hermes-kit
llms.txt1 starsChanged 50 days agoMITView on GitHub
Hermes Agent plugins, Hermes-oriented skills, and docs for a patched Hermes fork (Feishu customizations) and a memory write-gate method. skills/ and plugins/ are generated from a private source by allowlist export; do not hand-edit them.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-hotspot-digestSkill
- convert-documents-to-markdownSkill
- cursor-cliSkill
- desktop-browser-chromeSkill
- feishu-chat-style-reviewSkill
- feishu-ui-feedbackSkill
- figma-copy-proofreadSkill
- hermes-daily-reviewSkill
- hermes-upstream-checkSkill
- writing-with-cursorSkill
The file
Files
# hermes-kit > Hermes Agent plugins, Hermes-oriented skills, and docs for a patched Hermes fork (Feishu customizations) and a memory write-gate method. skills/ and plugins/ are generated from a private source by allowlist export; do not hand-edit them. ## Start here - [README](https://github.com/Adonis0123/hermes-kit/blob/main/README.md): overview, quick start per host, contents - [AGENTS.md](https://github.com/Adonis0123/hermes-kit/blob/main/AGENTS.md): install table per host, layout, naming rules, validation - [Install](https://github.com/Adonis0123/hermes-kit/blob/main/docs/install.md): Hermes plugins and skills, Claude Code marketplace, npx skills, pinning, updating ## Docs - [Hermes fork](https://github.com/Adonis0123/hermes-kit/blob/main/docs/hermes-fork.md): what the fork is, install, how hermes update follows it, switching back - [Feishu customizations](https://github.com/Adonis0123/hermes-kit/blob/main/docs/feishu-customizations.md): behavior and config keys of each fork patch - [Memory method](https://github.com/Adonis0123/hermes-kit/blob/main/docs/memory-method.md): what belongs in MEMORY.md, USER.md, SOUL.md - [Glossary](https://github.com/Adonis0123/hermes-kit/blob/main/CONTEXT.md): overlay, source repo, export allowlist, tap, marketplace ## Guides - [Memory provider adoption gate](https://github.com/Adonis0123/hermes-kit/blob/main/docs/memory-provider-adoption-gate.md): hot/warm/cold memory tiers, trigger conditions for an external memory provider - [Feishu gateway black-box checklist](https://github.com/Adonis0123/hermes-kit/blob/main/docs/feishu-gateway-blackbox-checklist.md): six manual checks with message-id evidence - [Quiet delivery in Feishu groups](https://github.com/Adonis0123/hermes-kit/blob/main/docs/feishu-quiet-group-delivery.md): one message per task, topics, noise controls, fork-only settings marked - [Remote lock screen design](https://github.com/Adonis0123/hermes-kit/blob/main/docs/hermes-lock-screen-design.md): authorization, execution, and verification for the hermes-lock-screen plugin - [Cron digest pipeline pattern](https://github.com/Adonis0123/hermes-kit/blob/main/docs/cron-digest-pipeline-pattern.md): thin pipeline, hard filter + soft score, 7-day dedup, single-channel fallback - [Upgrade-safe customization](https://github.com/Adonis0123/hermes-kit/blob/main/docs/upgrade-safe-customization.md): what survives hermes update, where customizations belong, overlay tests ## Decisions - [ADR 0001](https://github.com/Adonis0123/hermes-kit/blob/main/docs/adr/0001-private-source-allowlist-export.md): private source repos, published by allowlist export - [ADR 0002](https://github.com/Adonis0123/hermes-kit/blob/main/docs/adr/0002-fork-overlay-via-rebase.md): fork overlay re-applied by rebase ## Related - [adonis-skills](https://github.com/Adonis0123/adonis-skills): agent-agnostic skills and recommended third-party skills - [Adonis0123/hermes-agent](https://github.com/Adonis0123/hermes-agent): the patched Hermes fork - [NousResearch/hermes-agent](https://github.com/NousResearch/hermes-agent): upstream Hermes Agent
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.