dulus 0.2.56__tar.gz → 3.3.4__tar.gz

dulus-3.3.4/MANIFEST.in

@@ -0,0 +1,7 @@
+include pyproject.toml
+recursive-include docs *
+recursive-include data *
+recursive-include sandbox/dist *
+recursive-include webbridge *
+global-exclude __pycache__/*
+global-exclude *.pyc

{dulus-0.2.56 → dulus-3.3.4}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: dulus
-Version: 0.2.56
-Summary: Spanish-first multi-provider AI CLI — 14 NVIDIA models free, Mesa Redonda, voice, TTS, RTK token reducer, MemPalace
+Version: 3.3.4
+Summary: Use IA as an agent without an API key. $0. Harvest your browser session for Gemini (guest, no login), Claude.ai, Claude Code, Kimi.com, Qwen, DeepSeek — drive them like an API, no per-token billing. Plus LiteLLM (100+ paid providers), local models via Ollama, /lang in 34 languages, Mesa Redonda, voice, OCR, MemPalace, embedded sandbox OS.
 Author: KevRojo
 License: GPL-3.0
 Project-URL: Homepage, https://github.com/KevRojo/Dulus
@@ -36,25 +36,47 @@ Requires-Dist: Pillow>=10.0.0
 Requires-Dist: typing-extensions>=4.10.0
 Requires-Dist: composio>=1.0.0rc2
 Requires-Dist: beautifulsoup4>=4.12.0
+Requires-Dist: sentry-sdk>=2.0.0
+Requires-Dist: pytesseract>=0.3.10
 Provides-Extra: memory
 Requires-Dist: mempalace>=3.3.4; extra == "memory"
 Provides-Extra: voice
 Requires-Dist: sounddevice; extra == "voice"
+Requires-Dist: elevenlabs>=1.0.0; extra == "voice"
+Provides-Extra: webbridge
+Requires-Dist: playwright>=1.40.0; extra == "webbridge"
+Provides-Extra: litellm
+Requires-Dist: litellm>=1.50.0; extra == "litellm"
+Provides-Extra: ocr
+Requires-Dist: pytesseract>=0.3.10; extra == "ocr"
+Requires-Dist: Pillow>=10.0.0; extra == "ocr"
+Provides-Extra: ocr-deep
+Requires-Dist: pytesseract>=0.3.10; extra == "ocr-deep"
+Requires-Dist: Pillow>=10.0.0; extra == "ocr-deep"
+Requires-Dist: easyocr>=1.7.0; extra == "ocr-deep"
 Provides-Extra: full
 Requires-Dist: mempalace>=3.3.4; extra == "full"
 Requires-Dist: sounddevice; extra == "full"
+Requires-Dist: elevenlabs>=1.0.0; extra == "full"
+Requires-Dist: playwright>=1.40.0; extra == "full"
+Requires-Dist: litellm>=1.50.0; extra == "full"
+Requires-Dist: pytesseract>=0.3.10; extra == "full"
 Dynamic: license-file
 
 # ▲ DULUS
-
-> **Hunt. Patch. Ship.** A Python autonomous agent that flies on any model — Claude, GPT, Gemini, DeepSeek, Qwen, Kimi, Zhipu, MiniMax, and local models via Ollama. ~12K lines of readable Python. No build step. No gatekeeping. Just talons.
+>
+> `pip install dulus` → press Enter → working IA in 30 seconds. Try it.
 
 SET /sticky_input ON since the first run for the best experience!
 
 <p align="center">
-  <img src="https://raw.githubusercontent.com/KevRojo/Dulus/main/docs/hero.svg" alt="Dulus" width="100%">
+  
+  <img width="700" height="665" alt="mascot-hero" src="https://github.com/user-attachments/assets/8b122834-552c-4bd4-b46d-3e17deb74ab5" />
+
 </p>
 
+<p align="center"><i>The Dulus (Cigua Palmera) — Dominican national bird. Named after the bird, not the rocket.</i></p>
+
 <p align="center">
   <a href="#quick-start"><b>Quick Start</b></a> ·
   <a href="#models"><b>Models</b></a> ·
@@ -69,12 +91,31 @@ SET /sticky_input ON since the first run for the best experience!
   <a href="https://pypi.org/project/dulus/"><img src="https://static.pepy.tech/badge/dulus?style=flat-square" alt="downloads"/></a>
   <img src="https://img.shields.io/badge/python-3.11+-ff6b1f?style=flat-square&labelColor=07070a" alt="python"/>
   <img src="https://img.shields.io/badge/license-GPLv3-ff6b1f?style=flat-square&labelColor=07070a" alt="license"/>
-  <img src="https://img.shields.io/badge/version-v0.2.52-ff6b1f?style=flat-square&labelColor=07070a" alt="version"/>
-  <img src="https://img.shields.io/badge/providers-11-ff6b1f?style=flat-square&labelColor=07070a" alt="providers"/>
-  <img src="https://img.shields.io/badge/tools-27-ff6b1f?style=flat-square&labelColor=07070a" alt="tools"/>
+  <img src="https://img.shields.io/badge/version-v3.3.3-ff6b1f?style=flat-square&labelColor=07070a" alt="version"/>
+  <img src="https://img.shields.io/badge/providers-100%2B%20via%20LiteLLM-ff6b1f?style=flat-square&labelColor=07070a" alt="providers"/>
+  <img src="https://img.shields.io/badge/tools-30%2B-ff6b1f?style=flat-square&labelColor=07070a" alt="tools"/>
   <img src="https://img.shields.io/badge/tests-263+-ff6b1f?style=flat-square&labelColor=07070a" alt="tests"/>
+  <a href="https://x.com/KevRojo"><img src="https://img.shields.io/badge/x-%40KevRojo-ff6b1f?style=flat-square&labelColor=07070a&logo=x" alt="x"/></a>
 </p>
 
+<p align="center">
+  🌐 <b>Multilingual</b> ·
+  <a href="docs/README_EN.md">English</a> ·
+  <a href="docs/README_ES.md">Español</a> ·
+  <a href="docs/README_FR.md">Français</a> ·
+  <a href="docs/README_ZH.md">中文</a> ·
+  <a href="docs/README_JA.md">日本語</a> ·
+  <a href="docs/README_KO.md">한국어</a> ·
+  <a href="docs/README_PT.md">Português</a> ·
+  <a href="docs/README_RU.md">Русский</a> ·
+  <a href="docs/README_AR.md">العربية</a>
+</p>
+
+> **Official X / creator handle:** [@KevRojo](https://x.com/KevRojo) — that's me, the only contributor to this repo. Any other account claiming to be Dulus is a copycat.
+>
+> **$DULUS AI token  Solana):** [`9R8rrjXxcfQPmLTCLhmVpjr2uesjjkcgkinE6Lwdpump`](https://dexscreener.com/solana/9R8rrjXxcfQPmLTCLhmVpjr2uesjjkcgkinE6Lwdpump)
+
+-----
 <p align="center">
   <code>pip install dulus</code>
 </p>
@@ -82,26 +123,33 @@ SET /sticky_input ON since the first run for the best experience!
 <p align="center"><img src="https://raw.githubusercontent.com/KevRojo/Dulus/main/docs/divider.svg" alt="" width="100%"></p>
 
 <p align="center">
-  <a href="https://kevrojo.github.io/Dulus/"><b>🌐 Visit the Dulus website →</b></a><br>
+  <a href="https://dulus.ai/"><b>🌐 Visit the Dulus website →</b></a><br>
   <sub>The site covers features, demos, and details not documented in this README.</sub>
 </p>
 
 <p align="center"><img src="https://raw.githubusercontent.com/KevRojo/Dulus/main/docs/divider.svg" alt="" width="100%"></p>
 
-## What is this
-Talent cant be copied.
+## 🔥 What's new
 
-Dulus Reduce your IA costs by 60% parsing webchats and claude-code directly. Write poetry while Anthropic only see text.
-Use claude-code as an API without the new 'extra-usage' wall <3
+> Full changelog: [`docs/news.md`](docs/news.md)  ·  Inside the REPL: `/news`
 
-<p align="center"><img src="https://raw.githubusercontent.com/KevRojo/Dulus/main/docs/poetry-banner.png" alt="Anthropic only sees text while you and Claude are writing poetry" width="100%"></p>
+- **Dulus Agent — Telegram communities.** Dulus evolved from a CLI tool into a live AI agent inside Telegram groups. The first fully autonomous AI moderating and conversing in real communities — not a bot, not a filter, a real agent. Groups pay in $DULUS to activate him. We host Dulus for them — that's the business model. The CLI stays free forever. This is the paid layer. 🦅🇩🇴
 
-<img width="1240" height="882" alt="image" src="https://github.com/user-attachments/assets/27dd76bc-8919-4bb9-b3c3-38ae7d92e482" />
+- **v0.2.93 — IA WITHOUT AN API KEY, FIRST-RUN.** 🦅 The welcome wizard now offers, by default, to open Gemini in a browser and capture its **guest session** — no Google login, no API key, no credit card. From `pip install` to working IA in 30 seconds. Same flow works for Claude.ai / Kimi.com / Qwen / DeepSeek if you have those accounts. This was Dulus's ace under the sleeve. Now it's the front door.
+- **v0.2.92** — **`/lang` command.** 34 ISO codes + free-form descriptors. `/lang zh`, `/lang ja`, `/lang pt-br`, `/lang "speak as my gym tutor"`, `/lang "tigre de calle dominicano"`, `/lang "Yoda"`. The model role-plays the voice across the whole session. Triggered after Doubao (China's biggest IA assistant) started referring traffic to the repo.
+- **v0.2.91** — **CORS on the daemon.** The Android Sandbox APK now connects every app live — same daemon, finally cross-origin reachable.
+- **v0.2.89** — **Sandbox embedded INSIDE the desktop GUI.** Click `🦅 Sandbox` in the GUI Web tab → the Dulus OS renders inside the content frame via pywebview subprocess + Win32 `SetParent` reparent. Not a popup. Inside the frame.
+- **v0.2.89** — **Local OCR shipped first-class.** `/ocr` + `ExtractTextFromImage` tool, `WebBridgeScreenshot` auto-OCRs, `/img` sends image + verbatim OCR text together. Zero vision-model tokens for receipts / code screenshots / error stacks.
+- **v0.2.89** — **`kepano/obsidian-skills` bundled.** Dulus writes Obsidian-flavored markdown by default. Open `~/.dulus/memory/` as an Obsidian vault → instant graph view.
+- **v0.2.88** — **LiteLLM gateway: one provider entry, 100+ backends.** OpenRouter, Groq, Together, Bedrock, Vertex, Cohere, Perplexity, xAI, Mistral, Fireworks, Anyscale, Replicate, Azure, DeepInfra — the welcome wizard auto-installs the package and asks for the right per-backend key.
+- **v0.2.85** — **Slim wheel 11.4 MB → 2.5 MB.** Smaller than the original baseline.
 
+<p align="center"><img src="https://raw.githubusercontent.com/KevRojo/Dulus/main/docs/divider.svg" alt="" width="100%"></p>
 
-<p align="center">
-  <sub>⚡ <b>Saves you Claude tokens?</b> Throw a sat — BTC: <code>1JzatQDn9fMLnKTd3KYgztsLHC95bJEzSN</code></sub>
-</p>
+## What is this
+
+Dulus Reduce your IA costs by 60% parsing webchats and claude-code directly. Write poetry while Anthropic only see text.
+Use claude-code as an API without the new 'extra-usage' wall <3
 
 
 Another reminder of a Dulus magic spell: 
@@ -114,53 +162,79 @@ them:
 
 dulus get the prices of NVDA, TSLA, SP500:
 
-<img width="2094" height="1365" alt="image" src="https://github.com/user-attachments/assets/1551d651-9d69-4607-bac0-4adbde645783" />
-
 Be creative!!! 
 
 Dulus adapt any python repository <3
+---
 
-<p align="center"><img src="https://raw.githubusercontent.com/KevRojo/Dulus/main/docs/divider.svg" alt="" width="100%"></p>
+<p align="center"><img src="https://raw.githubusercontent.com/KevRojo/Dulus/main/docs/sec-quickstart.svg" alt="Quick Start" width="100%"></p>
 
+## Quick Start
 
-Dulus is a **lightweight Python reimplementation of Claude Code** that isn't locked to Claude. It ships the whole loop — REPL, tool dispatch, streaming, context compaction, checkpoints, sub-agents, voice, Telegram bridge, MCP, plugins — in roughly **12K lines you can actually read**. Fork it. Bend it. Run it offline against Qwen on your M2.
+### Option A — One-liner installer (recommended)
 
-> **v0.2.52 — May 12, 2026** — Session system overhaul: removed 50-session scan limit, metadata now includes message counts, eliminated daily prune from save path. **Recommendation:** wipe old sessions and start clean — only sessions, your memories stay intact.
-> **v0.2.22 — May 9, 2026** — `/bg start` spawns one detached Dulus daemon that serves CLI (IPC), Web (browser at `127.0.0.1:5000`), and Telegram simultaneously — all sharing the same session. WebChat now defaults to **loopback-only** (opt-in to LAN exposure with `/webchat lan on`).
-> **v0.2.21 — May 9, 2026** — Console-freeze fix: system prompt now tells the model SleepTimer is for user reminders only — pauses inside command pipelines must use `sleep N` inside the Bash command itself.
-> **v0.2.20 — May 9, 2026** — Windows IPC port-collision fix: switched to `SO_EXCLUSIVEADDRUSE` so a second Dulus instance correctly cedes the port and acts as client. End-to-end tested.
-> **v0.2.19 — May 9, 2026** — Shared sessions via tiny TCP socket on `127.0.0.1:5151`. `dulus "do X"` from any shell forwards into the running REPL/daemon — same history, memory, plugins. 80 lines of plain socket code instead of a daemon manager + IPC framework.
-> **v0.2.18 — May 9, 2026** — `beautifulsoup4` added as default dep for web scraping flows.
-> **v0.2.17 — May 9, 2026** — Mega-release: Composio plugin bundled (1000+ apps, no MCP), `/skill list` interactive picker (awesome / composio / local), awesome skills live from GitHub (no Claude Code needed), lite mode finally functional, system prompt rewritten in English, `VERSION` auto-syncs from pyproject.
-> **v0.2.16 — May 9, 2026** — MemPalace per-session dedup. No more re-injecting the same memory every turn — content-hash cache saves ~8K tokens in a 20-turn conversation. `/mem_palace reset` clears it on demand.
-> **v0.2.15 — May 9, 2026** — Banner image hosted locally so PyPI renders it correctly.
-> **v0.2.14 — May 9, 2026** — Multi-user Telegram bridge: `telegram_chat_ids: "123,456,,"` supported. Replies route to the user who sent each message.
-> **v0.2.13 — May 8, 2026** — Internal robustness fixes for Ollama streaming.
-> Type `/news` to see the full changelog.
+**Linux / macOS / WSL / Termux:**
 
----
+```bash
+curl -fsSL https://raw.githubusercontent.com/KevRojo/Dulus/main/install.sh | bash
+```
 
-<p align="center"><img src="https://raw.githubusercontent.com/KevRojo/Dulus/main/docs/sec-quickstart.svg" alt="Quick Start" width="100%"></p>
+**Windows (PowerShell):**
 
-## Quick Start
+```powershell
+irm https://raw.githubusercontent.com/KevRojo/Dulus/main/install.ps1 | iex
+```
 
-<img alt="image" src="https://github.com/user-attachments/assets/a5a447c6-2cce-42a5-87f8-7c3bc8367987" />
+The installer detects your OS, package manager, Python version, and WSLg
+audio bridge, then asks which profile you want:
 
+- **`full`** — everything: voice (Whisper + PortAudio), browser tools
+  (Playwright), MemPalace semantic memory, tmux, WSL audio bridge
+  (~1.5 GB).
+- **`standard`** — REPL + webchat + tmux daemon + Telegram bridge
+  (~300 MB).
+- **`basic`** — bare `pip install dulus` for servers / minimal sandboxes
+  (~150 MB).
+- **`custom`** — toggle each feature one by one.
 
-<img alt="image" src="https://github.com/user-attachments/assets/72526ae1-b69f-4529-adc7-eef1cd3876c8" />
+It installs only what's missing and never silently runs `sudo` — you
+choose between auto-install, "show me the command", or skip.
 
-<img alt="image" src="https://github.com/user-attachments/assets/eb11cb86-2f53-4979-b7bf-5bd1f97ed5fc" />
+Power-user flags:
 
-<img alt="image" src="https://github.com/user-attachments/assets/986ae7b5-5400-48aa-80eb-cdfd7dbb706e" />
+```bash
+# Preview without changing anything
+curl -fsSL .../install.sh | bash -s -- --dry-run
 
+# Non-interactive install (CI / scripts)
+curl -fsSL .../install.sh | bash -s -- --profile=full --pipx
 
-ROUND TABLE (DULUS UNIQUE FEATURE)
+# Latest pre-release
+curl -fsSL .../install.sh | bash -s -- --pre
+```
 
-<img alt="image" src="https://github.com/user-attachments/assets/9e8f17ed-6ca2-4ae0-b8c3-146ae5fef491" />
+```powershell
+# PowerShell equivalents
+irm .../install.ps1 | iex
+$env:DULUS_PROFILE='standard'; irm .../install.ps1 | iex   # preset via env
+.\install.ps1 -DryRun -Profile full                        # local run
+```
 
-Dulus is the first one meeting multiple models at the same time working for the same objective and sharing their ideas.
+### Option B — Docker (zero local Python setup)
 
+```bash
+# 1. Grab the compose file + env template
+curl -fsSLO https://raw.githubusercontent.com/KevRojo/Dulus/main/docker-compose.yml
+curl -fsSLO https://raw.githubusercontent.com/KevRojo/Dulus/main/.env.example
+mv .env.example .env   # then add your API keys
+
+# 2. Pull and run (WebChat at http://localhost:5050 — shifted off 5000
+#    so it doesn't collide with a native Dulus install on the same host)
+docker compose up -d
 
+# 3. Or jump into the REPL inside the container
+docker compose exec dulus dulus
+```
 
 ### One-liner
 
@@ -171,12 +245,7 @@ pip install "dulus[memory]" && dulus    # +MemPalace per-turn memory (pulls chro
 
 That's it. Dulus prompts you for a key on first run. The `[memory]` extra pulls in `mempalace` and its `chromadb` chain — skip it on Android/termux or anywhere wheels for `numpy`/`onnxruntime` aren't available; the CLI still boots and chats fine without it.
 
-Thanks for all the love on PyPi, the launch on PyPi was on 05-05-2026
------
-
-<img width="2593" height="1044" alt="image" src="https://github.com/user-attachments/assets/114b9ab1-e49f-490a-97b8-872f70b859bd" />
-
------
+---
 
 ### From source (hacking on Dulus itself)
 
@@ -224,8 +293,6 @@ echo "explain this diff" | git diff | dulus -p --accept-all
 
 ---
 
-<p align="center"><img src="https://raw.githubusercontent.com/KevRojo/Dulus/main/docs/terminal-boot.svg" alt="Dulus booting into session" width="100%"></p>
-
 <p align="center"><sub>↑ session boot. soul loaded, gold memory warm, shell sniffed. the little circles are real buttons on your Mac.</sub></p>
 
 ### 💻 Dulus OS (Sandbox)
@@ -234,12 +301,6 @@ echo "explain this diff" | git diff | dulus -p --accept-all
 
 <img width="1309" height="778" alt="image" src="https://github.com/user-attachments/assets/1c627990-7f87-489b-a0a2-14ad62fe2bb8" />
 
----
-<img width="1608" height="1903" alt="image" src="https://github.com/user-attachments/assets/450defa2-437b-470d-891a-9285d9e5e312" />
-
----
-<img width="3763" height="1975" alt="image" src="https://github.com/user-attachments/assets/10752aa2-6837-4097-a9a8-e02938992174" />
-
 ---
 The dulus sandbox is an early feature, expect bugs
 
@@ -327,31 +388,33 @@ dulus --model nvidia-web/deepseek-r1
 
 | Model | Type | ID |
 |---|---|---|
-| **DeepSeek R1** | Reasoning | `nvidia-web/deepseek-r1` |
-| **DeepSeek V3** | Instruct | `nvidia-web/deepseek-v3` |
-| **Kimi K2.5** | Long context | `nvidia-web/kimi-k2.5` |
-| **GLM-4** | Zhipu AI | `nvidia-web/glm-4` |
-| **MiniMax Text-01** | Text + Vision | `nvidia-web/minimax-text-01` |
-| **Mistral Nemotron** | NVIDIA-tuned | `nvidia-web/mistral-nemotron` |
-| **Mistral Large** | Instruct | `nvidia-web/mistral-large` |
-| **Llama 3.3 70B** | Meta | `nvidia-web/llama-3.3-70b` |
-| **Llama 3.1 405B** | Meta · flagship | `nvidia-web/llama-3.1-405b` |
-| **Llama Nemotron** | NVIDIA reasoning | `nvidia-web/llama-nemotron` |
-| **Qwen2.5 Coder** | Alibaba | `nvidia-web/qwen2.5-coder` |
-| **Qwen3 235B A22B** | MoE · Alibaba | `nvidia-web/qwen3-235b-a22b` |
-| **Phi-4** | Microsoft | `nvidia-web/phi-4` |
-| **Gemma 3 27B** | Google | `nvidia-web/gemma-3-27b` |
-
-**Automatic fallback.** Configure the chain in `~/.dulus/config.json`:
+| **DeepSeek V4 Flash** | Instruct | `nvidia-web/deepseek-ai/deepseek-v4-flash` |
+| **GLM-4.7** | Zhipu AI | `nvidia-web/z-ai/glm-4.7` |
+| **GLM-5.1** | Zhipu AI | `nvidia-web/z-ai/glm-5.1` |
+| **MiniMax M2.7** | Text + Vision | `nvidia-web/minimaxai/minimax-m2.7` |
+| **Kimi K2 Instruct** | Long context | `nvidia-web/moonshotai/kimi-k2-instruct` |
+| **Mistral Nemotron** | NVIDIA-tuned | `nvidia-web/mistralai/mistral-nemotron` |
+| **Seed OSS 36B** | ByteDance | `nvidia-web/bytedance/seed-oss-36b-instruct` |
+| **Solar 10.7B** | Upstage | `nvidia-web/upstage/solar-10.7b-instruct` |
+| **Step 3.5 Flash** | StepFun | `nvidia-web/stepfun-ai/step-3.5-flash` |
+| **Llama 3.3 70B** | Meta | `nvidia-web/meta/llama-3.3-70b-instruct` |
+| **Kimi K2.5** | Long context | `nvidia-web/moonshotai/kimi-k2.5` |
+| **DeepSeek R1** | Reasoning | `nvidia-web/deepseek-ai/deepseek-r1` |
+| **Llama Nemotron 70B** | NVIDIA reasoning | `nvidia-web/nvidia/llama-3.1-nemotron-70b-instruct` |
+| **Qwen2.5 72B** | Alibaba | `nvidia-web/qwen/qwen2.5-72b-instruct` |
+
+**Automatic fallback** — when a model hits its rate limit Dulus switches to the next one automatically. The default chain is built-in; override it in `~/.dulus/nvidia-providers.json`:
 
 ```json
 {
-  "nvidia_fallback_chain": [
-    "deepseek-r1",
-    "kimi-k2.5",
-    "llama-3.3-70b",
-    "mistral-nemotron",
-    "phi-4"
+  "fallback_models": [
+    "deepseek-ai/deepseek-v4-flash",
+    "moonshotai/kimi-k2-instruct",
+    "mistralai/mistral-nemotron",
+    "meta/llama-3.3-70b-instruct",
+    "deepseek-ai/deepseek-r1",
+    "nvidia/llama-3.1-nemotron-70b-instruct",
+    "qwen/qwen2.5-72b-instruct"
   ]
 }
 ```
@@ -378,23 +441,6 @@ Dulus's **Auto-Adapter** reads a random Python repo and figures out its tools on
 
 Adapt-and-install runs in under a second. New tools register **live**, no restart.
 
-Example adapting Sherlock repo:
-
-<img width="1765" height="166" alt="image" src="https://github.com/user-attachments/assets/c67dc15e-a2e3-4575-be34-8c9b54045510" />
-
------
-
-<img width="1327" height="751" alt="image" src="https://github.com/user-attachments/assets/676a0ef5-3699-4960-98a4-14a55fbef081" />
-
------
-
-<img width="885" height="301" alt="image" src="https://github.com/user-attachments/assets/52c02444-2606-41dc-bc33-ebe26ac41e5e" />
-
-----
-
-<img width="1006" height="271" alt="image" src="https://github.com/user-attachments/assets/d823428e-6344-4414-bf42-14ed3128f763" />
-
-
 ## MCP
 
 Drop a `.mcp.json` in your project root (or `~/.dulus/mcp.json` for user-wide):
@@ -460,6 +506,32 @@ pip install sounddevice faster-whisper numpy
 
 Then `/voice` in the REPL. Offline. Supports `/voice lang zh` and `/voice device` for mic selection.
 
+**Linux / WSL extra step:** `sounddevice` is a Python binding for the
+PortAudio C library, which isn't bundled with the wheel. If you see
+`PortAudio library not found` — install the system lib first:
+
+```bash
+sudo apt install libportaudio2 portaudio19-dev libasound2-dev
+pip install sounddevice --upgrade --force-reinstall
+```
+
+Note: `pip install portaudio` will always fail — there is no PyPI
+package by that name, only the apt one above.
+
+### Linux / WSL — tkinter for the GUI / webchat
+
+The desktop GUI (`dulus-gui`) needs **tkinter**, which is bundled with
+Python on Windows/macOS but ships as a separate apt package on Debian/
+Ubuntu/WSL. If you see `No module named 'tkinter'`:
+
+```bash
+sudo apt install python3-tk
+```
+
+Headless WSL/server users can skip this — `dulus[full]` works without
+tkinter for the REPL and webchat HTTP server thanks to lazy GUI imports
+(0.2.76+).
+
 ## Telegram bridge
 
 ```
@@ -660,6 +732,8 @@ dulus/
 └── tests/                # 263+ unit tests
 ```
 
+> **Interactive dependency graph & API docs:** [`docs/api.html`](docs/api.html) — open it in a browser to explore the full module graph (D3.js, zoom/pan, clusters by package).
+
 ---
 
 ## FAQ
@@ -689,6 +763,39 @@ git diff | dulus -p "write a commit message"
 
 ---
 
+## $DULUS — Token Utility
+
+The token isn't decoration. It's the fuel layer for everything Dulus is building.
+
+| Phase | Utility |
+|---|---|
+| **Now** | Community ownership. Creator-fee rewards locked on-chain to the builder. Alignment over extraction. |
+| **Business v1** | $DULUS holders get early access + discounted seats on the Dulus Business tier (multi-user workspaces, cloud-hosted instances, shared MemPalace). |
+| **Credits** | Pay for Dulus Business API credits with $DULUS — provider costs, inference minutes, premium model usage. |
+| **Deployments** | Spin up a cloud Dulus instance and pay the hosting with $DULUS. No fiat friction, no middleman. |
+| **Subscriptions** | Monthly Dulus Pro subscription payable in $DULUS. Hold enough → automatic fee discount tier. |
+| **Governance** | Top holders vote on feature priority and plugin marketplace policies. The flock decides. |
+
+> The open-source REPL stays free forever. $DULUS is the key to the business layer — not a gate on what already exists.
+
+**A message to the community —**
+
+I want to talk about the token. Honestly. No hype.
+
+I didn't launch it to get rich. The community launched it first, and when I saw early believers exposed without the actual builder behind it, I stepped in. I bought my position using the contract's own creator rewards. Zero personal capital deployed. I haven't sold a single token.
+
+The open-source project isn't going anywhere. The REPL, the tools, the free model tier — that stays free forever. But Dulus is growing into a business layer: cloud-hosted instances, multi-user workspaces, model credits, managed deployments. And that business layer is going to run on $DULUS.
+
+The token will be how you pay for Pro subscriptions. How you buy inference credits. How you spin up a cloud instance without fiat friction. Holders with enough weight get automatic tier discounts. And eventually — the flock votes: top holders decide feature priority and plugin marketplace policies.
+
+This isn't a promise. It's the architecture. That's how I've designed it.
+
+We keep flying. 🦅🇩🇴
+
+— KevRojo / [@KevRojo](https://x.com/KevRojo)
+
+---
+
 ## License
 
 GPLv3. Fork it, modify it, redistribute it — but keep it open. Derivative works must stay under GPLv3. Just don't ship `--accept-all` as the default.
@@ -701,6 +808,7 @@ If Dulus saved you tokens, time, or sanity — throw some sats:
 ```
 BTC: 1JzatQDn9fMLnKTd3KYgztsLHC95bJEzSN
 ```
+On x: @KevRojo
 
 <p align="center"><img src="https://raw.githubusercontent.com/KevRojo/Dulus/main/docs/divider.svg" alt="" width="100%"></p>