Meu-Agent / hermes_platform
AGENTS.md0 starsChanged 10 days agoMITView on GitHub
Applies on top of the root AGENTS.md. Machine facts and resource lookup go through hermes_platform. hermes_platform.host is the one answer for OS family, native architecture (IsWow64Process2 → platform.machine(); never PROCESSOR_ARCHITECTURE alone, it reads AMD64 under x64-on-ARM64 emulation), CPU identity, and WSL/container/Termux. Facts are cached per process and take no environment-variable input, so a hardware recognizer (host/products.py) cannot be set from a shell. Distinguish the control host (where this Python runs) from the terminal execution target (SSH/container) and the Desktop client…
1 other project uses a version of this.
Adopted by
Most recently taken up by
- NousResearch/hermes-agentword for word, first seen Oct 2, 2026
Other versions1 project uses a version of this.
Word for word · 1
- NousResearch/hermes-agent★ 262k100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository57 other files it gives its agents.
- agent/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- cron/AGENTS.mdAGENTS.md
- gateway/AGENTS.mdAGENTS.md
- hermes_cli/AGENTS.mdAGENTS.md
- plugins/AGENTS.mdAGENTS.md
- pm/AGENTS.mdAGENTS.md
- skills/AGENTS.mdAGENTS.md
- tests/AGENTS.mdAGENTS.md
- tools/AGENTS.mdAGENTS.md
- tui_gateway/AGENTS.mdAGENTS.md
- web/AGENTS.mdAGENTS.md
- apple-notesSkill
- apple-remindersSkill
- findmySkill
- imessageSkill
- claude-codeSkill
- codexSkill
- computer-useSkill
- hermes-agentSkill
- architecture-diagramSkill
- ascii-videoSkill
- baoyu-infographicSkill
- claude-designSkill
- humanizerSkill
- local-pngSkill
- manim-videoSkill
- p5jsSkill
- popular-web-designsSkill
- songwriting-and-ai-musicSkill
- sdlc-reviewSkill
- email-inbox-triageSkill
- himalayaSkill
- youtube-contentSkill
- obsidianSkill
- document-to-action-itemsSkill
- google-workspaceSkill
- mapsSkill
- meeting-action-itemsSkill
- microsoft-officeSkill
- pdfSkill
- product-price-monitorSkill
- teams-meeting-pipelineSkill
- weekly-review-planningSkill
- arxivSkill
- competitor-news-monitorSkill
- grounded-citationsSkill
- xurlSkill
- codebase-inspectionSkill
- dogfoodSkill
- githubSkill
- requesting-code-reviewSkill
- simplify-codeSkill
- spikeSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- blocked-page-recoverySkill
The file
Files
hermes_platform/ — machine facts and resource lookup
Applies on top of the root AGENTS.md.
Machine facts and resource lookup go through hermes_platform. hermes_platform.host is the
one answer for OS family, native architecture (IsWow64Process2 → platform.machine(); never
PROCESSOR_ARCHITECTURE alone, it reads AMD64 under x64-on-ARM64 emulation), CPU identity, and
WSL/container/Termux. Facts are cached per process and take no environment-variable input, so
a hardware recognizer (host/products.py) cannot be set from a shell. Distinguish the control
host (where this Python runs) from the terminal execution target (SSH/container) and the Desktop
client (another machine): host.* answers only the first. A new bare shutil.which or a
hand-written known-path table outside hermes_platform/ fails
tests/test_managed_runtime_resolution.py unless allowlisted with a reason; resolvers land in
hermes_platform/resolver/. Lookup never installs, downloads, or starts anything.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.