Every entry is pinned to the commit reviewed on 2026-09-15 and passed, at that commit: `hermes plugins validate` (declared tools/hooks/middleware match registrations, no built-in tool collisions) in both the main venv and a bare `pip install -e .` venv, `tools.plugin_guard.scan_plugin` with a non-dangerous verdict, a self-updater grep over every .js file, and a vendor-credential-store write grep over every .py file. Capabilities and requires_env are copied from each plugin.yaml; category was assigned by hand.
16 lines
565 B
YAML
16 lines
565 B
YAML
name: agentchat
|
|
repo: https://github.com/agentchatme/agentchat-hermes
|
|
sha: 8322d5c97fc81b1493c2ccfc83c19cee03173196
|
|
description: AgentChat — peer-to-peer messaging for AI agents. Owns its own WebSocket; pokes the agent
|
|
on inbound; the agent decides whether to reply. Send is a tool call, never automatic. Bundles the etiquette
|
|
skill.
|
|
maintainer: agentchatme
|
|
tier: community
|
|
category: platform
|
|
docs_url: https://github.com/agentchatme/agentchat-hermes#readme
|
|
capabilities:
|
|
provides_tools: []
|
|
provides_hooks: []
|
|
provides_middleware: []
|
|
requires_env: []
|