LyubomirT / intense-rp-next

IntenseRP Next v2 It's a local OpenAI-compatible API + desktop app that drives various web LLM chat UI (via Playwright), so you can use it from SillyTavern and other clients without paying for the official API. Slightly cursed yet surprisingly effective. What is this? · Quick start · Client setup · Documentation · Releases · Issues · Discord Server · 🎬 Preview Video 🎬 https://github.com/user-attachments/assets/ebf1bfcd-3b23-4614-b584-174791bcb004 Welcome 👋 If you're here because you want to use an LLM in SillyTavern without wiring up the paid official API: Welcome to the club! IntenseRP Next v2 drives the official web apps (like DeepSeek, Z.AI, Moonshot, QwenLM) in a real browser, and re-exposes them as an OpenAI-compatible endpoint. Unlike the official API, this is usually free (DeepSeek / GLM / Kimi are free to use with limits, and paid plans aren't added yet) and it gives you access to the full web UI experience (including reasoning toggles, search, file uploads, and more). Not without tradeoffs, of course - see below. Start here! 🎁 • Download a release (see Releases) and run it (or run from source) • Click **Start** and log in when the browser opens • Point your SillyTavern client at (default) and pick / / / mode IDs And it's done! It should Just Work™️. What is this? IntenseRP Next v2 (sometimes shortened to "IRP Next v2") is a local bridge between: • an OpenAI-style client (like SillyTavern), and • a provider web app (currently: DeepSeek, GLM Chat, Moonshot, QwenLM) Under the hood it: • Starts a local FastAPI server (OpenAI-compatible routes under ) • Launches a real Chromium session (Patchright/Playwright) • Logs in (manual or auto-login) • Intercepts the provider's streaming network responses • Re-emits them as OpenAI-style SSE deltas for your client In normal human terms: free acces to LLMs via their official web apps but turned into an API you can use in SillyTavern and other OpenAI-compatible clients. Of course, there are also official paid APIs, but not everyone can pay for them, so this is kind of a free alternative. 🙂 Should you use it? 🎯 If you read this far, you probably have a use case in mind! But here's the objective truth: It would work well for you if you: • want free-ish access to provider web models via the official web apps • prefer a clicky desktop app over a pile of scripts • are OK with the occasional wait or hiccup (web apps change) Not the best fit if you: • need high throughput / parallel requests (this uses one live browser session) • want to run headless on a server • want something that never breaks (that's perhaps the biggest caveat) > [!NOTE] > 1. Provider web apps change. When they do, a driver can break until it's updated. > 2. IntenseRP currently processes **one request at a time** (requests are queued). This is on purpose (single live browser session). > 3. This project is not affiliated with DeepSeek, ZhipuAI, SillyTavern, or any provider. Why v2? v2 is a full rewrite based on lessons learned from the original **IntenseRP API** (by Omega-Slender) and my own **IntenseRP Next v1**. The focus is less on a pile of features and more on making it sane to maintain and hard to break. It's a more modular codebase with a Playwright-first approach (network interception, no scraping), a better UI (PySide6), and a cleaner settings model, plus built-in update and migration flows. If you want to compare, have a look: | Area | IntenseRP API / Next v1 | IntenseRP Next v2 | |---|---|---| | Backend | Python (Flask) | Python (FastAPI) | | UI | customtkinter | PySide6 (Qt) | | Automation | Selenium-based | Playwright (Patchright) | | Scraping | HTML parsing (plus workarounds for NI) | Native Network interception | Quick start > [!TIP] > First launch can take a bit - v2 will verify/download its browser components. Windows (recommended) • Download the latest from Releases • Extract it anywhere • Open the folder and run • Click **Start** and wait for the browser to open Linux • Download the latest from Releases • Extract and run: If it complains about missing libraries, you may need Qt6 deps installed on your system. The best way is to install the package via your package manager, but if it doesn't stop you can just install the missing libs manually. From source (for devs) Requirements: Python 3.12+ (3.13 recommended) Connect SillyTavern (or any OpenAI-compatible client) Once the app says **Running (Port 7777)**: | Setting | Value | |---|---| | Endpoint | | | API | OpenAI-compatible chat completions | | API key | Leave blank (unless you enabled API keys) | | Model | / / | Available model IDs (depends on provider): • DeepSeek: • (uses your IntenseRP settings) • (forces DeepThink off) • (forces DeepThink on, Send DeepThink follows your setting) • GLM Chat: • (uses your IntenseRP settings) • (forces Deep Think off) • (forces Deep Think on, Send Deep Think follows your setting) • Moonshot: • (uses your IntenseRP settings) • (forces Thinking off, Send Thinking off) • (forces Thinking on, Send Thinking follows your setting) Note: these IDs are behavior presets (modes). GLM has separate real model selection in Settings. Moonshot IDs are still behavior presets, not a separate backend model selector. If you change the port in Settings, update the endpoint to match (example: ). Quick troubleshooting 🧯 • **Browser takes forever on first run**: it may be downloading/verifying Chromium. Let it cook, then try again. • **Client cannot connect**: confirm the app says **Running**, and the endpoint matches your port ( by default). • **401 Unauthorized**: you probably enabled API keys in Settings. Either disable them or add a key in your client. • **Login loops / stuck sign-in**: try disabling Persistent Sessions, or clear the profile in Settings (it wipes saved cookies). • **Slow responses**: requests are queued (one at a time), and DeepThink can add extra time. Tip: enable the console and/or logfiles before reporting issues. Logs…