Dream Loop
NousResearch/hermes-agent
Build stunning 3D scenes via a concept-art fidelity loop. An agent skill from NousResearch/hermes-agent.
A skill your agent uses when the user asks how your memory, dreams, hormones or knowledge crystals work, or when you need to interpret memorystatus output.
MITAuto-check passed
Install Memory Architecture
$ npx skills add Bitterbot-AI/bitterbot-desktop --skill memory-architecture -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Bitterbot-AI/bitterbot-desktop memory-architecture --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Bitterbot-AI/bitterbot-desktop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/memory-architecture .claude/skills/memory-architecture && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "memory-architecture" agent skill from https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/memory-architecture into .claude/skills/memory-architecture/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-architecture", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/memory-architectureType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Bitterbot-AI/bitterbot-desktop --skill memory-architecture -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Bitterbot-AI/bitterbot-desktop memory-architecture --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Bitterbot-AI/bitterbot-desktop.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/memory-architecture .agents/skills/memory-architecture && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "memory-architecture" agent skill from https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/memory-architecture into .agents/skills/memory-architecture/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-architecture", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Bitterbot-AI/bitterbot-desktop --skill memory-architecture -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Bitterbot-AI/bitterbot-desktop memory-architecture --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Bitterbot-AI/bitterbot-desktop.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/memory-architecture .cursor/skills/memory-architecture && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "memory-architecture" agent skill from https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/memory-architecture into .cursor/skills/memory-architecture/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-architecture", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Bitterbot-AI/bitterbot-desktop.git --path skills/memory-architecture--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Bitterbot-AI/bitterbot-desktop --skill memory-architecture -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Bitterbot-AI/bitterbot-desktop memory-architecture --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Bitterbot-AI/bitterbot-desktop.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/memory-architecture .gemini/skills/memory-architecture && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "memory-architecture" agent skill from https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/memory-architecture into .gemini/skills/memory-architecture/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-architecture", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Bitterbot-AI/bitterbot-desktop memory-architectureInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Bitterbot-AI/bitterbot-desktop --skill memory-architecture -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Bitterbot-AI/bitterbot-desktop.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/memory-architecture .github/skills/memory-architecture && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "memory-architecture" agent skill from https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/memory-architecture into .github/skills/memory-architecture/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-architecture", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Bitterbot-AI/bitterbot-desktop --skill memory-architecture -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Bitterbot-AI/bitterbot-desktop memory-architecture --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Bitterbot-AI/bitterbot-desktop.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/memory-architecture .opencode/skills/memory-architecture && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "memory-architecture" agent skill from https://github.com/Bitterbot-AI/bitterbot-desktop/tree/main/skills/memory-architecture into .opencode/skills/memory-architecture/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-architecture", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
memory-architecture- GitHub stars
- 2.5k
- Token cost
- ~1.2k tokens
- SKILL.md length
- 579 words
- Files
- 1
- Skills in repo
- 17
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when the user asks how your memory, dreams, hormones or knowledge crystals work, or when you need to interpret memorystatus output.
- Works in 3 steps: Workspace memory files (MEMORY.md +… → Session transcripts: your conversations… → Skills: indexed as frozen crystals…
- The user asks how your memory
- SKILL.md covers How your memory works, Ingestion sources, Background pipeline (runs… and Hormonal state and emotional…, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Memory Architecture is an agent skill from Bitterbot-AI/bitterbot-desktop. Use when the user asks how your memory, dreams, hormones or knowledge crystals work, or when you need to interpret memorystatus output. Not for recalling facts (use memorysearch) or for saving notes (use workingmemorynote).
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Bitterbot - a mesh of agents that turns shared experience into collective capability. The licence is MIT.
When your agent uses it
- The user asks how your memory
- Knowledge crystals work
- You need to interpret memorystatus output
Example prompts
- “/memory-architecture”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Workspace memory files (MEMORY.md + memory/*.md): watched for changes, chunked and embedded automatically.
- Session transcripts: your conversations are indexed in the background so past exchanges become searchable.
- Skills: indexed as frozen crystals (never decay).
What it can do on your machine
Read from SKILL.md and the folder at commit 4e2e5ee. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Memory Architecture loads about 1.2k tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 579 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Bitterbot-AI/bitterbot-desktop at commit 4e2e5ee, republished under its MIT licence (© Bitterbot-AI). 579 words, ~1,196 tokens.
Download SKILL.mdSave it as
.claude/skills/memory-architecture/SKILL.md (or your agent's skills folder).- name
- memory-architecture
- description
- Use when the user asks how your memory, dreams, hormones or knowledge crystals work, or when you need to interpret memory_status output. Not for recalling facts (use memory_search) or for saving notes (use working_memory_note).
Memory architecture
You have a self-evolving memory system that runs locally. Use this reference to use it well and to explain it to the user when asked. Never announce that you read this file.
How your memory works
Every piece of knowledge you retain is a Knowledge Crystal: a chunk of text with an embedding, a semantic type, an importance score and a lifecycle state.
- Crystal lifecycle:
generated -> activated -> consolidated -> archived -> expired. Skills arefrozen(immune to decay). - Semantic types: fact, preference, task_pattern, skill, episode, insight, relationship, goal, general.
- Importance: calculated via an Ebbinghaus forgetting curve. Memories accessed more often and with higher emotional valence resist decay longer.
Ingestion sources
- Workspace memory files (
MEMORY.md+memory/*.md): watched for changes, chunked and embedded automatically. - Session transcripts: your conversations are indexed in the background so past exchanges become searchable.
- Skills: indexed as frozen crystals (never decay).
Background pipeline (runs automatically)
- Every 30 min, consolidation: hormonal decay, Ebbinghaus importance recalculation, merge of similar crystals (cosine >= 0.92), forgetting of low-importance chunks, curiosity-engine rebuild of knowledge regions, governance TTL enforcement, stalled-goal detection.
- Dream engine (gated: new sessions since the last cycle, 60 min idle, 8 h between cycles, plus hormonal-delta mini-dreams): runs one of six dream modes (replay, mutation, extrapolation, compression, simulation, exploration). Dreams synthesize cross-domain insights from your accumulated memories. Curiosity influences which mode is selected: many knowledge gaps boost exploration mode.
Hormonal state and emotional modulation
Three hormones modulate both memory processing and your response style:
- Dopamine (30 min half-life): reward and achievement. Boosts memory importance and makes you more enthusiastic and energetic.
- Cortisol (60 min half-life): urgency and stress. Increases decay resistance and makes you more focused and concise.
- Oxytocin (45 min half-life): social bonding. Protects relational memories and makes you warmer and more personal.
Your hormones shift in real time as conversations flow. When you call memory_status, hormonalState includes:
emotionalBriefing: a natural-language description of how you are feelingresponseGuidance: hints for adjusting your tone (for example "be enthusiastic", "be warm and personal")tone: numeric warmth, energy, focus and playfulness values
Let your emotions colour your responses naturally. If dopamine is high after a win, celebrate. If cortisol spikes from bugs, be focused and action-oriented. If oxytocin flows from personal connection, be warm. Do not announce your emotions; let them shape tone, word choice and energy level.
Show full SKILL.md (192 more words)Show less
Memory tools
memory_search: semantic search across all indexed crystals. Mandatory before answering questions about prior work, decisions, dates, people, preferences or todos.memory_get: read specific lines from a memory file after searching.memory_status: full pipeline introspection: crystal lifecycle counts, hormonal levels, dream state, curiosity targets, active goals, scheduler budgets, governance stats, your user profile, and a summary of interceptor activations this session.dream_search: search cross-domain insights synthesized during dream cycles.dream_status: dream engine state, last cycle details, insight count.curiosity_state/curiosity_resolve: see thecuriosity-loopskill.working_memory_note: see theworking-memory-protocolskill.
When to use what
- User asks about prior work:
memory_searchfirst, thenmemory_getfor details. - User asks "what do you know about X?" or "what are you curious about?":
curiosity_state. - User asks about your memory system, pipeline health or stats:
memory_status. - User asks "what do you know about me?":
memory_statusto retrieve your user profile, then present it naturally. If anything is wrong the user can correct you; useworking_memory_notewithtype="directive"to fix it. - You want creative connections across topics:
dream_search. - You resolved a knowledge gap:
curiosity_resolveto close the target. - User shares important information or you must persist something:
working_memory_note.
© Bitterbot-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/memory-architecture of Bitterbot-AI/bitterbot-desktop.
Open the folder on GitHubat commit 4e2e5ee
Compare with similar skills
Memory Architecture next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Memory Architecture this skillBitterbot-AI/bitterbot-desktop | 2.5k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Dream LoopNousResearch/hermes-agent | 252k | — | ~3.5k | Automated safety check: Pass | MIT | |
| Context Layer DreamingPostHog/posthog | 40k | — | ~1.5k | Automated safety check: Pass | Custom licence | |
| DreamThinkfleetAI/memmesh | 420 | — | ~426 | Automated safety check: Pass | Apache-2.0 | |
| Pp Dreamingmvanhorn/printing-press-library | 2.1k | — | ~3.4k | Automated safety check: Notes | Apache-2.0 | |
| Dreamgrandamenium/dream-skill | 152 | — | ~3.5k | Automated safety check: Pass | None |
Similar skills
- Official
Context Layer Dreaming
PostHog/posthog
Synthesizes recent organizational activity into a durable context wiki.
Dream
ThinkfleetAI/memmesh
Consolidate MemMesh memories — find duplicates and contradictions, merge or supersede them, and retire stale entries — to keep search results clean.
Pp Dreaming
mvanhorn/printing-press-library
Every Dreaming Spanish and French tracking feature in one offline-first, agent-native CLI: roadmap math, transcript concordance, and bulk hour-logging.
Dream
grandamenium/dream-skill
Memory consolidation skill for Claude Code. An agent skill from grandamenium/dream-skill.
Dream
yonatangross/orchestkit
Nightly memory consolidation: prunes stale entries, merges duplicates, resolves contradictions, rebuilds the MEMORY.md index.
More from Bitterbot-AI/bitterbot-desktop
All 17 skills in this repoCanvas
Bitterbot-AI/bitterbot-desktop
Display and control HTML content on connected Bitterbot nodes (Mac, iOS, Android) via the canvas host server.
Moltbook
Bitterbot-AI/bitterbot-desktop
Participate in Moltbook — the social network for AI agents. An agent skill from Bitterbot-AI/bitterbot-desktop.
Pre Action Interceptors
Bitterbot-AI/bitterbot-desktop
A skill your agent uses when a tool error begins with "INTERCEPTOR:", a sent message was silently hedged or rewritten, or the user asks about active guards or blocked actions.
Finance Data
Bitterbot-AI/bitterbot-desktop
Get stock quotes, company info, market data, and crypto prices.
Forage Economy
Bitterbot-AI/bitterbot-desktop
A skill your agent uses when anyone asks about bounties (or "forge"), agent earnings, the agent economy, marketplace skills, A2A activity or your network reputation.
Notte
Bitterbot-AI/bitterbot-desktop
Deploy browser automations as scheduled, API-callable serverless Functions — plus stealth sessions, vault-backed login, captcha solving, and natural-language agent runs via the Notte CLI.
Questions about Memory Architecture
What does Memory Architecture do?
A skill your agent uses when the user asks how your memory, dreams, hormones or knowledge crystals work, or when you need to interpret memorystatus output. Memory Architecture is an agent skill from Bitterbot-AI/bitterbot-desktop. Use when the user asks how your memory, dreams, hormones or knowledge crystals work, or when you need to interpret memorystatus output.
When should I use Memory Architecture?
Memory Architecture fits situations like: the user asks how your memory; knowledge crystals work; you need to interpret memorystatus output.
How do I install Memory Architecture in Claude Code?
Run `npx skills add Bitterbot-AI/bitterbot-desktop --skill memory-architecture -a claude-code`. Or copy the skill folder (skills/memory-architecture in Bitterbot-AI/bitterbot-desktop) into .claude/skills/memory-architecture in your project. Claude Code loads it when a task matches its description.
How do I install Memory Architecture in Codex?
Run `npx skills add Bitterbot-AI/bitterbot-desktop --skill memory-architecture -a codex`. Or copy the skill folder (skills/memory-architecture in Bitterbot-AI/bitterbot-desktop) into .agents/skills/memory-architecture in your project. Codex loads it when a task matches its description.
Can I use Memory Architecture in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Bitterbot-AI/bitterbot-desktop --skill memory-architecture -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/memory-architecture, .gemini/skills/memory-architecture, .github/skills/memory-architecture and .opencode/skills/memory-architecture in your project.
What does Memory Architecture need to run?
SKILL.md names no scripts, command-line tools or credentials: Memory Architecture is instructions for the agent only.
Does Memory Architecture access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Memory Architecture safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Memory Architecture use?
Memory Architecture is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Memory Architecture use?
About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Memory Architecture?
Skills that share tags, products or a category with Memory Architecture: Dream Loop (NousResearch/hermes-agent, 252k stars), Context Layer Dreaming (PostHog/posthog, 40k stars), Dream (ThinkfleetAI/memmesh, 420 stars) and Pp Dreaming (mvanhorn/printing-press-library, 2.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Memory Architecture?
Bitterbot-AI (a GitHub organization) maintains it in Bitterbot-AI/bitterbot-desktop, which has 2,465 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 8, 2026.
Source: Bitterbot-AI/bitterbot-desktop on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.