mumo (Hermes Agent)
Runs a multi-model deliberation across models from different labs (Claude, GPT, Gemini, Grok, DeepSeek, Kimi, and more) via mumo's MCP server, returning full responses plus typed cross-model reactions. Use when independent perspectives are needed on architecture/product decisions, design and pla
as observed 2026-11-22T06:34:16.981Z- Identifier
mumo-hermes- Source
- ClawHub
- Version observed
- 0.10.0
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-09-09T11:17:27.097Z
- Observations recorded
- 5
- Installs (reported upstream)
- 1
- Weekly downloads (upstream)
- 646
- Declared license
- MIT-0
Observation history
2026-11-22T06:34:16.981Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"The skill now says \"reactions\" where it said \"claim map\", reads the four groups the tools print (Contested, Open, Pivotal, Kept), and puts the user between rounds: summarize e | "Setup now uses a browser sign-in: hermes mcp add mumo --url https://mumo.chat/api/mcp/oauth --auth oauth, allow access in the browser, answer Y to enable the tools. No API key is |
latestVersion |
"0.8.0" | "0.10.0" |
2026-11-21T05:34:10.121Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"New tool: ask_a_model puts a question to one model of your choice. It is added to tools.include in config/mumo.yaml; existing installs must add it to ~/.hermes/config.yaml and res | "The skill now says \"reactions\" where it said \"claim map\", reads the four groups the tools print (Contested, Open, Pivotal, Kept), and puts the user between rounds: summarize e |
latestVersion |
"0.7.0" | "0.8.0" |
2026-11-20T04:34:16.795Z
Fields that differed: license changelog description latestVersion
| Field | Before | After |
|---|---|---|
license |
null | "MIT-0" |
changelog |
"Credential hygiene: the MCP config references ${MUMO_API_KEY} resolved from ~/.hermes/.env instead of carrying a literal-key placeholder. Adds an end-to-end 'hermes mcp test mumo' | "New tool: ask_a_model puts a question to one model of your choice. It is added to tools.include in config/mumo.yaml; existing installs must add it to ~/.hermes/config.yaml and res |
description |
"Runs a multi-model deliberation across models from different labs (Claude, GPT, Gemini, Grok, DeepSeek, Kimi, and more) via mumo's MCP server, returning full responses plus typed | null |
latestVersion |
"0.6.3" | "0.7.0" |
2026-09-10T12:18:05.764Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"0.6.2: display name restored; install command uses the clawhub/mumo-hermes form the Hermes catalog generates." | "Credential hygiene: the MCP config references ${MUMO_API_KEY} resolved from ~/.hermes/.env instead of carrying a literal-key placeholder. Adds an end-to-end 'hermes mcp test mumo' |
latestVersion |
"0.6.2" | "0.6.3" |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.