https://github.com/unbug/monday
Run models in broswers without install anything.
https://github.com/unbug/monday
Last synced: 8 days ago
JSON representation
Run models in broswers without install anything.
- Host: GitHub
- URL: https://github.com/unbug/monday
- Owner: unbug
- License: mit
- Created: 2026-04-18T06:56:45.000Z (2 months ago)
- Default Branch: main
- Last Pushed: 2026-05-30T03:59:57.000Z (25 days ago)
- Last Synced: 2026-05-30T05:20:19.568Z (25 days ago)
- Language: TypeScript
- Homepage: https://unbug.github.io/monday/
- Size: 1.67 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Monday - Browser AI Chat
> Run open-source AI models **directly in your browser**. No server, no install, 100% private.
[](https://github.com/unbug/monday/actions/workflows/deploy.yml)
[](LICENSE)
**[Live Demo](https://unbug.github.io/monday/)** · **[Changelog](https://unbug.github.io/monday/)**
---
## Features
- **Zero Install** — Pure browser experience, no downloads needed
- **Browser-Native Inference** — Models run locally via WebGPU + WASM using [Web-LLM](https://github.com/mlc-ai/web-llm)
- **23 Pre-configured Models** — Qwen 2.5/3/3.5, SmolLM2, Gemma 2/3, Phi 3.5/4, Llama 3.2, DeepSeek R1, and more
- **Streaming Output** — Token-by-token real-time response
- **Chat History** — Persistent multi-session conversations via IndexedDB
- **Changelog** — In-app version history with expandable release details
- **Usage Statistics** — Dashboard with daily charts, per-model breakdown, and provider analytics
- **Model Comparison** — Side-by-side generation from two models with real-time token stats
- **Model Benchmark** — Built-in benchmark tool to measure tokens/sec and latency
- **Custom Model Import** — Load custom MLC-compiled models from any HuggingFace URL
- **Download Resume** — Resume interrupted model downloads from where you left off
- **Session Search** — Search conversations by title with date filtering
- **Command Palette** — Quick navigation with ⌘K
- **Prompt Templates & Personas** — 8 built-in personas + custom persona creation
- **Message Actions** — Edit and regenerate user messages inline
- **Generation Parameters** — Per-session temperature, top-p, max tokens sliders
- **System Prompts** — Customizable per-session system prompts
- **Token Counter** — Real-time tokens/sec and total token usage
- **Model Cache Manager** — View and delete cached models
- **Recent Models** — Quick access to recently used models
- **Recommended Models** — Top models based on your usage history
- **Storage Quota** — Monitor browser storage usage
- **Markdown Rendering** — Code highlighting, LaTeX math, GFM tables
- **Chat Export** — Export conversations as Markdown
- **BorderBeam UI** — Animated border effects with ocean/colorful/mono variants
- **Theme Toggle** — Light / Dark / System with auto-detection
- **Mobile Responsive** — Sidebar overlay, auto-close, safe-area support
- **PWA Ready** — Web app manifest, apple-touch-icon
- **100% Private** — Nothing leaves your browser
---
## Architecture
### High-Level System Architecture
```mermaid
graph TB
subgraph Browser["🌐 Browser (Client-Side Only)"]
UI["React UI
Vite + TypeScript"]
Engine["Web-LLM Engine
WebGPU / WASM"]
IDB["IndexedDB
Chat Persistence"]
Cache["Browser Cache
Model Weights"]
end
subgraph External["☁️ External (Read-Only)"]
HF["HuggingFace CDN
MLC Model Registry"]
GHP["GitHub Pages
Static Hosting"]
end
User(("👤 User")) --> UI
UI -->|"streamChat()"| Engine
Engine -->|"Token Stream"| UI
UI -->|"saveSessions()"| IDB
IDB -->|"loadSessions()"| UI
Engine <-->|"Download Once"| HF
Engine -->|"Cache Weights"| Cache
GHP -->|"Serve SPA"| Browser
style Browser fill:#1a1a2e,stroke:#a78bfa,color:#e5e5e5
style External fill:#0d1117,stroke:#444,color:#999
style Engine fill:#7c3aed,stroke:#a78bfa,color:#fff
```
### Routing Architecture
Monday uses a **zero-dependency URL routing** system built on the HTML5 History API — no React Router, no hash fragments.
**All 14 named views and their paths** (defined in `src/App.tsx`):
| View key | URL path |
|---|---|
| `chat` | `/monday/` |
| `models` | `/monday/models` |
| `changelog` | `/monday/changelog` |
| `cache` | `/monday/cache` |
| `stats` | `/monday/stats` |
| `comparison` | `/monday/comparison` |
| `benchmark` | `/monday/benchmark` |
| `custom-models` | `/monday/custom-models` |
| `persona-marketplace` | `/monday/persona-marketplace` |
| `knowledge` | `/monday/knowledge` |
| `plugins` | `/monday/plugins` |
| `mcp-servers` | `/monday/mcp-servers` |
| `webdav` | `/monday/webdav` |
| `memory` | `/monday/memory` |
**How it works:**
```mermaid
flowchart LR
URL["URL\n/monday/…"] -->|popstate| VFP["viewFromPath()\nURL → View enum"]
VFP --> State["view state\nReact useState"]
State -->|useEffect| PS["history.pushState"]
PS --> URL
subgraph GH["GitHub Pages compat"]
F["public/404.html\nsaves path → sessionStorage"]
R["Redirect → /monday/"]
A["App init reads sessionStorage\nhistory.replaceState"]
F --> R --> A
end
style State fill:#7c3aed,stroke:#a78bfa,color:#fff
style GH fill:#0d1117,stroke:#444,color:#999
```
**Key behaviours:**
- Calling `setView(v)` triggers a `useEffect` that does `history.pushState` to the mapped URL — the URL bar updates instantly without a page reload.
- `popstate` events (browser back / forward) call `viewFromPath(pathname)` to resolve the URL back into a `View` and update React state.
- **GitHub Pages 404 compatibility**: `public/404.html` captures the requested path in `sessionStorage` and redirects to `/monday/`. On first render `App.tsx` reads it back and calls `history.replaceState` to restore the original URL before the SPA mounts.
> **Rule for adding a new view:**
> 1. Add the key + path to `VIEW_PATH` in `App.tsx`.
> 2. Add a `view === 'new-view'` render branch in the JSX return.
> 3. Add a navigation callback to `useKeyboardShortcuts` and a menu item in `Sidebar`.
---
### Component Architecture
```mermaid
graph TD
App["App.tsx
URL Router + Global State"]
App --> Sidebar["Sidebar
Session List + Nav"]
App --> Header["Header
Model Badge + Theme"]
subgraph Views["Routed Views (view state)"]
V_chat["chat\n ChatLayout"]
V_models["models\n ModelSelector"]
V_knowledge["knowledge\n KnowledgePanel"]
V_plugins["plugins\n PluginManager"]
V_mcp["mcp-servers\n McpServerManager"]
V_memory["memory\n MemoryPanel"]
V_webdav["webdav\n WebDAVSettings"]
V_stats["stats\n ModelStats"]
V_cmp["comparison\n ModelComparison"]
V_bench["benchmark\n ModelBenchmark"]
V_persona["persona-marketplace\n PersonaMarketplace"]
V_custom["custom-models\n CustomModelImport"]
V_cache["cache\n (cache manager)"]
V_cl["changelog\n Changelog"]
end
App --> Views
Header --> TT["ThemeToggle
Light/Dark/System"]
Header --> WG["WebGPUCheck"]
V_chat --> ML["MessageList"]
V_chat --> CI["ChatInput
BorderBeam textarea"]
subgraph Hooks["Custom Hooks"]
useModel["useModel
Load/Unload/Progress"]
useChat["useChat
Sessions/Messages/Stream"]
useTheme["useTheme
Light/Dark/System"]
useKnowledge["useKnowledge / useKnowledgeBases"]
useVectorStore["useVectorStore
IndexedDB vectors"]
useEmbedding["useEmbeddingModel
GTE-small MLC"]
useMcp["useMcpServers"]
end
subgraph Lib["Core Library"]
engine["engine.ts
Web-LLM Singleton"]
models["models.ts
Model Registry"]
storage["storage.ts
IndexedDB Ops"]
changelog["changelog.ts
Version Data"]
end
App --> Hooks
Hooks --> Lib
engine -->|"CreateMLCEngine"| WEBLLM["@mlc-ai/web-llm"]
style App fill:#7c3aed,stroke:#a78bfa,color:#fff
style Views fill:#1a1a2e,stroke:#a78bfa,color:#e5e5e5
style Hooks fill:#1e3a5f,stroke:#3b82f6,color:#e5e5e5
style Lib fill:#1a3328,stroke:#22c55e,color:#e5e5e5
```
### Data Flow: Chat Message Lifecycle
```mermaid
sequenceDiagram
participant User
participant ChatInput
participant useChat
participant engine.ts
participant WebLLM
participant IndexedDB
User->>ChatInput: Type message + Enter
ChatInput->>useChat: sendMessage(content)
useChat->>useChat: Create user msg + empty assistant msg
useChat->>engine.ts: streamChat(history)
engine.ts->>WebLLM: chat.completions.create(stream:true)
loop Token Streaming
WebLLM-->>engine.ts: yield delta token
engine.ts-->>useChat: yield token
useChat-->>useChat: Append to assistant msg
useChat-->>ChatInput: Re-render (streaming)
end
useChat->>useChat: Finalize msg, generate title
useChat->>IndexedDB: saveSessions(updated)
useChat-->>User: Complete response displayed
```
### Model Loading Flow
```mermaid
sequenceDiagram
participant User
participant ModelSelector
participant useModel
participant engine.ts
participant WebLLM
participant HuggingFace as HF CDN
User->>ModelSelector: Click model card
ModelSelector->>useModel: load(modelId)
useModel->>useModel: setState(downloading, 0%)
useModel->>engine.ts: loadModel(modelId, onProgress)
engine.ts->>WebLLM: CreateMLCEngine(modelId)
WebLLM->>HuggingFace: Fetch model weights (WASM/WebGPU)
loop Download Progress
HuggingFace-->>WebLLM: Chunk data
WebLLM-->>engine.ts: InitProgressReport
engine.ts-->>useModel: progress callback
useModel-->>ModelSelector: Update progress bar
end
WebLLM-->>engine.ts: Engine ready
engine.ts-->>useModel: resolve
useModel->>useModel: setState(ready, 100%)
useModel-->>User: Model badge shown ✓
```
---
## Tech Stack
| Layer | Technology |
|-------|-----------|
| **Framework** | Vite 8 + React 19 + TypeScript 6 |
| **AI Runtime** | [@mlc-ai/web-llm](https://github.com/mlc-ai/web-llm) (WebGPU + WASM) |
| **UI Effects** | [border-beam](https://www.npmjs.com/package/border-beam) |
| **Persistence** | IndexedDB (sessions, messages) |
| **Deployment** | GitHub Pages via GitHub Actions |
| **Build** | Vite, ESNext target |
---
## Supported Models
| Model | Parameters | Size | Provider |
|-------|-----------|------|----------|
| **Qwen 3 0.6B** ⭐ | 0.6B | ~400 MB | Alibaba |
| Qwen 3 1.7B | 1.7B | ~1 GB | Alibaba |
| Qwen 3 4B | 4B | ~2.5 GB | Alibaba |
| **Qwen 3.5 0.8B** ⭐ | 0.8B | ~500 MB | Alibaba |
| Qwen 3.5 2B | 2B | ~1.2 GB | Alibaba |
| **Qwen 2.5 0.5B** ⭐ | 0.5B | ~350 MB | Alibaba |
| Qwen 2.5 1.5B | 1.5B | ~900 MB | Alibaba |
| Qwen 2.5 3B | 3B | ~1.8 GB | Alibaba |
| Qwen 2.5 Coder 1.5B | 1.5B | ~900 MB | Alibaba |
| **SmolLM2 360M** | 360M | ~200 MB | HuggingFace |
| SmolLM2 1.7B | 1.7B | ~1 GB | HuggingFace |
| **Gemma 2 2B** | 2B | ~1.3 GB | Google |
| **Gemma 3 4B** | 4B | ~2.5 GB | Google |
| Gemma 3 1B | 1B | ~700 MB | Google |
| **Phi 3.5 Mini** | 3.8B | ~2 GB | Microsoft |
| **Phi 4 Mini** ⭐ | 3.8B | ~2.2 GB | Microsoft |
| **DeepSeek R1 Distill Qwen 1.5B** ⭐ | 1.5B | ~1 GB | DeepSeek |
| **Llama 3.2 1B** | 1B | ~700 MB | Meta |
| **Llama 3.2 3B** | 3B | ~1.8 GB | Meta |
| TinyLlama 1.1B | 1.1B | ~600 MB | Community |
| StableLM 2 Zephyr 1.6B | 1.6B | ~950 MB | Stability AI |
| InternLM 2.5 1.8B | 1.8B | ~1.1 GB | Shanghai AI Lab |
| OLMo 1B | 1B | ~600 MB | Allen Institute |
⭐ = Recommended for most users
---
## Competitive Analysis
Roadmap informed by deep analysis of these leading AI chat platforms:
| Product | Stars | Key Differentiator | Monday Relevance |
|---------|-------|-------------------|-----------------|
| [OpenClaw](https://github.com/openclaw/openclaw) | 364k | Personal always-on AI assistant: multi-channel (WhatsApp/Telegram/Slack/Discord/…), SOUL.md identity, **AgentSkills/SKILL.md ecosystem**, ClawHub registry (52.7k skills, 12M installs), Skill Workshop AI, per-agent allowlists | **Skills system** (SKILL.md spec), skill marketplace, SOUL.md persona persistence, self-improving agent memory |
| [Open WebUI](https://github.com/open-webui/open-webui) | 132k | Full-featured self-hosted AI platform: RAG, pipelines, MCP, RBAC, voice/video, image gen | Feature-complete reference for chat UX, RAG, tools |
| [NextChat](https://github.com/ChatGPTNextWeb/NextChat) | 88k | Lightweight cross-platform AI client: Vercel deploy, MCP, masks, artifacts, Tauri desktop | Lightweight UX, prompt templates, artifacts rendering |
| [LobeHub](https://github.com/lobehub/lobe-chat) | 75k | Agent-as-unit-of-work platform: 10k+ plugins, agent groups, personal memory, TTS/STT | Agent system, plugin ecosystem, memory architecture |
| [Jan](https://github.com/janhq/jan) | 42k | Offline desktop ChatGPT: local LLMs via llama.cpp, custom assistants, OpenAI-compatible API | Offline-first philosophy, model management, MCP integration |
| [GPT-Runner](https://github.com/nicepkg/gpt-runner) | 379 | AI presets for code: conversations with code files, IDE integration, version-controlled prompts | Preset system, project-scoped AI configuration |
| [Claude Code](https://github.com/anthropics/claude-code) | 118k | Terminal coding agent: deep codebase understanding, multi-step agentic task execution, bash/git/test tools, CLAUDE.md project config, plugins directory, `@claude` GitHub tagging, `computer_use` tool (screenshot→observe→action loop in sandboxed VM) | **Agent mode** (v0.30), **plugin system** (v0.27), **task brief** (CLAUDE.md equivalent), **computer-use loop** (v1.3) |
| [browser-use](https://github.com/browser-use/browser-use) | 90.4k | LLM-controlled browser automation: Playwright-backed agent, click/type/scroll/navigate/screenshot/extract-text primitives, skills directory, AGENTS.md + CLAUDE.md conventions, CLI, cloud hosting, 100-task real-world benchmark | **Browser-use agent** (v1.3): action primitives, sandboxed iframe execution loop, DOM-state context, screenshot observation |
| [Playwright MCP](https://github.com/microsoft/playwright-mcp) | 31.4k | MCP server for browser automation: navigate/click/fill/screenshot/DOM tools via accessibility tree (no vision model needed); vision + coordinate-based modes opt-in; used by VS Code, Cursor, Claude Desktop, Codex, Copilot | **Playwright MCP bridge** (v1.3): connect Monday's v0.27 MCP client to `@playwright/mcp` for full external-browser control |
---
## Roadmap
> **North Star (immutable)**: _A local-first, browser-native AI workstation._
> WebGPU inference + optional remote providers, with first-class memory,
> tools and offline capability — all running entirely in the user's browser.
>
> **Three non-negotiable axes** every release must satisfy:
>
> 1. **Local-first** — every feature works with WebGPU + IndexedDB only;
> cloud providers are an option, never a requirement.
> 2. **Phase progression** — releases ship the **earliest unreleased
> version** in `### Versioned task breakdown` end-to-end. No skipping
> versions, no scope outside the listed checkboxes.
> 3. **Release gate** — a version is "done" only when its release gate is
> green. Trivial built-ins or polish do **not** unlock the next version.
### Versioned task breakdown
The autonomous Cron picks the **first unchecked, unblocked** item in the
**earliest unreleased version** and ships it end-to-end (code + build green
+ visible in UI + entry in CHANGELOG). It never invents scope outside this
list, and never skips a version. Past versions remain documented as a
historical record below.
#### v0.25 — Knowledge & RAG (storage layer) _(current target)_
Phase 5 of the legacy plan, split for scope safety. RAG is the highest-value
unmet feature in the product.
- [x] **Document upload** — Upload PDFs / TXT / MD files into a "Knowledge"
panel (PDF parsing via `pdfjs-dist`)
- [x] **Client-side chunking** — Split documents into ~500-token chunks
in-browser (no server)
- [x] **Browser vector store** — IndexedDB-backed vector store with
cosine similarity, schema migration registered in `storage.ts`
- [x] **Knowledge bases** — Organize documents into named collections;
attach a collection to a session
**Release gate**: a user uploads a 5-page PDF, sees chunks indexed, and a
search box returns the top-K matching chunks (no LLM yet — that's v0.26).
Released: 2026-04-25
#### v0.26 — RAG (retrieval + citation)
- [x] **Embedding model** — Run a small embedding model via Web-LLM
(e.g. `gte-small` MLC build) and persist embeddings
- [x] **Semantic search** — On send, query the active knowledge base and
inject top-K chunks into the system prompt
- [x] **Citation display** — Show which chunks were used per assistant
message, with click-to-open
- [x] **Citation persistence** — Citations survive page reload (stored
alongside message in IndexedDB)
**Release gate**: a question answered using a chunk shows a citation that
opens to the exact span of the source document; reload preserves it.
Released: 2026-04-26
#### v0.27 — Tools, Function calling, MCP
Phase 6 advanced — the **only** sanctioned tools work. Net-new built-in
mini-tools (calculator / clock / unit converter / JSON formatter / one-shot
web-search button / standalone formatter) are **out of scope**: they
distract from the function-calling / plugin / MCP work that actually
lets users plug in *any* tool. Mini-tools, if at all, ship later **as
plugins** through the system below.
- [x] **Function calling** — Parse model tool-call outputs (OpenAI-style
`tool_calls` JSON) and dispatch to in-browser functions
- [x] **Plugin system** — Load third-party tool plugins from URL
(JSON manifest declaring `name / description / inputSchema /
handlerUrl`)
- [x] **MCP client** — Connect to an MCP server (WebSocket transport) and
expose its tools to the model
- [x] **Tool call inspector** — A panel that shows the request / response
/ latency of every tool call in a session
**Release gate**: a user installs one external plugin from URL or connects
to one MCP server, the model invokes a tool from it, and the inspector
shows the full request / response.
Released: 2026-04-26
#### v0.28 — Collaboration & Sharing
- [x] **Share conversations** — Generate a shareable static HTML export
(no server)
- [x] **Import/export** — Full data import / export (sessions, personas,
settings, knowledge bases) as a single `.monday` zip
- [x] **WebDAV sync** — Cross-device sync via user-supplied WebDAV server
- [x] **Shared personas** — Publish a persona to a static community
registry (curated JSON file in the repo)
- [x] **Conversation forking** — Branch a session at any message;
branches are siblings, navigable in the sidebar
**Release gate**: round-trip import → export → re-import preserves every
session, persona and knowledge base byte-for-byte.
Released: 2026-04-26
#### v0.29 — Desktop, PWA polish & shortcuts
- [x] **Update prompt** — Banner when a new service worker is installed
- [x] **Offline indicator** — Header chip when offline; gracefully
disable cloud-only features
- [x] **Background notifications** — Notify when a long generation
completes while the tab is hidden (uses existing
`useNotifications`)
- [x] **Desktop app** — Tauri wrapper that targets macOS / Windows / Linux
- [x] **Keyboard shortcuts overlay** — `?` opens a list of every shortcut
(Cmd+K / Cmd+N / Cmd+⇧S / Cmd+E …); shortcuts also documented in
the README
- [x] **Multi-window** — Open a conversation in a separate browser
window / Tauri window with shared IndexedDB
**Release gate**: a Tauri build runs on macOS with full chat + RAG +
tools functionality; offline mode degrades gracefully.
Released: 2026-05-31
#### v0.30 — Agent mode & analytics
- [x] **Multi-turn memory** — Auto-summarize early turns when the context
window is exceeded; summaries are visible and editable
- [x] **Agent mode** — Multi-step task execution with tool use (an outer
planner loop on top of v0.27 function calling)
- [x] **Model chaining** — Pipeline: fast model drafts → large model
refines, configurable per persona
- [x] **Batch generation** — Generate N responses in parallel and pick
the best
- [x] **Usage analytics** — Local-only dashboard: model usage, tokens
consumed, average tps, sessions per day
- [x] **i18n** — Multi-language interface (English, 中文, 日本語) with
language picker in settings
- [x] **Accessibility** — Screen-reader landmarks, keyboard-only
navigation, high-contrast theme
**Release gate**: a documented agent-mode demo solves a 3-step task
(search → summarize → save) end-to-end with zero manual intervention.
Released: 2026-04-27
#### v0.31 — Code Arena / Showdown Mode
A richer evolution of the existing **Model Comparison** view, inspired by
[WebDev Arena](https://web.lmarena.ai), [Design Arena](https://designarena.ai)
and the indie "Grass Field challenge" rigs that show up in Twitter dual-pane
screenshots: same prompt → two models → live HTML/canvas preview → shareable
recording. Net-new vs. v0.2's plain text-only comparison.
- [x] **Dual artifact panes** — Side-by-side terminal-style cards with
provider badge, model name, status (`pending / streaming / done`)
and generation duration in seconds
- [x] **Sandboxed iframe preview** — Each pane mounts the streamed
HTML/CSS/JS into a `sandbox="allow-scripts"` iframe, refreshed on
every chunk (debounced) and on a manual **↻ Run** button
- [x] **Code ↔ Preview tabs** — Per-pane toggle between rendered preview
and source view, with a **Copy** button on each
- [x] **Synchronized scroll** — Code view in both panes scrolls in
lockstep (line-aligned) to make diffs obvious
- [x] **Challenge prompt library** — Curated presets (Grass Field, Solar
System, Pelican on a Bicycle, Tetris, Snake, Bouncing Balls,
Particle System, CSS Loader Gallery), one-click load into the arena
- [x] **Recording & video export** — `MediaRecorder` captures both
iframes as a synchronized timelapse `.webm` (default 30 fps,
configurable), with a small "@username" watermark from settings
- [x] **PNG share card** — Export a single PNG with both final previews,
model names, durations and watermark — sized for Twitter (16:9)
- [x] **Verdict & local leaderboard** — `Team A / Tie / Team B` voting UI;
results persisted in IndexedDB and aggregated into a per-model
win/tie/loss table (purely local, no upload)
**Release gate**: a user picks two models, loads the "Grass Field"
preset, hits Send, sees both iframes animate side-by-side, exports a
`.webm` with watermark, votes a winner, and the leaderboard updates.
Released: 2026-04-29
#### v1.0 — External LLM Providers & Web Search _(stable)_
The "1.0" promise: anything saved in v1.0 keeps working until v2.0.
- [x] **OpenAI-compatible API** — Configure any OpenAI-compatible endpoint
(custom base URL + API key, stored encrypted in IndexedDB)
- [x] **Ollama integration** — Connect to a local Ollama server
(`http://localhost:11434`) with model auto-discovery
- [x] **LM Studio** — Connect to LM Studio's local OpenAI-compatible
server
- [x] **llama.cpp server** — Connect to `llama.cpp --server` HTTP mode
- [x] **vLLM** — Connect to a vLLM inference endpoint
- [x] **DeepSeek API** — First-class DeepSeek cloud provider (chat +
reasoner models)
- [x] **Provider switcher** — Per-session toggle between WebGPU local
inference and external API providers
- [x] **SearXNG integration** — Web search via a user-supplied SearXNG URL
- [x] **Stable storage schema v1** — Migration registry frozen; future
migrations must add, not break, fields
**Release gate**: a 24-hour soak test (1 hour with each provider) passes;
the storage migration test from v0.25 → v1.0 round-trips without loss.
Released: 2026-04-30
#### v1.1 — Skills System
Inspired by [OpenClaw's AgentSkills/SKILL.md ecosystem](https://docs.openclaw.ai/tools/skills) and
[ClawHub](https://clawhub.ai/) (52.7k tools, 12M downloads). Skills sit between personas
(identity) and plugins (tools): a skill is a **structured capability pack** that teaches
the model *how* to behave in a specialized domain — e.g. "Python Debugger",
"Technical Writer", "SQL Analyst". Multiple skills can be stacked in one session.
Persona = who the AI *is*. Plugin = what tools the AI has. Skill = what the AI *knows
how to do* (domain instructions, workflow steps, required-plugin declarations).
- [x] **Skill format** — Skill spec stored in IndexedDB: `name`, `description`,
`instructions` (markdown injected into system prompt), `requiredPlugins` (list
of plugin URLs/IDs), `version`, `tags`, `icon`
- [x] **Skill composer** — Per-session skill panel: attach 1–N skills alongside a
persona; active skills shown as chips in the session header; skill instructions
appended to the system prompt before each turn
- [x] **Skill registry** — Community skill registry (curated JSON file in the repo,
like persona registry) with 20+ launch skills across categories: Coding,
Writing, Research, Data, Language, Creative
- [x] **Skill builder UI** — In-app skill editor: name, description, tag picker,
markdown instructions with live token-count estimate, required-plugin picker,
export as `.monday-skill` JSON
- [x] **Skill + plugin binding** — A skill can declare required plugins by URL/ID;
installing a skill from the registry auto-prompts to install any missing
plugins (same flow as v0.27 plugin install)
- [x] **SOUL.md equivalent** — "Soul" tab in the persona editor: a persistent
cross-session identity prompt that survives `/new` and session resets; stored
in IndexedDB alongside the persona; separate from the per-session system prompt
- [x] **Skill marketplace UI** — Browse/search/install from the community registry;
show tags, install count (local-only counter), author; one-click install
- [x] **Skill hot-reload** — Changes to an active skill take effect on the next
message send (no session restart required)
**Release gate**: a user installs a "Python Debugger" skill from the registry, attaches
it to a new session alongside a persona, sends a debugging question, and the model
follows the skill's specialized workflow; the skill persists on page reload; the session
header shows the active skill chip.
Released: 2026-05-03
#### v1.2 — Self-Improving Agent & Persistent Memory
Inspired by the top-trending ClawHub skills: `self-improving-agent` (411k downloads),
`ontology` typed memory graph (171k downloads), and `self-improving + proactive agent`
(174k downloads). All state is local-only — nothing leaves IndexedDB.
- [x] **Persistent memory store** — Cross-session key-value memory backed by IndexedDB;
the model can read memories at session start and write new ones during the
conversation; memories panel shows all entries with edit/delete
- [x] **Memory namespaces** — Memories scoped to three levels: global (all sessions),
per-persona, per-skill; the active session inherits the union of applicable
namespaces
- [x] **Correction capture** — When a user edits or regenerates a message, optionally
record the correction as a named memory entry ("Prefer concise answers",
"Always use TypeScript strict mode"); visible in the memories panel
- [x] **Ontology store** — Typed entity graph: Person, Project, Task, Event, Document;
entities have properties + relationships; browsable/editable in a side panel;
injected as a compact context block when relevant entities are mentioned
- [x] **Session compaction with learning** — When compacting long sessions (v0.30
multi-turn memory), extract preference signals and entity mentions into the
memory store, not just a plain summary; user reviews before committing
- [x] **Skill Workshop (browser edition)** — After a session ends, the model proposes
skill refinements based on corrections, regenerations, and user edits;
proposals shown in a diff view; user approves → saved to the relevant skill
in IndexedDB
- [x] **Memory-aware personas** — A persona can declare which memory namespaces it
reads on activation (e.g. "global" + "per:this-persona"); persona editor shows
a memory preview panel
**Release gate**: after 3 sessions with a persona, the memory panel shows ≥5
automatically captured preferences; a Skill Workshop proposal is generated, approved,
and the next session reflects the updated skill instructions.
Released: 2026-05-03
#### v1.3 — Browser-Use & Computer-Use (In-Browser Agent Loop)
Inspired by [Claude Code's `computer_use` tool](https://github.com/anthropics/claude-code)
(screenshot → observe → action loop in a sandboxed VM), [browser-use](https://github.com/browser-use/browser-use)
(90.4k ⭐ — LLM-controlled Playwright agent with skills directory and action primitives),
[Playwright MCP](https://github.com/microsoft/playwright-mcp) (31.4k ⭐ — accessibility-tree
MCP server used by VS Code / Cursor / Codex), and
[Codex CLI's](https://github.com/openai/codex) sandboxed bash/file/edit execution model.
Extends the v0.30 agent loop and v0.27 MCP client into a full browser-use and
in-browser computer-use system.
**Three execution tiers** of increasing capability:
- **Tier 1 — Sandboxed iframe agent**: model generates HTML/CSS/JS → renders in a
`sandbox="allow-scripts"` iframe → `html2canvas` screenshot → model observes →
next action. 100% in-browser, zero external dependencies.
- **Tier 2 — DOM-state computer-use**: serialize the active iframe's accessibility
tree to compact JSON and inject as a context block; model issues action commands
(click, type, scroll, navigate); dispatcher translates to DOM events. Inspired by
Playwright MCP's accessibility-tree approach — no vision model required.
- **Tier 3 — Playwright MCP bridge**: connect Monday's v0.27 MCP client to a
locally-running `@playwright/mcp` server; full external-browser control
(navigate real URLs, fill forms, run tests) with model in the loop; every
action logged in the existing tool-call inspector.
- [x] **Agent action primitives** — `navigate`, `click`, `type`, `scroll`,
`extract-text`, `take-screenshot`, `read-dom`; each is a named MCP-style
tool callable by the model via the v0.27 function-calling layer
- [x] **Sandboxed iframe execution loop (Tier 1)** — generate → render in
`sandbox="allow-scripts"` iframe → `html2canvas` screenshot → attach as
image to next LLM call → iterate; debounced auto-refresh + manual ↻ Run;
reuses the iframe infra planned for v0.31 Code Arena
- [x] **DOM-state capture (Tier 2)** — serialize active iframe's accessibility
tree (ARIA roles, labels, input states) to compact JSON injected into context
before each model turn; depth + node-count budget to stay token-safe
- [x] **Vision mode (Tier 1/2)** — `OffscreenCanvas` / `html2canvas` screenshot
attached as base64 image in the next LLM call; requires a multimodal model
(e.g. Qwen-VL); falls back to DOM-state mode for non-vision models automatically
- [x] **Playwright MCP bridge (Tier 3)** — one-click connect in the MCP panel;
Monday auto-discovers `@playwright/mcp` if already configured;
domain allowlist + blocked-origins enforced per task brief
- [x] **Task brief (AGENTS.md / CLAUDE.md equivalent)** — per-task markdown config
declaring goal, allowed domains, step budget, and stop criteria;
stored in IndexedDB; shown as a collapsible header above the agent thread
- [x] **Agent audit trail** — chronological log of every action + observation +
screenshot thumbnail; collapsible per step inside the chat thread; inspired by
Codex CLI's terminal-log citation model and Codex Web's task-delegation audit view
- [x] **Async task queue** — "delegate and come back" UI inspired by Codex Web:
submit a browser task, minimize the panel, get notified via the v0.29
background notification system when the agent finishes or needs human input
- [x] **Sandbox security model** — Tier 1: `sandbox="allow-scripts"` only (no
`allow-same-origin`); Tier 3: domain allowlist + `--blocked-origins` forwarded
to Playwright MCP; credentials redacted in audit trail logs (mirrors
browser-use's `fill()` debug-log redaction practice)
**Release gate**: a user opens the agent panel, gives the task "fill in the sandboxed
form and click Submit", the agent executes ≥5 actions (screenshot → click → type →
submit → screenshot), the audit trail shows every step with thumbnails, the async
task queue marks it done and triggers a notification, and the final iframe state
is visible in the panel.
Released: 2026-05-12
#### v1.4 — Persona Marketplace & Image Input
Extending the persona system (v1.1) with community discovery and multimodal input.
- [x] **Persona marketplace browsing** — Browse community personas from the curated
registry (already exists as `PERSONA_REGISTRY`); add search/filter by category,
sort by install count; one-click install to the local persona store; shows
persona preview (system prompt snippet, params, soul) before installing
- [x] **Image input** — Paste or drop an image into the chat input; for vision-capable
models, the image is attached as a base64 data URL in the next LLM call;
non-vision models show a graceful "vision not available" message ✅
- [x] **Full PWA** — Service worker with cache-first strategy for app shell + model
weights; offline fallback page; install banner on repeat visits from desktop ✅
**Release gate**: a user browses the persona marketplace, installs a new persona,
switches to it in a session, and the persona's soul and system prompt are active;
a user pastes an image into chat and the vision model processes it.
Released: 2026-05-13
#### v1.5 — Voice & TTS — Multimodal I/O
Voice input and text-to-speech output for hands-free interaction,
inspired by [Open WebUI's voice features](https://github.com/open-webui/open-webui) and
[NextChat's voice support](https://github.com/ChatGPTNextWeb/NextChat).
- [x] **Voice input** — Browser Speech Recognition API for voice-to-text in the chat input;
real-time transcription with interim results shown as placeholder text;
stop button to end recording; automatic send on silence detection (configurable timeout) ✅
- [x] **TTS output** — Web Speech API text-to-speech for assistant responses; per-message play/pause/stop controls;
voice selector (if available); auto-play toggle in settings;
graceful fallback message when TTS is not supported ✅
**Release gate**: a user speaks into the microphone, sees real-time transcription,
and the text is sent as a message; a user plays TTS on an assistant message
and the browser speaks the response.
Released: 2026-05-13
#### v1.6 — Context Injection
Allow users to attach reusable text and code snippets to any session.
Snippets are injected into the system prompt before each turn, giving
the model persistent context without requiring full RAG.
- [x] **Context library** — Create, name, and organize text/code snippets;
each snippet has a title, content (markdown), and optional category tag
- [x] **Session context attachment** — Attach one or more snippets to a session;
attached snippets appear as a collapsible context block in the chat header ✅
- [x] **Context injection** — Attached snippets are prepended to the system
prompt before each turn; context is visible in a "Context" panel alongside
the message thread
- [x] **Quick context** — One-click context templates (e.g. "Project README",
"API Reference", "Coding Standards") loaded from a built-in catalog ✅
- [x] **Context search** — Search the snippet library by title and content;
filter by category ✅
**Release gate**: a user creates a snippet, attaches it to a session, and the
model's response reflects knowledge of the snippet content.
Released: 2026-05-30
#### Cross-cutting standing rules
These apply to **every** version and are enforced by the cron:
1. **No "miscellaneous mini-tool" releases.** A built-in tool that takes
<1 day to implement (calculator, clock, formatter, converter,
one-shot web-search button) does **not** count as a version and
**must not** be added directly. Such utilities ship later as
first-class plugins via the v0.27 plugin / MCP system, not as
bespoke React components.
2. **HEARTBEAT.md cites the current target version + the exact
checkbox(es) in flight.** The Next Steps list is taken verbatim from
this file, not invented.
3. **Local-first invariant** — every new feature must work with the
default WebGPU + IndexedDB stack; remote providers are additive.
4. **Storage schema is versioned** — any IndexedDB schema change ships
with a forward migration in `src/lib/storage.ts`.
5. **No skipping versions** — if v0.25 is unfinished, work on v0.25 only.
If every checkbox in the current version is blocked, the cron must
spend the slot on tests, docs, refactors or accessibility for that
version, **not** on a later version or on net-new mini-tools.
### Historical phases (for reference)
Phases 1–3, Phase 0.8 and parts of Phases 4 / 6 shipped in v0.2 → v0.21.
They remain documented below as a record but are **not authoritative**
for future work — the `### Versioned task breakdown` above is.
> Note: v0.22–v0.24 (Calculator / Web Search / Unit Converter / JSON
> Formatter / Current Time) were rolled back on 2026-04-25 because they
> bypassed this Roadmap. Those features will return only as plugins via
> v0.27.
#### Phase 1 — Core Chat Enhancement (v0.2.x)
> Bring chat to feature parity with basic ChatGPT UX
- [x] **Markdown rendering** — Render assistant responses with proper Markdown, code blocks, syntax highlighting
- [x] **Code copy button** — One-click copy for code blocks
- [x] **LaTeX support** — Math equation rendering with KaTeX
- [x] **System prompt** — Customizable system prompt per session
- [x] **Generation params** — Temperature, top_p, max_tokens sliders
- [x] **Auto-scroll control** — Pause auto-scroll when user scrolls up
- [x] **Chat export** — Export conversations as Markdown/JSON
- [x] **Token counter** — Display tokens/sec and total token usage
- [x] **Message actions** — Copy, regenerate, edit user messages
### Phase 2 — Model Management (v0.3.x)
> Rich model lifecycle and expanded model support
- [x] **Model cache manager** — View/delete cached models, show disk usage
- [x] **More models** — Add Llama 3.2 1B/3B, DeepSeek-R1-Distill, Mistral 7B, Stable Code 3B
- [x] **Model benchmarks** — Auto-run speed benchmark on load, show tokens/sec
- [x] **Custom model import** — Load custom MLC-compiled models from URL
- [x] **Model comparison** — Side-by-side generation from two models
- [x] **Download resume** — Resume interrupted model downloads with progress persistence
- [x] **Storage quota** — Show browser storage used vs available
### Phase 3 — Prompt Templates & Personas (v0.7.x)
> Inspired by NextChat masks, GPT-Runner presets, LobeHub agents
- [x] **Prompt templates** — Pre-built conversation starters (coding assistant, translator, tutor, etc.)
- [x] **Custom personas** — Create/save/share AI personas with system prompts + params
- [ ] **Persona marketplace** — Browse community-shared personas (static JSON registry)
- [x] **Quick prompts** — Slash commands (`/translate`, `/code`, `/explain`) in chat input
- [ ] **Context injection** — Attach text/code snippets as context before sending
### Phase 4 — Multimodal & Rich Input (v0.5.x)
> Add vision and file capabilities as models support them
- [ ] **Image input** — Paste/upload images for vision models (when WebGPU vision models available)
- [ ] **File upload** — Attach text files as conversation context
- [ ] **Drag & drop** — Drag files directly into chat
- [ ] **Clipboard paste** — Intelligent paste handling (images, code, rich text)
- [ ] **Voice input** — Browser Speech Recognition API for voice-to-text
- [ ] **TTS output** — Read assistant responses aloud via Web Speech API
### Phase 5 — Knowledge & RAG (v0.6.x)
> Local-first retrieval augmented generation, inspired by Open WebUI RAG
- [ ] **Document upload** — Upload PDFs, TXT, MD files
- [ ] **Client-side chunking** — Split documents into chunks in-browser
- [ ] **Browser vector store** — IndexedDB-based vector storage
- [ ] **Embedding model** — Run small embedding model via Web-LLM
- [ ] **Semantic search** — Query uploaded documents before sending to LLM
- [ ] **Citation display** — Show which document chunks were used in response
- [ ] **Knowledge bases** — Organize documents into named collections
### Phase 6 — Tools & Plugins (v0.7.x)
> Function calling and tool use, inspired by LobeHub plugins and Open WebUI tools
- [ ] **Function calling** — Parse model tool-call outputs and execute browser-side functions
- [ ] **Built-in tools** — Calculator, current time, unit converter, JSON formatter
- [ ] **Web search** — Browser-side web search integration (via public APIs)
- [ ] **Code execution** — Sandboxed JavaScript execution in iframe
- [ ] **Artifacts** — Render generated HTML/SVG/Mermaid in preview panel (like NextChat artifacts)
- [ ] **Plugin system** — Load third-party tool plugins from URL (JSON manifest)
- [ ] **MCP client** — Model Context Protocol support for external tool servers
### Phase 0.8 — Personalization & Discovery (v0.8.x)
> Personalized experience and easier conversation discovery
- [x] **Model usage tracking** — Automatically track which models you use most
- [x] **Recommended models** — Top 3 most-used models displayed in Model Selector
- [x] **Reset recommendations** — Clear usage history to reset model recommendations
- [x] **Session search** — Search conversations by title in the sidebar
- [x] **Date filtering** — Filter sessions by Today, Yesterday, This Week, This Month
- [ ] **Model usage stats** — Visual chart of model usage frequency
- [x] **Recent models** — Quick access to recently used models
### Phase 7 — Collaboration & Sharing (v0.9.x)
> Social features inspired by LobeHub channels and Open WebUI community
- [ ] **Share conversations** — Generate shareable link (static HTML export)
- [ ] **Import/export** — Full data import/export (sessions, personas, settings)
- [x] **WebDAV sync** — Sync data across devices via WebDAV (like NextChat)
- [ ] **Shared personas** — Publish personas to community registry
- [ ] **Conversation forking** — Branch a conversation at any message
### Phase 8 — Desktop & PWA (v0.9.x)
> Expand beyond browser tab, inspired by Jan desktop and NextChat Tauri
- [ ] **Full PWA** — Offline-capable progressive web app with service worker
- [ ] **Install prompt** — Smart install banner for mobile and desktop
- [ ] **Notifications** — Background generation completion notifications
- [ ] **Desktop app** — Tauri wrapper for native macOS/Windows/Linux
- [ ] **Keyboard shortcuts** — Full keyboard navigation (Cmd+K, Cmd+N, etc.)
- [ ] **Multi-window** — Open conversations in separate windows/tabs
### Phase 9 — Advanced AI Features (v1.0.x)
> Towards a complete local AI workstation
- [ ] **Multi-turn memory** — Compress long conversations for extended context
- [ ] **Agent mode** — Multi-step task execution with tool use
- [ ] **Model chaining** — Pipeline: fast model drafts → large model refines
- [ ] **Batch generation** — Generate multiple responses and pick best
- [ ] **A/B testing** — Compare model outputs with user ratings
- [ ] **Usage analytics** — Local analytics dashboard (model usage, tokens, sessions)
- [ ] **i18n** — Multi-language interface (English, 中文, 日本語, etc.)
- [ ] **Accessibility** — Screen reader support, keyboard navigation, high contrast
### Phase 10 — External LLM Providers & Web Search (v1.1.x)
> Connect to cloud and local AI servers alongside native WebGPU inference
- [ ] **OpenAI-compatible API** — Configure any OpenAI-compatible endpoint (custom base URL + API key)
- [ ] **Ollama integration** — Connect to a local Ollama server (http://localhost:11434)
- [x] **LM Studio** — Connect to LM Studio's built-in OpenAI-compatible local server
- [x] **llama.cpp server** — Connect to llama.cpp's HTTP server (`--server` mode)
- [x] **vLLM** — Connect to a vLLM inference server endpoint
- [x] **DeepSeek API** — First-class DeepSeek cloud API provider (chat + reasoner models)
- [x] **Provider switcher** — Toggle between WebGPU local inference and external API providers in-session
- [x] **SearXNG integration** — Web search via a self-hosted SearXNG instance URL
- [ ] **Web search tool** — Inject search results as context before sending to the model
---
## Keyboard Shortcuts
| Shortcut | Action |
|----------|--------|
| `⌘K` | Toggle Command Palette |
| `⌘N` | New Chat |
| `⌘⇧S` | Stop Generation |
| `⌘1` | Models |
| `⌘2` | Model Cache |
| `⌘3` | Usage Statistics |
| `⌘4` | Persona Marketplace |
| `⌘5` | Knowledge |
| `⌘6` | Model Comparison |
| `⌘7` | Model Benchmark |
| `⌘8` | Custom Model Import |
| `⌘9` | Plugins |
| `⌘0` | MCP Servers |
| `⌘⇧E` | Export All Data |
| `⌘⇧I` | Import Data |
| `?` | Keyboard Shortcuts Overlay |
On Windows/Linux, replace `⌘` with `Ctrl`.
---
## Development
```bash
npm install # Install dependencies
npm run dev # Start dev server (http://localhost:5173)
npm run build # Production build to dist/
npm run preview # Preview production build
```
## Requirements
- Chrome 113+ or Edge 113+ (WebGPU support required)
- GPU with 2GB+ VRAM recommended
- ~200MB–2GB storage per model (cached in browser)
## Project Structure
```
monday/
├── public/
│ ├── favicon.svg # App icon (purple gradient smiley)
│ ├── apple-touch-icon.svg # iOS home screen icon
│ └── manifest.json # PWA manifest
├── src/
│ ├── App.tsx # Root: view router, state orchestration
│ ├── App.css # All component styles
│ ├── components/
│ │ ├── Sidebar.tsx # Session list, brand, version link
│ │ ├── ModelSelector.tsx # Model cards with BorderBeam
│ │ ├── MessageList.tsx # Chat message rendering
│ │ ├── ChatInput.tsx # Input textarea with send/stop
│ │ ├── Changelog.tsx # Expandable release history
│ │ ├── ThemeToggle.tsx # Light/Dark/System switcher
│ │ └── WebGPUCheck.tsx # WebGPU compatibility warning
│ ├── hooks/
│ │ ├── useChat.ts # Session/message/streaming state
│ │ ├── useModel.ts # Model load/unload/progress
│ │ └── useTheme.ts # Theme persistence + system detection
│ ├── lib/
│ │ ├── engine.ts # Web-LLM singleton, streamChat()
│ │ ├── models.ts # Model registry (7 models)
│ │ ├── storage.ts # IndexedDB CRUD
│ │ └── changelog.ts # Version history data
│ └── types/
│ └── index.ts # TypeScript interfaces
├── index.html # Entry HTML with mobile meta tags
├── vite.config.ts # Vite config (base: '/monday/')
└── package.json # v0.1.0
```
## License
MIT