By lsetiawan
Personal Brain OS — markdown vault personal operating system. File-per-entity with [[wiki links]], works with Obsidian, Logseq, or Claude Code alone. Persistent identity, voice, knowledge, relationships, and episodic memory for research software engineers and startup founders.
Scaffold a new Brain OS markdown vault with all module directories, entity templates, config files, and git-crypt encryption
Create an implementation plan based on research findings, with Brain OS context awareness
Execute an implementation plan phase by phase, with progress tracking
Initialize a Thoughts working-memory repository for deep work sessions alongside Brain OS
Create or append to today's daily note with wellness scores and reflection
Searches Brain OS for relevant prior knowledge — heuristics, decisions, failures, ADRs, and cross-domain wellness context. Use during research, planning, and implementation to surface what you already know.
Scans recent Thoughts artifacts for knowledge worth promoting to Brain OS. Identifies decisions, patterns, debugging insights, contacts, and content ideas that should become permanent knowledge.
Finds and summarizes relevant artifacts in the Thoughts working-memory repository. Use when you need to locate research documents, plans, or notes from recent work sessions.
Use this skill when the user asks to "score an idea", "write a blog post", "draft a thread", "create newsletter", "content calendar", "check ideas pipeline", "save bookmark", "learning notes", "content gap", "what should I write about", "draft content", "idea scoring", "publish post", "content metrics", or mentions content ideas, drafts, bookmarks, learning, content strategy, content pillars, or publishing workflow.
Use this skill when the user asks to "log ADR", "architecture decision", "debugging session", "tech debt", "code patterns", "project status", "log this bug fix", "what did I decide about", "engineering decisions", "code review notes", "snippets", or mentions ADR, debugging log, tech-debt tracking, engineering patterns, project tracking, or architecture decisions.
Use this skill when the user asks to "look up contact", "prepare for meeting", "log interaction", "stale contacts", "who is", "when did I last talk to", "meeting prep", "add contact", "network check", "relationship", "circles", "introduction", or mentions contacts, meetings, interactions, relationship management, CRM, or networking.
Use this skill when the user asks about "goals", "heuristics", "decisions", "failures", "promote", "weekly review", "metrics", "memory", "past decisions", "experiences", "rhythms", "deadlines", "active contexts", "what did I decide", "why did I choose", "lessons learned", "rules of thumb", "what's on my plate", "my schedule", "quarterly review", "progress check", "what failed", "what worked", or mentions goals, todos, metrics, rhythms, deadlines, decisions, heuristics, failures, experiences, promotion, or active contexts.
Use this skill when the user asks to "check my voice", "write a post", "write content", "check my brand", "anti-patterns", "what's my bio", "bio variants", "writing style", "brand positioning", "my values", "my tone", "vocabulary", "personal brand", "identity", "who am I professionally", "how do I come across", "update my bio", "brand pillars", or mentions voice, tone, identity, personal brand, positioning, bio, or writing guidelines.
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin monorepo for AI-augmented personal knowledge management.
A markdown vault personal operating system for research software engineers and startup founders. Manage identity, voice, knowledge, relationships, and episodic memory — all in plain files, readable by Claude Code and Obsidian alike.
Core architecture: file-per-entity with YAML frontmatter, [[wiki links]], and a two-repo design:
~/brain/ — Persistent long-term memory (git-versioned, append-only)thoughts/ — Working memory for the current project (read-write)/bootstrap, /weekly-review, /meeting-prep, /write-blog, /journal, /promote, and morepython-frontmatter: pip install python-frontmattergit-crypt (optional): brew install git-cryptclaude --plugin-dir /path/to/AgentsOS/personal-brain-skill
Or add to your project's marketplace.json:
{
"plugins": [
{ "path": "/path/to/AgentsOS/personal-brain-skill" }
]
}
/bootstrap to scaffold your ~/brain/ vaultidentity/voice.md and identity/values.yaml/journal, /score-idea, /meeting-prep, etc.AgentsOS/
└── personal-brain-skill/
├── SKILL.md # Main skill routing (progressive disclosure)
├── AGENT.md # 14 core operating rules
├── package.json # Plugin metadata
├── skills/ # 6 modular sub-skills
│ ├── personal-identity/
│ ├── content-pipeline/
│ ├── engineering-knowledge/
│ ├── network/
│ ├── operations-memory/
│ └── personal-life/
├── commands/ # 13 slash commands
├── agents/ # 3 specialist agents
├── hooks/ # Behavioral enforcement hooks
├── scripts/ # Python automation scripts
└── assets/ # Templates and git-crypt configs
Personal Brain OS uses a progressive disclosure architecture with three loading levels:
| Level | What loads | When |
|---|---|---|
| L1 | Routing skill (SKILL.md) | Every session |
| L2 | Module-specific behavioral rules | When a module is invoked |
| L3 | Actual personal data files | On demand, within token budgets |
The promotion workflow moves knowledge from working memory to long-term storage:
thoughts/ during project work/promote to review what to keep~/brain/| Command | Purpose |
|---|---|
/bootstrap | Scaffold a new Brain OS vault |
/init-thoughts | Initialize a Thoughts working-memory repo |
/link-brain | Symlink Brain OS into current project (read-only) |
/weekly-review | Comprehensive weekly review |
/meeting-prep | Prepare for a meeting with a contact |
/write-blog | Write a blog post with voice compliance |
/score-idea | Score a content idea across 5 dimensions |
/journal | Create/update daily note with wellness metrics |
/life-review | Personal life review with trends |
/research-codebase | Research and save findings to Thoughts |
/create-plan | Create an implementation plan |
/implement | Execute a plan phase by phase |
/promote | Promote Thoughts artifacts to Brain OS |
MIT
Landung Setiawan
npx claudepluginhub lsetiawan/agentsos --plugin personal-brain-skillClaude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Make your AI agent code with your project's architecture, rules, and decisions.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation