Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Every webrain environment variable — engine paths, browser cache and profile roots, encrypted vault, credentials, STT/vision keys, and local AI (whisper + Qwen3-VL-2B).
| Variable | Description | Default |
|---|---|---|
CDP_URL | CDP endpoint to attach to | http://127.0.0.1:9222 |
WEBRAIN_CHROME | Explicit Chrome binary path | auto-discovered |
WEBRAIN_BROWSERS_DIR | Engine cache dir (Chrome for Testing, Obscura) | %LOCALAPPDATA%\webrain\browsers / ~/.cache/webrain/browsers |
WEBRAIN_LIGHTPANDA / WEBRAIN_OBSCURA | Explicit lightpanda/obscura binary paths | auto-discovered |
WEBRAIN_PROFILES_DIR | Per-account browser profile root | %APPDATA%\webrain\profiles / ~/.config/webrain/profiles |
WEBRAIN_VAULT_DIR | Encrypted credential vault dir | %APPDATA%\webrain / ~/.config/webrain |
WEBRAIN_USER / WEBRAIN_PASS | Login fallback credentials (env channel) | — |
GROQ_API_KEY / OPENAI_API_KEY / FIREWORKS_API_KEY / OPENROUTER_API_KEY | Cloud STT (transcript) keys; all four also power the vision ask chain (OpenRouter → OpenAI → Fireworks → Groq → bundled local Qwen3-VL-2B) | — |
SERPAPI_API_KEY | serpapi.com paid Google SERP provider — used by webrain_serp when limit > 10 | — |
WEBRAIN_2CAPTCHA_KEY | 2captcha API key for Google /sorry-wall reCAPTCHA solving (webrain_serp google/brave flows) | — |
WEBRAIN_NO_STEALTH | Set 1 to skip the injected stealth JS + UA override (e.g. the webrain serp google flow) | off |
WEBRAIN_STEALTH_NOISE | Set 0 to disable the canvas/audio fingerprint-noise injection (sites that distrust the spoofed profile) | on |
WEBRAIN_STT_MODEL | Cloud STT model override (e.g. whisper-large-v3) | provider default |
WEBRAIN_WHISPER_BIN / WEBRAIN_WHISPER_MODEL | Local whisper-cli binary / GGUF model paths | bundled cache |
EMBED_URL / EMBED_MODEL / EMBED_API_KEY | OpenAI-compatible /v1/embeddings endpoint + model + Bearer token for webrain_vision op=index / retrieve (any compatible server: OpenAI, Ollama, TEI, local vLLM) | api.openai.com/v1/embeddings + text-embedding-3-small |
RUST_LOG | Log verbosity (webrain=info,tungstenite=warn) | as above |
webrain_watch transcribes locally via bundled whisper-cli + a GGUF model, and
vision:true describes frames via a vision LLM — local Qwen3-VL-2B (bundled
llama-server, webrain install vision) when no cloud key is set.
| Install | What it bundles |
|---|---|
webrain install watch | ffmpeg+ffprobe, yt-dlp, whisper-cli + a GGUF model |
webrain install whisper | a whisper GGUF model (--model small.en) |
webrain install vision | llama-server (latest CPU build) + Qwen3-VL-2B (GGUF + mmproj) |
~/.lightpanda, ~/.obscura, ~/.local/bin → the webrain engine cache.