombstone; delete_entity removes a name, its aliases and links from the entity index (never a fact) and keeps an HMAC of each name the same way (not of an alias only a fact's text gave, which goes without one), and both rewrite the file so freed pages keep no copy; the first writable open after an upgrade that changes the extraction rules relinks the facts to their entities under the new rules (stores up to 2,000 facts and 500,000 characters; larger ones on fact_store rebuild_entities), changing only the names it guessed and their links, never a fact, a declared name or an alias someone gave; subagents never write, but a cron job's explicit fact_store / fact_feedback calls do unless cron_writes: false (on by default); no subprocesses or telemetry (at the debug log level the recall stages log fact ids and scores, never text), and no network calls or credentials unless embeddings: on or rerank: on (both off by default). With embeddings: on, the text of facts, and of messages and fact_store search queries that are not greetings, goes to the OpenAI-compatible embeddings endpoint the user configures, also after cron turns while cron_writes is on (embedding_url; https, plain http only to localhost, a private or link-local address, or a local host name such as one without a dot or ending in .local), with the key read from the environment variable the user names (embedding_key_env, OPENAI_API_KEY unless set, sent as a Bearer token to whatever embedding_url is configured, never stored in config) and no redirects followed; facts that recall would not inject, and facts and messages that look like they hold a secret (checked by pattern, best effort), are not sent; the vectors are kept in the same file (table fact_embeddings), deleted with their fact by forget / end / remove and all of them by the next writable session after the option is switched off; the provider keeps what it received under its own terms; with rerank: on, before a turn the user's message and up to rerank_top_k (40) candidate fact texts, and for a fact_store search its query and results, go to the rerank endpoint the user configures (rerank_url; https, plain http only to localhost, a private or link-local address, or a local host name), with no credentials and no redirects followed; facts that recall would not inject or that look like they hold a secret, and queries that hold one, are not sent; a failure or a slow answer gives the recall of rerank: off and pauses the endpoint (60 s, doubling to 900 s); nothing the endpoint returns is stored; the bundled language dictionaries are gzip-compressed plain-text word lists; with auto_extract on (off by default) user sentences that state a preference or decision are stored. Since 0.19.0, fact_store merge combines duplicate facts in one transaction while keeping each copy's history, sources and confirmations under its original id. The retained fact keeps its own text, trust and origin; copies leave current search and recall. Optional expect pins the exact shown versions and refuses changed participants without a write. Scheduled jobs can merge only copies created in their own session. Forgetting the retained fact also erases its merged copies. Merge is local and makes no new network or model calls. Version 0.19.1 adds strict tooling for comparing recorded margins; the normal RECALL_MARGIN remains 1.0. Version 0.19.2 closes a timed-out rerank or embeddings request socket so a server dripping response headers does not keep its worker alive. During TLS wrapping, cancellation is retained but the handshake can continue until its own socket timeout; DNS resolution is outside socket cancellation. Version 0.20.0 adds an opt-in local task-outcome journal and the memory-provider tool fact_experience: emitted and candidate fact/version identifiers, an optional short task and correction, outcome/reason and optional corrected-source references. It is separate from trust, origin and ranking. Agent reports are not authenticated human confirmations. Collection and detailed tracing are off by default; retention is bounded to 30 days and 1000 attempts per store, with up to 10 revisions per attempt. Forgetting any referenced fact removes the dependent attempt and outcome from the store. No new model, network or credential use; synchronous local writes add latency. PR #45 also loads NumPy on first use outside the plugin-loader lock; concurrent first callers wait for import completion. Version 0.20.1 limits SQLite busy waits for the optional journal and retries transient contention once. Failed receipts are reported and are not queued; the SQLite timeout is not a full search deadline. Version 0.20.2 writes no receipt for a prefetch that emits nothing, applies journal retention whenever a writer opens the store (also with the journal off) and scrubs removed outcome text from the file like a forgotten fact. Version 0.20.3 adds one system-prompt line, only with the journal on, asking the agent to record an outcome when the person corrects an answer that used recalled facts (an agent report, not human confirmation). Version 0.21.0 adds an opt-in prefetch_max_tokens budget for the recalled block: facts that do not fit are left out whole, never cut; off by default. Version 0.22.0 keeps entity links honest on a text change: a new entities list replaces the declared names, and a declared name the new text no longer says is dropped; revert restores a version's declared names from an additive version_names table (names with keyed hashes, removed with the version and by delete_entity in every spelling a tombstone covers, including by older releases through triggers). Version 0.22.1 makes the secret/instruction screen about 30× faster on long texts with the same decisions (patterns unchanged; a prefilter chooses where they are tried). Version 0.22.2 sends a slow reranker only as many of the first candidates as its measured speed answers in half rerank_timeout (at least two), so a large pool no longer times out and pauses the endpoint; the candidates not sent keep their order behind the scored ones. Version 0.23.0 stops feedback (helpful/unhelpful) from refreshing a fact's age: optional temporal decay counts from when the current version was recorded, and updated_at changes only when the fact itself does; a correction with a new text (correct / update content) starts at its origin's trust without the old text's helpful marks, recalls and confirmations, like change, while a date-only correction keeps them and revert restores the old trust. Version 0.23.1 takes a correction that journal retention removed off the disk on the open connection (the file rewrite runs after the receipt write, with busy timeout 0 at every step) and clears only the rewrite mark it served. Version 0.24.0 adds two experimental features, both off by default and with no new network, model or credential use: memory_map.py, a command-line exporter nothing in the provider calls, which prints one store as a read-only JSON snapshot for a person to read (opened mode=ro in one read transaction; a forgotten fact is its id and date only; corrected versions and texts the safety screen hides carry no text; with --config it reads config.yaml's search settings, with --hermes-home the hermes-dreaming files about the profile store), whose output holds the facts' texts and so is personal data; and prefetch_clause_coverage: on, which gives each of two separate Russian or English questions in one message a second look at the facts the coverage gate left out. Version 0.25.0 limits the memory map export to 1000 facts and 300 names by default (--max-facts / --max-entities, 0 for none) and says what it cut in SNAP.limits; nothing else changes. Version 0.25.1 fixes recall by meaning dropping a fact that names a short Russian name in another grammatical case than the message (Eva as «Ева» / «Еву»): the name now also meets a capitalized word of the fact that may be a case form of it. Version 0.25.2 reads that word by its case ending rather than a short stem: names whose stem changes meet their forms («Лев» / «Льва»), and different names that only shared a short stem («Аня» / «Анна») no longer meet; nothing else changes. Version 0.25.3 no longer imports NumPy when the provider starts (the first search that needs it does, as does opening a store whose vectors need re-encoding) and treats a NumPy that is installed but fails to import as missing, so recall goes on by words; finds a Latin word written into Chinese, Japanese, Korean or Thai text by itself; refuses at write, and leaves out of recall, a prompt addressed to an assistant and the agent's report of its own steps; and auto_extract (off by default) no longer stores a reply such as "I like that" as a preference; no change to defaults, schema or network behaviour. Version 0.26.0 adds an experimental presence gate, prefetch_presence_gate (off by default): with it on, a fact this provider injected is held back past the six-turn repeat window only while the model can verifiably still see it (its exact recall line inside a <memory-context> block the core fenced, or its fact id and text in a fact_store result), reading only the messages the core already passes to sync_turn, with no new storage, network, model or credential use; tool results now carry raw Unicode instead of Unicode escape sequences (a payload that cannot be encoded keeps the escaped form); change names the keywords it drops and correct writes the keywords it is given; with the gate off, recall is unchanged. Version 0.26.1 fixes that gate after an independent review: a sync the core queued before a compaction no longer counts as the current view, a fact the compaction removed is recalled again once a fresh view no longer shows it, a compaction that fails no longer switches the gate off for the session, a late sync keeps its own turn, and a fact_store history result counts as the fact being visible; with the gate off nothing changes. Version 0.26.2: with the task-outcome journal on (off by default), a prefetch that only refreshes facts the session already holds records no new attempt and carries no Memory attempt line, so a repeated block adds nothing new to the context. Version 0.26.3: with the journal and the presence gate on, a delivery whose attempt could not be written after a compaction no longer stops that fact from recording attempts later. Version 0.26.4 fixes the presence gate after a second independent review: two late syncs in a row each keep their own turn, a quiet session that compacted leaves no lasting state, and a refresh no longer keeps token-budget room for an attempt line it does not carry. Version 0.26.5 fixes four edge cases found in a third review of the presence gate and the journal (both off by default): a long pasted message keeps its turn, a session the provider forgot drops its turns' messages, a failed attempt write drops only receipts older than the last compaction, and the token budget no longer keeps room for an attempt line in a block that became a refresh. Version 0.26.6 loads numpy's OpenBLAS on one thread on Windows when the plugin is what imports numpy, which saves about 225 MB of commit charge per Hermes process on an 8-thread machine. Version 0.27.0 adds French auto-extraction of stated preferences and shared decisions, and an optional one-hop memory graph over the entity index that reaches facts next to the ones a query names (bounded reads, off by default). Version 0.28.0 links a wiki pointer line (Wiki page: namespace/.../slug.md) to its namespace and page slug as entities, and recall before a turn searches only what the person wrote: a reply's quoted message, attachment notes, the author's name prefix in shared chats and the cron hint are left out, and a notice of finished background work recalls nothing. Version 0.29.0 records in the optional task-outcome journal (with experience_trace on) one word for why the reranker did or did not order a recall, never error text or facts, and adds measurement tooling; no change to defaults, schema or network behaviour. Version 0.29.1 refuses a fact id that is not a whole number (a JSON true or 1.9 acted on fact #1, and forget erased it) and restores the connection's own SQLite busy timeout after the recall-count flush; no change to defaults, schema or network behaviour. Version 0.29.2 refuses a trust change, trust floor or limit that is no number (a JSON true or "nan" in trust_delta set a fact's trust to the top, and min_trust: true made search and list answer nothing); no change to defaults, schema or network behaviour.Communitymemory42itpartypattayahermes-dreamingNightly deterministic memory consolidation ("dreaming"): corroborates candidate facts with what humans actually said on distinct days, proposes the few worth keeping with a verbatim edit anchor, asks whether stale memory entries still hold, and wakes the agent only when there is work — including a memory file close to its char limit. Fact sources: the holographic store, a SQLite or JSONL export, or none. Secrets and instructions are screened by the dream's own rules plus a verbatim copy of the holographic plugin's screen (scripts/holo_screen.py, MIT, same maintainer), applied to stored facts and human messages before anything reaches memory, the report or the model. Portable Agent Plugins v1 package (plugin.json + skills/); no tools, hooks, middleware or env vars. Disclosure — by default the scripts make no network or LLM calls and open state.db and every fact store read-only (SQLite mode=ro; with holographic >= 0.15.0 including its fact_versions/fact_confirmations tables, to say who stands behind a fact); they also read Hermes config.yaml's memory/timezone keys and the holographic plugin's db_path/scope/cron_writes/min_trust_threshold (the floor recall applies, so a rejected fact is only reported when the store still trusts it) and, to say so in install.py --check, embeddings/mirror_memory_writes, the pending/memory approval queue, cron/jobs.json (to find their own jobs) and — only when chat_stores is set, with holographic scope user/chat/thread — the per-chat databases next to the store (counts of every one; facts of the chats listed in promote_from). An optional cloud judge (judge in dreaming.json, off by default; off, its code is not even loaded) may, once the owner enables it, send for each mention the rules counted the fact's text and that person's own words (no reply quote, link, id, sender or time; names inside the text may be included; screened for secrets and instructions first), only from the chats, sources and chat stores the owner lists, over HTTPS to the providers the owner lists, in the owner's order: OpenRouter's Decisions API (model typesafe/jev-1.14, Jev by TypeSafe; the data reaches OpenRouter and TypeSafe) and/or OpenAI's Decisions API (model gpt-6-luna); when the first gives no usable answer the same pair may reach the next. A verdict can only remove a counted mention — from promotion, confirmation, fact decay, "said again" after a rejection, the selection of new facts and conflicts, and evidence. Keys OPENROUTER_API_KEY / OPENAI_API_KEY are read from the environment or, since Hermes withholds these provider keys from cron scripts, straight from their own line in $HERMES_HOME/.env; the judge's calls are billed to those keys. It keeps a 90-day verdict cache and a 90-day local journal of the pairs sent in $HERMES_HOME/cache (the journal is deleted on nights the judge is off); the nightly spending cap ($0.05 by default) is soft; data already sent cannot be recalled and falls under the providers' retention terms. The user-run installer copies three gate scripts into $HERMES_HOME/scripts, seeds $HERMES_HOME/dreaming.json and, through Hermes' cron Python API, creates (or with --rebind re-points) two agent cron jobs bound to this plugin's own skill with only the memory toolset, plus one no_agent job (every 15 min, no model) that reads the fact stores to keep a hash index of diary lines and, for facts holographic >= 0.8.0 has forgotten, rewrites the dream's own cache files, judge files and diary without them, deletes the output files of the dream's own cron jobs that mention them (by id or verbatim text) and deletes the set-aside copies of its own broken state files; with a chat --deliver target the reports are attached as a session you can reply to. The agent runs send recent human messages (up to 200 / 40k chars, each with its chat type and sender id) and fact snippets to your configured model; state goes to $HERMES_HOME/cache and a diary to $HERMES_HOME/memories/DREAMS.md (configurable); memory files are changed by the agent only through the regular memory tool, and with the holographic provider it also adds candidate facts via fact_store (with holographic >= 0.15.0 marked said or inferred; with holographic >= 0.8.0 also change / end / correct / forget, the last three only on a human's own answer; forget is irreversible), lowers trust on human-rejected facts via fact_feedback, with holographic >= 0.15.0 raises trust (fact_feedback confirmed, +0.05, at most 10 facts a night) on facts people repeated on two or more different days and, when keywords.enabled is set (off by default), adds search keywords to facts via fact_store update. Since 3.4.0, with holographic >=0.19.0 and profile scope, it also reads fact_merges and current version ids to propose disjoint duplicate pairs. It saves immutable proposal numbers, both full texts, version ids, origins, keywords and the provider database path in cache/dream-proposals.json; open proposals expire after 180 days and closed ones are removed after 30 days. Full pair texts are included in the agent report and therefore reach the configured agent model. Old facts are merged by fact_store only after the adult memory owner approves the exact proposal; the response checks the database and uses expect to refuse changed versions. Scheduled extraction may merge only a newly added paraphrase from its own session into an existing fact, never old facts from other sessions. The scripts themselves still open the fact store read-only. The sweep also cleans the state of merged copies and archives their hashes so a later forget can remove older untagged diary copies; merging itself does not erase the diary. No new credentials, network providers or tools are introduced. Version 3.4.2 clarifies that forget cleans the store and the skill's own files; Git history, external database dumps, system backups and Hermes session history require separate cleanup. Reports distinguish a successful store deletion from a retained external copy and do not promise that retrying removes a documented history boundary. Version 3.5.0 adds explicit cron maintenance: known stock prompts are synchronized while custom prompts are preserved; --update-existing applies only explicitly supplied settings and --job-id scopes the entire operation. cron.expected_roles controls desired creation without pausing existing jobs. --upgrade validates the request before copying gate scripts and updating cron through public APIs, then checks the result. Checks expose paused jobs, execution modes, missing roles and duplicates; no automatic activation or job deletion. --inherit-model explicitly clears both model and provider pins. The public cron update API has no CAS; avoid concurrent configuration edits during installation. Version 3.6.0 adds opt-in read-only task-outcome summaries and recorded memory-attempt explanations from holographic >=0.20.0 (experience_schema=1). It reads bounded attempt/version references and agent-reported outcomes; usefulness does not change truth, trust, ranking or MEMORY.md. It makes no new model or network calls and keeps no second correction-text cache. Explicit --memory-store must be in chat_stores.promote_from; stores are never joined. task_outcomes: true adds only summary counts to the ordinary nightly result and creates no extra wakeup. Missing capability is reported as unsupported, not as a successful empty journal. Human corrections reported by the agent are not authenticated human confirmation. Version 3.6.1 reuses parsed numbers within a bounded in-memory nightly cache, reducing repeated work without changing contradiction rules. Version 3.6.2 copies the cron gate scripts atomically (an interrupted install keeps the previous gate) and names any cron job the installer refuses to change with the fix. Version 3.7.0 keeps the whole-store duplicate search within its nightly budget on large stores (it also narrows candidates by the numbers and names the pair rule requires; the rule still decides every pair) and names the store in task-outcome summaries. Version 3.7.1 derives each message's data once per nightly pass, with memory bounded by corroboration.memory_mb (default 256 MB; above it data is rebuilt on demand, never changing decisions). Version 3.7.2 makes the quarantine screen about 40× faster on long messages with byte-identical decisions (re-vendored holographic screen 0.22.1). Version 3.7.3 fixes an install-time scanner false positive in that screen's start list (3.7.2 was refused by hermes plugins install) and runs hermes plugins validate in CI. Version 3.7.4 changes no behaviour: the vendored holographic screen is copied whole and checked before it is written. Version 3.8.0 no longer promotes an agent's conclusion nobody confirmed (holographic origin inferred) to MEMORY.md by any corroboration route; people repeating it offer it for confirmation instead, and stores without origins are promoted as before; --explain says why, and --memory-explain keeps the provider's count of candidates that changed before the record. Version 3.8.4 keeps, for each memory entry, hashed word stems and numbers plus a 60-character preview (none for an entry with a secret) in the loss-guard snapshot in $HERMES_HOME/cache, so an entry the agent compressed, reworded or merged is no longer reported as lost; the alert names lost entries by that preview. Version 3.8.5 has the nightly agent change memory entries with the memory tool's patch (Hermes 0.22 removed replace; replace remains only as the fallback for Hermes 0.21), counts a patch staged in the pending/memory approval queue as waiting, and compares a lost entry only with entries the night wrote (also across a split, with numbers compared as numbers); for an entry of fewer than two word stems the snapshot also keeps hashed stems of its short words or, for one with no words and no secret, hashed character trigrams; state files with a UTF-8 BOM are read. Version 3.8.6: install.py --check counts a judge key only from its own line in $HERMES_HOME/.env, the one a cron script can read, and names DREAM_* variables set only in the terminal it runs in, compared with their lines in that .env (a DREAM_* value may be printed, a key never is); it and a new read-only dream.py --nightly-status read the dreaming jobs' next_run_at in cron/jobs.json to say when Hermes will not fire them (a gateway that is down, a job paused or with no next run). The nightly prompt never patches through another entry's whole text and keeps an absorbed entry when a merge fails; the loss-guard snapshot also keeps hashed full dates and each entry's hashed head key. No new credentials, network calls, tools or writes.Communitymemory27itpartypattayahermes-field-notesField notes for a Hermes install: search known pitfalls before debugging and record new ones with root cause; register every local core edit as a patch note with a declarative checks file, then verify read-only after each hermes update (OK / MISSING / UPSTREAMED / N/A / UNKNOWN with reason) and list core files changed outside the registry. Ships 42 pitfalls and 10 patch recipes checked against 0.22.0. Optional pinned Telegram dashboard edited in place by an hourly no_agent cron job. Portable Agent Plugins v1 package (plugin.json + skills/); no tools, hooks, middleware or env vars; never edits the core or runs patch scripts. Disclosure — its scripts only read the Hermes core (pyproject.toml, read-only git status/diff) and never edit it or run patch scripts; the skill does walk the agent through hand-editing core files from its patch recipes and re-running the owner's re-apply scripts, each only after the user says yes. Network: Telegram Bot API only when the dashboard is enabled (reuses the agent's TELEGRAM_BOT_TOKEN from env or ~/.hermes/.env), and the public GitHub API without credentials (latest release plus compare against the installed commit SHA, cached 12 h; upstream.check=false disables). Writes: the notes store (~/.hermes/field-notes), ~/.hermes/field-notes.json, state and lock files in ~/.hermes/cache, a copy of the cron script in ~/.hermes/scripts when install.py runs (the skill runs it on first use), and one hourly no_agent cron job only when the user runs install_cron.py (it reads ~/.hermes/installs/*/facts.json to find Hermes' own Python and re-runs itself with it). Without a dashboard chat, install_cron.py sends the job's alerts to the Telegram home channel when TELEGRAM_HOME_CHANNEL is set (read from env or ~/.hermes/.env), else local.Communitytools2

Developer Mode

Explore built-in Hermes toolsets and actions.

HermesAgent

Developer?

Create a Hermes extension for Desktop or agent workflows.

Developer Section