Curtis AI Chat

---

Screenshots

Real captures, regenerated any time with npm run shots && npm run mockups (Playwright driving Obsidian over the DevTools protocol).

---

Quick start

60 seconds to your first message.

1. Install — download the latest release (main.js, manifest.json, styles.css) into <vault>/.obsidian/plugins/curtis-ai-chat/, then enable it under Settings → Community plugins. Or use BRAT for auto-updates during the beta.

2. Configure one provider — open Settings → Curtis AI Chat → Provider Configuration, enable a provider, paste an API key. Keys are stored in your OS keychain via the Obsidian SecretStorage API.

3. Send a message — click the robot icon in the ribbon, pick a model from the header dropdown, type, hit Enter. (All commands are hotkey-assignable under Obsidian's Settings → Hotkeys — none are bound by default.)

[!TIP] Want fully private, free, offline AI? Install Ollama, run ollama pull qwen2.5:7b-instruct, then enable Ollama (Local) in provider settings. No API key. Nothing leaves your machine.

---

Highlights

The flagship features. Full details in CHANGELOG.md and the per-feature docs.

Plus a full type-safety pass: every AI provider response shape is strictly typed, with type-guard narrowing at every JSON boundary. Zero lint warnings on npm run build.

---

Features

🤖 Curtis Agent

The AI can now call tools to modify your vault. Eleven built-in tools: read_note, search_notes, semantic_search, create_note, edit_note, list_notes, get_tags, get_backlinks, get_current_note, get_current_date, calculator.

• Every major provider — Anthropic via native tool use, OpenAI-compatible endpoints (OpenAI, Gemini, Ollama, Groq, DeepSeek, custom). The model must support tool calling.
• agentMaxTurns safety cap (default 5) prevents runaway tool loops
• MCP servers — connect your existing Model Context Protocol servers (Settings → MCP servers) and every tool they expose becomes callable alongside the built-ins. Streamable HTTP transport — local stdio servers need an HTTP bridge such as mcp-proxy or supergateway.
• Opt-in via Settings → Agent → Enable

→ docs/AGENT.md

⚔️ Multi-model arena

Pick 2 models, send one prompt, watch responses stream side-by-side. Click Promote to chat on any column to continue with that model.

• Compare quality, latency, and cost live
• All providers supported (mind per-provider rate limits)
• Stacks vertically on mobile

→ docs/ARENA.md

🎨 Inline diff rewrite

Select text in any note → right-click → Rewrite with AI (diff) (or assign a hotkey under Settings → Hotkeys). The AI generates an improved version and a modal shows line-by-line green/red diff. Accept or reject.

• Cursor-style review workflow
• Reuses your active provider and model
• Word-level diff and inline editor decorations planned for v1.1

→ docs/DIFF_REWRITE.md

@ @-mention vault notes

Type @ in the chat input → fuzzy-search your vault → click a result to attach. Note content is prepended to your message as invisible context. Chips above the input show what's attached.

• Active-note pill in the chat header for one-click attach of the current note
• AI uses attached content as the source of truth — no re-searching
• Works with or without the Agent enabled

→ docs/MENTIONS.md

🎙️ Voice I/O

• Speech-to-text via OpenAI Whisper — click the mic button, talk, transcribed text lands in the chat input
• Text-to-speech via browser speechSynthesis — speaker button on every assistant message, no API key needed
• Auto-speak toggle in the header for hands-free listening
• Markdown is stripped before synthesis so the voice reads naturally

→ docs/VOICE.md

💬 Chat that gets out of the way

• Streaming responses with a clean Telegram-style bubble layout
• Model picker with capability pills (vision 👁, tools 🔧, context length)
• Per-message hover actions: copy, quote-into-input, save-as-note, insert-into-active-note, regenerate, edit-and-resend
• Conversation history dropdown
• Cross-conversation search (assignable hotkey)

🖼️ Image attachments

• Paste (Ctrl+V), drag-and-drop, or paperclip — three ways to attach
• Images save as real vault files (not base64 blobs in localStorage)
• Vision-capable models see them automatically; non-vision models get a clear "switch to a vision model" notice
• Transcripts via /save-all embed images as ![[wikilinks]]

→ docs/IMAGES.md

✂️ Inline selection actions

Right-click any selection in a note for Explain · ELI5 · Summarize · TL;DR · Improve · Fix grammar · Shorten · Translate · Make a table · Pros & cons · Code review · Refactor · Add tests. Each writes the result directly back into the note — replace or insert-below.

→ docs/SELECTION_ACTIONS.md

🧠 Long-term memory

Curtis remembers durable facts about you across conversations — preferences, identity, projects, standing instructions. Facts live in a markdown file in your vault.

• Auto-capture: background LLM extraction after each turn (0–3 facts)
• Manual: /remember <fact> or right-click selection → Save to memory
• Edit UI: edit/delete individual facts from Settings → Memory
• Recall: every prompt includes a ## What you know about the user block

→ docs/MEMORY.md

🔎 Vault retrieval (RAG)

Ask about your vault in plain language — the most relevant note excerpts are retrieved and injected into the prompt automatically.

• Any embeddings provider — OpenAI, Gemini, Z.ai, or fully local via Ollama/LM Studio (Anthropic and Azure are excluded — no embeddings API / deployment-specific URL scheme)
• Automatic injection — top-k excerpts in every prompt; skipped when you @-attach a note, because curated context wins
• Live index — edits re-embed in the background; rebuilds are incremental and cheap
• semantic_search tool — the agent queries the vault by meaning, not just keywords
• Your index stays yours — int8-quantized JSON in the plugin folder; nothing uploaded beyond the embeddings provider you configure

Enable in Settings → Vault retrieval, then Rebuild index.

⌨️ Slash commands

Type / in the chat input for an autocomplete menu of 17 commands — /clear, /regen (alias /regenerate), /title, /copy, /note, /save-all, /paste, /model, /provider, /system, /stats, /remember, /forget, /memory, /export, /help.

→ docs/SLASH_COMMANDS.md

⚙️ Customizable

• Chat panel position (left/right), background (theme default or a wallpaper image from your vault)
• Configurable system prompt, temperature, max tokens
• Enter-to-send (default) or Enter-for-newline
• Auto-save assistant responses to a folder of your choice
• Show or hide token counts after each response

---

Why Curtis AI Chat

Curtis AI Chat is the agent layer for Obsidian. Where other plugins focus on a single workflow (chat, RAG, or text generation), Curtis ships all three with a polyglot provider model and a native Obsidian feel.

[!NOTE] Comparison refreshed 2026-10-03. Other plugins ship fast — Copilot's v4 agent chat is real and actively developed, Smart Connections remains the gold standard for RAG (Curtis' own retrieval is new; theirs is battle-tested), Text Generator excels at template-driven writing. Curtis aims to be the free, polyglot, local-first agent layer that ties chat, tools, and memory together.

Principles

• Your data stays yours. Conversations as markdown files in your vault (AI/Conversations/ by default) — synced across devices, searchable in native Obsidian search, and readable by the agent. Images as real vault files. Memory as a markdown file you can read and edit. No telemetry, no tracking, no phone-home.
• No vendor lock-in. Thirty providers ship built-in. Add any OpenAI-compatible endpoint as a custom provider in 30 seconds. Switch models mid-conversation.
• Local-first when you need it. Enable Ollama and nothing ever leaves your machine. Useful for private notes, air-gapped machines, or when you just don't want to pay per token.
• Native Obsidian feel. Real Obsidian setting components. Messages render through MarkdownRenderer. Themes respected — light, dark, Things, Minimal, all of them.

---

Configuration

Full configuration reference lives in the docs:

• Providers (API keys, endpoints, custom providers)
• Slash commands
• Memory
• Curtis Agent
• Voice I/O
• Image attachments
• Selection actions
• @-mentions
• Inline diff rewrite
• Multi-model arena

Or start at the docs index.

---

Privacy & security

Curtis AI Chat accesses your vault files only in user-initiated cases:

1. Agent vault-search tool — when you explicitly invoke a tool in chat, the plugin enumerates markdown files. The agent sees file paths and contents you ask it to read.
2. Image picker — when you click the paperclip, the plugin lists image files.
3. Folder picker — when you configure auto-save or wallpaper folders.
4. @-mention autocomplete — when you type @, the plugin fuzzy-searches note names. Note contents are only read when you actually attach and send.

No file contents are sent to AI providers except message text, attached images, attached note contents, and tool-call results. API keys are stored in your OS keychain (Windows Credential Manager / macOS Keychain / Linux Secret Service), never in the vault.

Clipboard: the plugin reads the system clipboard only when you paste into the chat input (Ctrl+V / long-press → Paste), and writes to it only when you click copy on a message. Nothing is read from or written to the clipboard in the background.

[!IMPORTANT] Tool calls go to your AI provider. Vault contents read by agent tools are sent to the provider as part of the conversation. If you're on a cloud provider, that content leaves your machine. Switch to Ollama for fully offline operation.

Network access

Curtis is vault-first — no background telemetry, no analytics, no auto-update checks. Every outbound request is user-initiated. The plugin may contact these domains:

The two web tools (web_search, read_url), voice transcription, MCP, and vault retrieval are off by default. Without them, the only external calls are to whichever AI provider you configured — or none, if you're on Ollama. MCP tool calls go only to the server URLs you entered; tool results travel through your AI provider like any other tool result.

---

Installation

[!TIP] Curtis AI Chat is in the community plugin directory. Install from there, manually (below), or via BRAT for beta-channel updates.

Manual install

1. Download the latest release main.js, manifest.json, and styles.css.
2. In your vault, create .obsidian/plugins/curtis-ai-chat/.
3. Copy the three files into that folder.
4. Open Settings → Community plugins, refresh the list, enable Curtis AI Chat.

From source (developers)

git clone https://github.com/JordanNewell/curtis-ai-chat.git
cd curtis-ai-chat
npm install
npm run build

See CONTRIBUTING.md for dev setup, code style, and the audit checklist.

---

Mobile

Curtis AI Chat works on iOS and Android with a few caveats:

• Hover-only elements (per-message toolbar, code-block copy) are always visible on touch at reduced opacity
• Touch targets sized to Apple HIG minimums (44pt send button, 40pt header icons)
• Wallpaper background auto-disabled on phones for scroll performance
• /paste may fail if the OS blocks clipboard read — use Ctrl+V / long-press → Paste
• Streaming falls back to buffered responses automatically when a provider blocks mobile CORS
• Local providers work over LAN (http://192.168.1.50:11434/v1/chat/completions)

---

Roadmap

• Curtis Agent: Anthropic, Gemini, and Ollama provider support (v1.1)
• Inline diff rewrite: word-level diff and inline editor decorations
• Settings: declarative getSettingDefinitions() — shipped in v1.2.0 (see ADR: settings API)
• Vault retrieval (RAG): embedding index over the vault, auto-injected context, semantic_search agent tool (v1.4.0)
• MCP client: connect external MCP servers, their tools join the agent toolset (v1.4.0)
• Conversations as vault markdown files with automatic localStorage import (v1.4.0)
• Voice: streaming TTS, wake-word detection
• Conversation branching UI
• Plugin settings import/export
• Semantic memory retrieval via sqlite-vec (when memory exceeds ~150 facts)

See the open issues for the live list.

---

Contributing

PRs welcome — see CONTRIBUTING.md for dev setup, code style, and the audit checklist every change goes through before merge.

[!NOTE] Not accepting external PRs yet while the v1 line stabilizes. Bug reports and feature requests via Issues are very welcome.

Architecture decisions

Settings API

Since v1.2.0 Curtis targets Obsidian 1.13.0+ and uses the declarative getSettingDefinitions() API for its settings tab. Every section and row is indexed by Obsidian's settings search; dynamic re-renders go through the sanctioned SettingTab.update().

History: through v1.1.x the floor was 1.11.4 (set by the SecretStorage API for per-provider key storage) and the tab used the imperative display() API, which Obsidian 1.13 deprecated. The dual-path (getSettingDefinitions() + display() fallback) was evaluated and rejected — the declarative path's SettingTab.update() is 1.13-only, so supporting both meant either shipping a broken tab on older versions or tripping the no-unsupported-api lint rule. When Obsidian 1.13.6 reached the stable channel for all desktop and mobile users (August 2026), the migration shipped as v1.2.0: a single declarative path, zero deprecation warnings, and settings search that actually finds things.

💬 Feedback

All feedback is public and lives on GitHub:

• Bug found? Open an issue
• Feature idea? Start a discussion
• Love it? Share in Show & Tell
• Stuck? Ask in Q&A

No GitHub account? Email [email protected] and it gets posted publicly for you.

---

License

MIT © Jordan Newell