How do I install the Hermes Bridge skill?

Run npx skillmds@latest add zedarvates/hermes-bridge in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Hermes Bridge safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Hermes Bridge?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Hermes Bridge free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Hermes Bridge?

zedarvates (@zedarvates) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Hermes Bridge by zedarvates — Agent Skill

Name: Hermes Bridge
Author: zedarvates

Hermes Bridge

Expose routing, local chat, fusion, skill search, infrastructure advice, and privacy-safe QA run manifests to Hermes-Agent or another OpenAI-function-calling framework, plus a one-call MCP config generator. Use when connecting botte-secrète's routing and evidence contracts to another agent framework.

zedarvates 00a8ddd 8 files · 24.3 KB Updated Sep 17, 2026

File contents

hermes_bridge — connect the belt to another agent framework

botte-secrète already runs a standard MCP server (skills.llm_mcp.server, stdio JSON-RPC). If the target framework speaks MCP, that's the whole integration — no code in this module runs:

python -m skills.hermes_bridge.cli config --cwd /path/to/botte-secrete
# → paste the printed {"mcpServers": {...}} block into the framework's MCP config

This module exists for frameworks — [[hermes-second-brain]] among them — that instead expect a flat list of OpenAI-function-calling tool specs + a dispatcher, a common shape for agents built before/without MCP support.

python -m skills.hermes_bridge.cli schemas          # focused tool specs, OpenAI-shaped
python -m skills.hermes_bridge.cli call botte_auto_route --prompt "rename x to y"

from skills.hermes_bridge import TOOL_SCHEMAS, dispatch

# register TOOL_SCHEMAS with the framework's tool-calling mechanism, then:
dispatch("botte_auto_route", {"prompt": "..."})   # → JSON string, same shape as the MCP tool

Focused tools

Deliberately a subset of the ~35-tool MCP surface — the ones that matter for a second-brain / routing integration:

tool	what it does
`botte_auto_route`	decide local-vs-cloud (0 tokens); `execute=true` to actually run it
`botte_local_chat`	run a prompt on a local model — 0 cloud tokens
`botte_fusion`	cascade / draft_refine / vote — models collaborating
`botte_find_skills`	0-token local search over installed skill catalogs
`botte_infra_tips`	hardware/software setup advice for running local models
`botte_qa_agent_run`	emit a strict private run outcome without trusting agent self-report

Why this matters for a second-brain agent

Every task [[hermes-second-brain]] would otherwise send straight to its own model gets a chance to resolve locally or via the cheapest capable tier first — see [[bench]] for the measured (not asserted) savings from that. botte_find_skills also gives Hermes 0-token access to the local skill catalog instead of re-deriving capabilities from scratch each session.

Related: [[llm_mcp]] (the native MCP server this bridges from), [[auto_router]], [[bench]] (the proof), docs/integrations/hermes.md (the full integration write-up).

---name: hermes-bridgedescription: Expose routing, local chat, fusion, skill search, infrastructure advice, and privacy-safe QA run manifests to Hermes-Agent or another OpenAI-function-calling framework, plus a one-call MCP config generator. Use when connecting botte-secrète's routing and evidence contracts to another agent framework.---# hermes_bridge — connect the belt to another agent frameworkbotte-secrète already runs a standard MCP server (`skills.llm_mcp.server`,stdio JSON-RPC). If the target framework speaks MCP, **that's the wholeintegration** — no code in this module runs:```bashpython -m skills.hermes_bridge.cli config --cwd /path/to/botte-secrete# → paste the printed {"mcpServers": {...}} block into the framework's MCP config```This module exists for frameworks — [[hermes-second-brain]] among them — thatinstead expect a flat list of OpenAI-function-calling tool specs + adispatcher, a common shape for agents built before/without MCP support.```bashpython -m skills.hermes_bridge.cli schemas # focused tool specs, OpenAI-shapedpython -m skills.hermes_bridge.cli call botte_auto_route --prompt "rename x to y"``````pythonfrom skills.hermes_bridge import TOOL_SCHEMAS, dispatch# register TOOL_SCHEMAS with the framework's tool-calling mechanism, then:dispatch("botte_auto_route", {"prompt": "..."}) # → JSON string, same shape as the MCP tool```## Focused toolsDeliberately a subset of the ~35-tool MCP surface — the ones that matter fora second-brain / routing integration:| tool | what it does ||------|----------------|| `botte_auto_route` | decide local-vs-cloud (0 tokens); `execute=true` to actually run it || `botte_local_chat` | run a prompt on a local model — 0 cloud tokens || `botte_fusion` | cascade / draft_refine / vote — models collaborating || `botte_find_skills` | 0-token local search over installed skill catalogs || `botte_infra_tips` | hardware/software setup advice for running local models || `botte_qa_agent_run` | emit a strict private run outcome without trusting agent self-report |## Why this matters for a second-brain agentEvery task [[hermes-second-brain]] would otherwise send straight to its ownmodel gets a chance to resolve locally or via the cheapest capable tierfirst — see [[bench]] for the measured (not asserted) savings from that.`botte_find_skills` also gives Hermes 0-token access to the local skillcatalog instead of re-deriving capabilities from scratch each session.Related: [[llm_mcp]] (the native MCP server this bridges from), [[auto_router]],[[bench]] (the proof), `docs/integrations/hermes.md` (the full integration write-up).

Frequently asked questions