What is gemini-obsidian?

An Obsidian vault integration that reads and searches local notes, creates or updates notes, and answers questions using retrieved note content. Obsidian is a local note-taking app, and RAG means finding relevant text before forming an answer.

Use it to list files, search notes, manage daily notes, write notes, and ask questions about an Obsidian vault.

It lets you work with your personal notes without manually locating and copying them into each question.

gemini-obsidian — Plugin for Gemini CLI by thoreinstein

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/thoreinstein/gemini-obsidian

Made for: Gemini CLI.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/thoreinstein/gemini-obsidian/gemini-extension/github.svg)](https://agentmods.dev/plugins/thoreinstein/gemini-obsidian/gemini-extension)

Your own site

<a href="https://agentmods.dev/plugins/thoreinstein/gemini-obsidian/gemini-extension"><img src="https://agentmods.dev/badge/plugins/thoreinstein/gemini-obsidian/gemini-extension/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/thoreinstein/gemini-obsidian/gemini-extension"><img src="https://agentmods.dev/badge/plugins/thoreinstein/gemini-obsidian/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

gemini-obsidian scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

The scan reads gemini-extension.json. This mod also ships 3 executable files (scripts/reindex-note.js, scripts/session-init.js, scripts/validate-frontmatter.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

gemini-extension.json · 13 lines

What it actually says

{
  "name": "gemini-obsidian",
  "version": "1.8.1",
  "description": "Obsidian Vault integration with local RAG capabilities",
  "instructions": "Use these tools to interact with the user's Obsidian vault. You can read notes, list files, search (fuzzy), create/append notes, get daily notes, and use RAG (Retrieval Augmented Generation) to answer questions based on the notes. Always check if a vault path is known; if not, ask the user to provide it or set the OBSIDIAN_VAULT_PATH environment variable.",
  "mcpServers": {
    "gemini-obsidian": {
      "command": "node",
      "args": ["${extensionPath}/dist/index.js"]
    }
  }
}

Files

What ships with it

3 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today Changed 7391956b2acd
yesterday Changed 2018a875272a
2d ago First seen · 13 lines scan A 74e45e14145d

Subscribe to this mod's changes

gemini-obsidian is a plugin published in the GitHub repository thoreinstein/gemini-obsidian (102 stars, last pushed today), licensed ISC. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-14.

Data and AI RAG and vectors gemini-cli gemini-cli-extensions gemini-extensions obsidian-md

neo4j-skills

Agent skills for Neo4j graph database — Cypher queries, graph modeling, drivers, imports, GraphRAG, GDS, vector indexes, and Aura provisioning.

neo4j-contrib/neo4j-skills · not measured

obsidian-rag

Obsidian vault integration with local RAG capabilities for Claude Code.

thoreinstein/obsidian-rag · not measured

qdrant

Vector database collections and semantic search via direct calls to the Qdrant REST API.

dinglebear-ai/dendrite · not measured

tei

Inspect and query a Text Embeddings Inference server through its HTTP API.

dinglebear-ai/dendrite · not measured

veritasreason

Full-stack knowledge graph skills: semantic extraction, decision intelligence, context graphs, reasoning, explainability, ontology, provenance, deduplication, visualization, and multi-format export.

bibinprathap/VeritasGraph · not measured

clip-aware-embeddings

Semantic image-text matching with CLIP and alternatives. Use for image search, zero-shot classification, similarity matching. NOT for counting objects, fine-grained classification (celebrities, car models), spatial reasoning, or compositional queries. Activate on "CLIP", "embeddings", "image similarity", "semantic…

curiositech/some_claude_skills · not measured