LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
Pluginofficial publisher

Copilot for Obsidian

Plugin : A set of capabilities installed into an AI application or a host · requires obsidian

Chat with your vault, semantic search, web and YouTube, agent capabilities inside Obsidian.

The most mature AI plugin for Obsidian; it reads the entire vault and sends it to the configured model.

Overall score
8.2 /10
Security: one caveat, see the card
Utility
9.0
Reliability
10.0
Security
One caveat
Ease
5 min · Comfortable

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Obsidian users accumulate notes without an easy way to query them or automatically connect ideas. Copilot for Obsidian adds an AI agent directly inside the app, capable of reading the vault, creating files, running semantic searches, and handling multi-step tasks.

In practice, the plugin relies on three agents: opencode (recommended, managed by Copilot), Claude Code (via an existing installation), or Codex (via a dedicated adapter). The agent can inspect notes, use tools, write to the vault in native Markdown with wikilinks, and continue a conversation across multiple turns. A Quick Ask feature lets you query a text selection without leaving the current note.

The plugin suits researchers, writers, engineers, and anyone managing a dense knowledge base in Obsidian who wants to query it in plain language or automate repetitive tasks such as renaming notes or merging duplicates.

However, Agent mode is desktop-only: it runs local processes that are incompatible with mobile. On mobile, only Quick Chat, custom commands, and Quick Ask remain available. Users who do not want to connect an API key or subscribe to a plan will not have access to hosted features.

What it offers

  • ·Multi-step Agent mode: the agent inspects notes, uses tools, and creates Obsidian files in native Markdown with wikilinks.
  • ·Local semantic search via Miyo, the built-in indexing engine that also supports external PDFs and EPUBs.
  • ·Support for multiple agents: opencode, Claude Code, and Codex, each configurable with its own skills.
  • ·Projects: a dedicated workspace with its own instructions, reusable context, and per-project chat history.
  • ·Quick Ask: query a text selection, then replace or insert the answer without leaving the current note.
  • ·Custom commands: save repeatable prompts, run them with / in the agent or from the command palette.
  • ·Multi-agent collaboration: mention several agents with @ for a shared research or review request (paid).
  • ·OpenArtifacts publishing: publish a Markdown note at a stable public link that updates automatically (paid).

In practice

Price
Freemium
Commercial use
Commercial use: yes
Available on
obsidian
Host
obsidian
Licence
AGPL-3.0
FR interface
No

Security and data

Rating
Security: one caveat, see the card
Your data
Local or cloud depending on use
Maintenance
Active
Last release
23 October 2026

Links and repository checked on 25 October 2026 · added on 1 April 2023

How to install Copilot for Obsidian

1. Open Obsidian and go to Settings > Community Plugins > Browse. 2. Search for "Copilot" and install the Copilot for Obsidian plugin. 3. Enable the plugin, then open Settings > Copilot > Basic > Agents. 4. Choose your agent: download opencode, connect Claude Code via Auto-detect, or install the Codex adapter. 5. To use your own API key, enter it under Settings > Copilot > BYOK (it will be stored in the device keychain, not in the vault). 6. Click the Agent icon in the sidebar or run "Open Copilot Agent Chat Window" from the command palette.
Settings → Community plugins → Copilot

In the same category

Whole category Meetings & notes →