Agent Dreaming Agnostic
Memory-agnostic background consolidation — reviews sessions, scores candidates, promotes durable insights to the active memory backend (built-in MEMORY.md or Holographic). Three-phase (Light/Deep/Condensation/REM). Run via cron or manually.
Install
npx skills add nexus9888/hermes-memory-skills --skill agent-dreaming-agnosticgit clone --depth 1 https://github.com/nexus9888/hermes-memory-skills.git /tmp/hermes-memory-skills
mkdir -p ~/.claude/skills
cp -r /tmp/hermes-memory-skills/agent-dreaming-agnostic ~/.claude/skills/agent-dreaming-agnosticPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Agent Dreaming (Memory-Agnostic)
Three-phase background memory consolidation that auto-detects the active memory
backend (built-in MEMORY.md or Holographic) and routes Phase 2 promotions to the
correct tools. Condensation (formerly `memory-lean-check`) is built into the
dreaming lifecycle as Phase 2.5.
**When to run:** Scheduled cron (recommended: every 6–8 hours) or manually after
a burst of activity.
**Autonomous vs interactive:** Light and Deep phases run autonomously in both
cron and manual modes. REM phase sends a message to the user with proposed
structural actions and waits for response — it never creates wiki pages or skills
without approval.
---
## Phase 0: Backend Detection (NEW — run first)
Before any dreaming work, determine which memory backend is active. This
determines which tools you use in Phase 2.
### Steps
1. **Read the active memory provider** from `$HERMES_HOME/config.yaml`:
```bash
grep -A10 "^memory:" $HERMES_HOME/config.yaml | grep "provider:" | awk '{print $2}'
```
Or read the config and check `memory.provider`.
2. **Set backend mode:**
| Config value | Backend | Tools to use in Phase 2 | Threshold check |
|---|---|---|---|
| `""` (empty) or `null` or absent | **built-in** | `memory(action='add'|'replace'|'remove')` | Char limit (60%/80% of 2,200) |
| `holographic` | **holographic** | `fact_store(action='add'|'update'|'remove')` + `fact_feedback(action='helpful'|'unhelpful')` | Trust score (min 0.3 default) |Details
- Skill name
agent-dreaming-agnostic- Repository
- nexus9888/hermes-memory-skills
- Path
agent-dreaming-agnostic/SKILL.md- Repo updated
- 3 June 2026
FAQ
What does the Agent Dreaming Agnostic skill do?
Memory-agnostic background consolidation — reviews sessions, scores candidates, promotes durable insights to the active memory backend (built-in MEMORY.md or Holographic). Three-phase (Light/Deep/Condensation/REM). Run via cron or manually.
How do I install the Agent Dreaming Agnostic skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add nexus9888/hermes-memory-skills --skill agent-dreaming-agnostic. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Agent Dreaming Agnostic popular?
It lives in nexus9888/hermes-memory-skills, which has 49 GitHub stars and 5 forks.
Related skills
Agent Dreaming
49nexus9888/hermes-memory-skills
DEPRECATED — use agent-dreaming-agnostic instead. Background memory consolidation for built-in MEMORY.md only.
AI Assessment Scale
74mastepanoski/claude-skills
Evaluate AI contribution in software projects using the AI Assessment Scale (AIAS) v2 5-level framework. Adapt the education-focused framework for transparent project documentation across development stages.
Iso 42001 AI Governance
74mastepanoski/claude-skills
AI governance readiness and gap assessment using ISO/IEC 42001:2023. Evaluate AI management-system practices for risk management, accountability, transparency, security, and continuous improvement.
R00 ComposioHQ Awesome Claude Skills Datascience
50Tameoltreasure34/r08-composiohq-awesome-claude-skills-datascience
🤖 Data Science & AI/ML skill suite derived from ComposioHQ/awesome-claude-skills. Data pipelines, model training, evaluation, MLOps and analytical reporting. Provides 10 specialised commands for data-science, machine-learning, analytics workflows.
Nist AI Rmf
74mastepanoski/claude-skills
AI risk assessment using NIST AI RMF 1.0 framework. Evaluate AI systems across 4 core functions (Govern, Map, Measure, Manage) for trustworthy and responsible AI deployment.
Humanizer
66aparente/claude-skills
Rewrite text that sounds AI-generated while keeping the writer's facts, meaning, and voice. Use when editing or reviewing prose for inflated claims, sales language, vague sources, repetitive structure, stock AI words, passive voice, filler, or chatbot artifacts. Based on Wikipedia's "Signs of AI writing.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.