Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/zhhjluka/hm-arch/hermesgit clone --depth 1 https://github.com/zhhjluka/hm-archWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/zhhjluka/hm-arch/hermes)<a href="https://agentmods.dev/agents/zhhjluka/hm-arch/hermes"><img src="https://agentmods.dev/badge/agents/zhhjluka/hm-arch/hermes.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00859 |
| Opus 5 | $0.00000 | $0.00430 |
| Sonnet 5 | $0.00000 | $0.00172 |
| Haiku 4.5 | $0.00000 | $0.00086 |
Grade A, and why
hermes scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes Agent setup (HM-Arch)
Install HM-Arch and configure Hermes to use the native HM-Arch Memory Provider.
Hermes integration uses native plugin registration. hm-arch install hermes
creates the HM-Arch plugin bridge, updates $HERMES_HOME/config.yaml, and
initializes the SQLite database.
Install HM-Arch
From a GitHub Release wheel (current v2.0.4):
python3.12 -m venv .venv && source .venv/bin/activate
python -m pip install --upgrade pip
python -m pip install /path/to/hm_arch-2.0.4-py3-none-any.whl
From PyPI:
pip install hm-arch
# or:
pipx install hm-arch
From npm:
npm install -g @hm-arch/installer
The npm package can install and diagnose Hermes through its managed runtime:
hm-arch-install install hermes
hm-arch-install status hermes
hm-arch-install doctor hermes
Hermes home
Hermes reads configuration from:
$HERMES_HOME/config.yamlwhenHERMES_HOMEis set, or~/.hermes/config.yamlby default
export HERMES_HOME="${HERMES_HOME:-$HOME/.hermes}"
mkdir -p "$HERMES_HOME"
Configure HM-Arch
Recommended:
hm-arch install hermes
# or:
hm-arch-install install hermes
Then restart Hermes so the running agent process loads the provider plugin.
Manual equivalent:
Edit $HERMES_HOME/config.yaml. Example minimal configuration:
memory:
provider: hm-arch
plugins:
hm-arch:
db_path: hm_arch_memory.db
memory.provider: hm-archselects the HM-Arch Memory Provider.plugins.hm-arch.db_pathis relative toHERMES_HOMEunless you use an absolute path. Default database file:hm_arch_memory.dbunder Hermes home.
Enable the HM-Arch plugin in Hermes Agent per Hermes documentation (plugin
discovery uses the installed hm_arch package and
hm_arch.integrations.hermes.register).
Provider conflicts
If another external provider is already configured (e.g. mem0), HM-Arch refuses
to register silently. Set memory.provider to hm-arch explicitly when you
intend to switch.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 152 lines · 0 tokens per session scan A a7bfefee66a0
hermes is an agent published in the GitHub repository zhhjluka/hm-arch (18 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 859 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
history-management
The runtime keeps conversation history for each agent session and sends a provider-facing working history to the model. Two complementary limits operate on different representations.
design-reviewer
Design-review sub-agent. Reviews design docs across the four dimensions of architecture, interface, performance, and security, covering MemOS's multi-memory / multi-storage backend constraints.
integration-tester
MemOS integration-testing sub-agent. Authors and executes pytest cases under tests/ based on the task's requirements and design, and emits real test reports.
explorer
Read-only code exploration sub-agent. Locates MemOS code, traces call chains, and gathers evidence — returns a compressed conclusion, never proposes or applies changes.
Agent Prompt: Dream memory consolidation
Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.
lessons-learned
Hard-won knowledge from building this codebase. When you make a mistake or discover a non-obvious behavior, add it here.