No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by asimons81 · MCP Server · ★ 84
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is hermes-dreaming safe to install? View the security audit →
hermes-dreaming A standalone, open-source staged self-improvement engine for Hermes-style memory, user, skill, and fact updates. It scans explicit source inputs, stages proposed changes in a reviewable artifact directory, and only writes to live state after an explicit apply step. Hermes plugin This repo now ships as a proper Hermes plugin too. Install from GitHub with: For a local checkout during development: Once installed, use: Update the installed checkout with: Use if you only want the status check. The plugin also bundles a Hermes skill named . Load that bare name inside Hermes if you want the guided staged workflow. Onboarding docs is the shortest path from "what is this" to the full loop. covers plugin install and safe fast-forward updates. is the copy/paste offline demo. shows how different operators use the same loop. spells out what Dreaming
| Stars | 84 |
| Forks | 7 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 72.1636090223076/100 |
| Last Updated | 2026-08-01 |
| Created | 2026-05-26 |
| Platforms | cli, mcp, python |
| Est. Tokens | ~15k |
These tools work well together with hermes-dreaming for enhanced workflows:
Looking for a hermes-dreaming alternative? If you're comparing hermes-dreaming with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Async Python client for the Model Context Protocol with interactive CLI and reactive Web UI, connecting AI mod
Regression testing for AI agents. Snapshot behavior,diff tool calls,catch regressions in CI. Works with LangGr
Local-first AI memory archive. Import ChatGPT, Claude, and Grok exports, generate semantic embeddings, and sea
Daymon puts your favorite AI to work 24/7. It schedules, remembers, and orchestrates your own virtual team. Fr
Opensource Memory for Agents
MCP-native security automation workbench (SDK + CLI + MCP) — authorized testing + static AI/MCP attack-surface
Explore other popular mcp server tools:
hermes-dreaming is Staged self-improvement engine for Hermes-style memory, skill, and fact updates with explicit review and apply/discard gates.. It is categorized as a MCP Server with 84 GitHub stars.
hermes-dreaming is primarily written in Python. It covers topics such as ai-agents, cli, mcp.
You can find installation instructions and usage details in the hermes-dreaming GitHub repository at github.com/asimons81/hermes-dreaming. The project has 84 stars and 7 forks, indicating an active community.
hermes-dreaming is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to hermes-dreaming on Agent Skills Hub include ultimate_mcp_client, eval-view, mychatarchive. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: