Swarmvault
swarmclawai/swarmvault
Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval…
Lets an agent read, write and maintain its own memory in a Brain folder of an Obsidian-compatible vault, while keeping the user's own notes read-only.
Install Open Second Brain
$ npx skills add itechmeat/open-second-brain --skill open-second-brain -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install itechmeat/open-second-brain open-second-brain --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/itechmeat/open-second-brain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/open-second-brain .claude/skills/open-second-brain && 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 "open-second-brain" agent skill from https://github.com/itechmeat/open-second-brain/tree/main/skills/open-second-brain into .claude/skills/open-second-brain/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "open-second-brain", 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/itechmeat/open-second-brain/tree/main/skills/open-second-brainType 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 itechmeat/open-second-brain --skill open-second-brain -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install itechmeat/open-second-brain open-second-brain --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/itechmeat/open-second-brain.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/open-second-brain .agents/skills/open-second-brain && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "open-second-brain" agent skill from https://github.com/itechmeat/open-second-brain/tree/main/skills/open-second-brain into .agents/skills/open-second-brain/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "open-second-brain", 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 itechmeat/open-second-brain --skill open-second-brain -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install itechmeat/open-second-brain open-second-brain --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/itechmeat/open-second-brain.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/open-second-brain .cursor/skills/open-second-brain && 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 "open-second-brain" agent skill from https://github.com/itechmeat/open-second-brain/tree/main/skills/open-second-brain into .cursor/skills/open-second-brain/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "open-second-brain", 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/itechmeat/open-second-brain.git --path skills/open-second-brain--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 itechmeat/open-second-brain --skill open-second-brain -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install itechmeat/open-second-brain open-second-brain --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/itechmeat/open-second-brain.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/open-second-brain .gemini/skills/open-second-brain && 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 "open-second-brain" agent skill from https://github.com/itechmeat/open-second-brain/tree/main/skills/open-second-brain into .gemini/skills/open-second-brain/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "open-second-brain", 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 itechmeat/open-second-brain open-second-brainInstalls 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 itechmeat/open-second-brain --skill open-second-brain -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/itechmeat/open-second-brain.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/open-second-brain .github/skills/open-second-brain && 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 "open-second-brain" agent skill from https://github.com/itechmeat/open-second-brain/tree/main/skills/open-second-brain into .github/skills/open-second-brain/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "open-second-brain", 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 itechmeat/open-second-brain --skill open-second-brain -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install itechmeat/open-second-brain open-second-brain --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/itechmeat/open-second-brain.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/open-second-brain .opencode/skills/open-second-brain && 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 "open-second-brain" agent skill from https://github.com/itechmeat/open-second-brain/tree/main/skills/open-second-brain into .opencode/skills/open-second-brain/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "open-second-brain", 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
open-second-brain- GitHub stars
- 430
- Token cost
- ~1.2k tokens
- SKILL.md length
- 606 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
Lets an agent read, write and maintain its own memory in a Brain folder of an Obsidian-compatible vault, while keeping the user's own notes read-only.
- Works in 6 steps: Check whether Open Second Brain is… → Read the machine-local config if… → Read the vault-local operating manual… → …
- Setting up agent-owned memory inside an Obsidian vault
- SKILL.md covers Layout, Core principles, Default workflow and Search surfaces, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Open Second Brain owns one top-level folder in the vault, `Brain/`, where the agent writes taste signals, accreted preferences (unconfirmed, confirmed, retired), an evidence log and snapshots. User-authored notes live wherever the operator names them and are read only when listed under `notes.read_paths` in `Brain/_brain.yaml`; the agent never writes to them. The exception is the note-lifecycle tools, which act on a user-note path the caller names and can move a note to `Archive/`.
The default workflow checks configuration with `o2b status` or the `second_brain_status` MCP tool, reads the vault's `Brain/_BRAIN.md` operating manual, records taste signals with `brain_feedback`, and records evidence after producing a durable artifact with `brain_apply_evidence`. Searches are routed by question shape, such as `brain_search` for hybrid keyword and semantic recall and `second_brain_query` for pages by title. Raw evidence stays separate from synthesized knowledge, secrets are never written, and the excerpt is cut off in the search section.
When your agent uses it
- Setting up agent-owned memory inside an Obsidian vault
- Recording preferences and corrections so they carry across sessions
- Searching the vault's memory by topic or by page title
- Checking the health of the brain with the doctor tool
Example prompts
- “Check whether Open Second Brain is configured for my vault.”
- “Record in the brain that I prefer short commit messages.”
- “Search the brain for what we decided about the pricing page.”
Requirements
- An Obsidian-compatible Markdown vault
- The `o2b` CLI or the Open Second Brain MCP server
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Check whether Open Second Brain is configured: o2b status or second_brain_status MCP tool.
- Read the machine-local config if available (vault path, agent identity, timezone).
- Read the vault-local operating manual Brain/_BRAIN.md - this is the per-vault contract for agents.
- Record taste signals as they arrive in dialogue via brain_feedback (see the brain-memory skill).
- After producing a durable artifact, check applicable preferences and record evidence via brain_apply_evidence (see the brain-memory skill).
- For read access to vault pages by title, use second_brain_query.
What it can do on your machine
Read from SKILL.md and the folder at commit 0f0c9a7. 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
Open Second Brain loads about 1.2k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 606 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 itechmeat/open-second-brain at commit 0f0c9a7, republished under its MIT licence (© itechmeat). 606 words, ~1,232 tokens.
Download SKILL.mdSave it as
.claude/skills/open-second-brain/SKILL.md (or your agent's skills folder).- name
- open-second-brain
- description
- Use Open Second Brain to read, write, and maintain an agent-owned second brain in an Obsidian-compatible Markdown vault. The agent owns one top-level directory (`Brain/`). User-authored notes live wherever the operator names them and are read-only inputs when listed in `notes.read_paths`.
Open Second Brain
Use this skill when a user asks an agent to use, configure, inspect, or maintain Open Second Brain.
Layout
Open Second Brain owns one top-level directory in the vault: Brain/. Everything the agent generates on its own lives under it. The exception is the note-lifecycle family (brain_note_lifecycle, brain_scaffold_stub), which acts on a user-note path the caller names and can move a note to a second top-level directory, Archive/.
Brain/- agent-writable observing memory. Taste signals, accreted preferences (unconfirmed → confirmed → retired), evidence log, snapshots. Operations go through MCP toolsbrain_feedback,brain_apply_evidence,brain_dream,brain_brief,brain_query,brain_doctor- see thebrain-memoryskill for the calling protocol. CLI counterparts:o2b brain *.- User-authored notes - the operator's daily journal, weekly notes, project notes, etc. Folder names are operator-chosen. The agent reads these paths only when they appear under
notes.read_pathsinBrain/_brain.yaml; the agent never writes to them.
Core principles
- Treat the vault as user-owned durable knowledge.
- Write only into
Brain/. Never write to user-authored note folders. - Keep raw operational evidence separate from synthesized knowledge: per-event records go to
Brain/log/, preferences live inBrain/preferences/. - Never write secrets, tokens, passwords, private keys, or credential-bearing connection strings.
- Prefer deterministic CLI commands (
o2b brain ...,o2b doctor,o2b status) over guessing file paths.
Default workflow
- Check whether Open Second Brain is configured:
o2b statusorsecond_brain_statusMCP tool. - Read the machine-local config if available (vault path, agent identity, timezone).
- Read the vault-local operating manual
Brain/_BRAIN.md- this is the per-vault contract for agents. - Record taste signals as they arrive in dialogue via
brain_feedback(see thebrain-memoryskill). - After producing a durable artifact, check applicable preferences and record evidence via
brain_apply_evidence(see thebrain-memoryskill). - For read access to vault pages by title, use
second_brain_query.
Show full SKILL.md (317 more words)Show less
Search surfaces
Name the surface a question is shaped for, and route to it explicitly:
- Generic recall -
brain_searchruns hybrid keyword + semantic search over raw chunks. Use it for open-ended, topical, or exploratory questions. - Summary surface - for a question that targets a specific source or an artifact kind (a summary, digest, or other declared
schema.page_typestype), reach for the summary surface: search by source or filter by artifact kind rather than running a generic search over raw chunks.brain_searchdetects this structurally and returnssurface: "summary"on the response as an advisory route hint; a source-targeted query uses asource:<path>token and an artifact-kind query uses akind:<type>/type:<type>token whose value is a declared page type. The hint never changes ranking - it names the intended surface so the agent asks the right way. - Answerable signal - when
brain_searchreturnsdecision_model.answerable, pass itsprobabilitytobrain_recall_gateorbrain_context_packasdecision_answerabletogether with the scores andmatch_quality.decision_answerable.disagrees: trueon the verdict means search again with other words, or say the vault may not cover the question; the level and action stay as they are. - Skill offers -
skills_attachoffers skills for the current turn; when the operator configured the optionalskillsdecision-model use it may be decision-model assisted (the result then carries adecision_modelfield). Cite itsoffer_idonget_skilleither way.
Safety
If a write operation might affect anything outside the Brain/ directory, ask for explicit confirmation. When in doubt, prefer Brain/.
Decision-model verdicts (decision_model on brain_hygiene scan dedup findings, doctor alias candidates and brain_tension verify) are advisory only: merges, dismissals and resolutions still need an explicit action.
To label a note, call brain_labels suggest before assign; suggest never assigns, and a null suggestion means no confident value.
See also
brain-memoryskill — when and how to callbrain_feedback/brain_apply_evidence.Brain/_BRAIN.md(in each vault) — operating manual for that vault, generated byo2b brain init.docs/plans/2026-05-15-brain-observing-memory.md(in the repo) — full design.
© itechmeat, 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/open-second-brain of itechmeat/open-second-brain.
Open the folder on GitHubat commit 0f0c9a7
Compare with similar skills
Open Second Brain 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 |
|---|---|---|---|---|---|---|
| Open Second Brain this skillitechmeat/open-second-brain | 430 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Swarmvaultswarmclawai/swarmvault | 708 | — | ~6.1k | Automated safety check: Pass | MIT | |
| Obsidian Project Memorybrycewang-stanford/Auto-Empirical-Research-Skills | 4.5k | — | ~2.4k | Automated safety check: Pass | Custom licence | |
| AI BrainOotto-AI/claude-content-skills | 101 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Qmdbreferrari/obsidian-mind | 4.9k | — | ~1.7k | Automated safety check: Pass | MIT | |
| NexusProfSynapse/nexus | 154 | — | ~1.3k | Automated safety check: Pass | MIT |
Similar skills
Obsidian Project Memory
brycewang-stanford/Auto-Empirical-Research-Skills
This skill should be used when the user asks to maintain an Obsidian knowledge base for a research project, import an existing research repository into Obsidian, keep project memory or daily notes…
AI Brain
Ootto-AI/claude-content-skills
Give Claude a permanent, searchable long-term memory using an Obsidian vault as the store.
Qmd
breferrari/obsidian-mind
Search the vault using QMD semantic search. An agent skill from breferrari/obsidian-mind.
Nexus
ProfSynapse/nexus
Read, search, and edit the user's Obsidian vault (notes, folders, canvas, bases, tasks, memory/workspaces, saved prompts) from the shell via the nexus CLI — no MCP connection needed.
Agent Recall
Goldentrii/AgentRecall-X
Persistent compounding memory for AI agents. An agent skill from Goldentrii/AgentRecall-X.
More from itechmeat/open-second-brain
Decision Model Setup
itechmeat/open-second-brain
Sets up, evaluates or turns off Open Second Brain's optional decision-model feature, starting from the o2b decision-model check command and a provider route you choose.
Codegraph Detection Partner
itechmeat/open-second-brain
Teaches the agent to detect whether the codegraph symbol graph is available and use it for callers, callees and impact questions, without installing or writing anything for it.
Open Second Brain Embeddings Setup
itechmeat/open-second-brain
Walks through turning on semantic search in Open Second Brain: embedding key, sqlite-vec extension, first reindex and an optional periodic refresh, starting from o2b search check.
Brain Schema Author
itechmeat/open-second-brain
Adds, renames, reviews and explains Brain schema tokens, aliases, prefixes and link types in Open Second Brain vaults, previewing each change before applying it.
Related
Works with
Categories
Questions about Open Second Brain
What does Open Second Brain do?
Lets an agent read, write and maintain its own memory in a Brain folder of an Obsidian-compatible vault, while keeping the user's own notes read-only. Open Second Brain owns one top-level folder in the vault, `Brain/`, where the agent writes taste signals, accreted preferences (unconfirmed, confirmed, retired), an evidence log and snapshots.yaml`; the agent never writes to them.
When should I use Open Second Brain?
Open Second Brain fits situations like: setting up agent-owned memory inside an Obsidian vault; recording preferences and corrections so they carry across sessions; searching the vault's memory by topic or by page title; checking the health of the brain with the doctor tool.
How do I install Open Second Brain in Claude Code?
Run `npx skills add itechmeat/open-second-brain --skill open-second-brain -a claude-code`. Or copy the skill folder (skills/open-second-brain in itechmeat/open-second-brain) into .claude/skills/open-second-brain in your project. Claude Code loads it when a task matches its description.
How do I install Open Second Brain in Codex?
Run `npx skills add itechmeat/open-second-brain --skill open-second-brain -a codex`. Or copy the skill folder (skills/open-second-brain in itechmeat/open-second-brain) into .agents/skills/open-second-brain in your project. Codex loads it when a task matches its description.
Can I use Open Second Brain 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 itechmeat/open-second-brain --skill open-second-brain -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/open-second-brain, .gemini/skills/open-second-brain, .github/skills/open-second-brain and .opencode/skills/open-second-brain in your project.
What does Open Second Brain need to run?
SKILL.md names no scripts, command-line tools or credentials: Open Second Brain is instructions for the agent only. Our summary lists: An Obsidian-compatible Markdown vault; The `o2b` CLI or the Open Second Brain MCP server.
Does Open Second Brain 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 Open Second Brain 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 Open Second Brain use?
Open Second Brain 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 Open Second Brain use?
About 1.2k tokens (SKILL.md is roughly 4.9k 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 Open Second Brain?
Skills that share tags, products or a category with Open Second Brain: Swarmvault (swarmclawai/swarmvault, 708 stars), Obsidian Project Memory (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars), AI Brain (Ootto-AI/claude-content-skills, 101 stars) and Qmd (breferrari/obsidian-mind, 4.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Open Second Brain?
itechmeat (a GitHub user) maintains it in itechmeat/open-second-brain, which has 430 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 6, 2026.
Source: itechmeat/open-second-brain on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.