Persistent brain for Claude Code sessions using Obsidian. Auto-logs sessions, captures curated insights, enables project-scoped context resume, and provides fast cross-project search via tags and metadata.
Triage open `- [ ]` items across your Obsidian vault with evidence-grounded AI classification. Auto-closes items shipped by merged PRs, surfaces items needing external action (e.g. `gh issue close`), hides stale items by default. Replaces the old token-overlap heuristic with a two-pass AI pipeline backed by a persistence cache. Use when: (1) sweeping a project for done work, (2) auditing what's still actionable, (3) recovering from /recall deferral fatigue.
Interactively saves curated insights from the current Claude Code session to the Obsidian vault. Use when: (1) /compress command to save session insights, (2) /compress <topic> to extract a specific topic, (3) user wants to capture decisions, patterns, solutions, or error fixes from the current session.
Batch-cluster vault notes into named themes. Use when: (1) /consolidate to seed themes from unassigned notes, (2) /consolidate stats, (3) /consolidate split <id>, (4) /consolidate merge <a> <b>, (5) /consolidate --full to wipe and recluster everything.
Captures architectural and technical decisions as ADR-lite notes in the Obsidian vault. Use when: (1) /decide command to record a decision from the current session, (2) /decide <decision summary> to capture a specific decision, (3) user wants to document why a particular technical choice was made.
Install dev version of obsidian-brain into the plugin cache for local testing, or restore the original. Use when: (1) /dev-test install to test unreleased changes, (2) /dev-test restore to put back the original, (3) /dev-test to check current status.
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 that turns your Obsidian vault into a persistent brain across sessions. Auto-logs sessions, captures curated knowledge, enables project-scoped context resume, and provides fast search across all historical context.
Claude Code sessions are ephemeral — when you close a session, the context is gone. Your existing CLAUDE.md and memory system help, but they lack:
Obsidian Brain bridges this gap by writing structured markdown notes to your Obsidian vault, where Dataview turns them into a queryable knowledge base.
CC Session Lifecycle
|
|-- SessionStart --> Injects last-session context hint
|-- PreCompact ---> Saves context snapshot before compression
|-- /compress ----> You curate & save specific insights
|-- /recall ------> Loads project context from vault
|-- /vault-search > Searches across all sessions & insights
|-- /standup -----> Generates daily/weekly project summaries
|-- /standup deep > Evidence-based open-item consolidation
|-- /emerge ------> Cross-project pattern discovery
|-- /link --------> Cross-references notes with wikilinks
|-- /retro -------> Session retrospective & process improvements
|-- /vault-ask ---> Synthesized answers from vault knowledge
+-- SessionEnd ---> Auto-logs session to vault
All data flows are one-directional filesystem writes — no MCP server, no REST API, no Obsidian plugins required (except Dataview for dashboards). A local SQLite + FTS5 index enables fast full-text search as the vault scales. Works even when Obsidian isn't running.
/plugin marketplace add abhattacherjee/obsidian-brain
/plugin install obsidian-brain@obsidian-brain-repo
Then run /obsidian-setup once to point the plugin at your Obsidian vault.
If you previously installed obsidian-brain from the claude-code-skills
marketplace, switching is seamless — your config and vault are untouched, so
no /obsidian-setup is needed:
/plugin marketplace add abhattacherjee/obsidian-brain/plugin install obsidian-brain@obsidian-brain-repo/plugin uninstall obsidian-brain@claude-code-skills — so only one version is enabled.Run only one version at a time. Keeping both the monorepo and standalone plugins enabled simultaneously double-registers the session hooks. A built-in guard reduces duplicate notes if both are ever briefly active — it errs toward suppressing a duplicate rather than writing two — but the supported configuration is a single enabled version.
Run /obsidian-setup after installation. It will:
claude-sessions/, claude-insights/, claude-dashboards/, claude-check-items/~/.claude/obsidian-brain-config.jsonPlugin-first publishing for Claude Code skills. Auto-assembles and syncs plugins from plugin-manifest.json files. Also supports bare skills and individual repos
Creates polished, narrated product demo videos using Remotion with AI-crafted storytelling, real app screenshots, animated phone mockups, brand-aligned styling, TTS voiceover, and background music.
Interactive Figma UI design skill with brainstorming, progress tracking, and design-to-code bridging via Figma MCP
Creates detailed story specifications with TDD implementation steps, success metrics, Figma UX design gates, and vertical splitting from various inputs (plans, requirements, GitHub issues).
Prevents context window overflow by delegating token-heavy reads to isolated sub-agents that return distilled summaries. Auto-detects when ralph-loop is needed. Covers: documentation sites, code audits, dependency research, large PR reviews, competitive analysis, security advisories.
npx claudepluginhub abhattacherjee/obsidian-brain --plugin obsidian-brainMCP server that saves 98% of your context window with session continuity. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and automatic state restore across compactions.
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.
Open-source, local-first Claude Code plugin for token reduction, context compression, and cost optimization using hybrid RAG retrieval (BM25 + vector search), reranking, AST-aware chunking, and compact context packets.