forked from CameronJGrant/telegram-scam-baiter
#telegram-scam-baiter
Telethon + OpenAI bot that engages unsolicited DMs with safe, time-wasting small talk. It uses a focused system prompt, keeps recent chat history, and replies with human-like delays to keep scammers busy while revealing nothing useful.
What it does
- Listens for messages from a single target (by username or numeric user ID), or auto-targets the first inbound DM.
- Maintains a rolling history and crafts short, question-ending replies to keep the other person typing.
Environment variables
| Variable | Required | Default | Description |
|---|---|---|---|
| TG_API_ID | yes | — | Telegram API ID from https://my.telegram.org |
| TG_API_HASH | yes | — | Telegram API hash from https://my.telegram.org |
| TG_SESSION | no | telethon_session | Session file prefix used by Telethon |
| TARGET_USERNAME | no | — | Target's public username (without @). Leave empty if using TARGET_USER_ID |
| TARGET_USER_ID | no | 0 | Target's numeric Telegram user ID (use if no username) |
| TARGET_DISPLAY_NAME | no | — | Person’s display name (case-insensitive; exact or partial match across dialogs) |
| TARGET_CACHE_FILE | no | target_id.txt | Path to store resolved numeric ID for future runs |
| OPENAI_API_KEY | yes | — | OpenAI API key |
| OPENAI_MODEL | no | gpt-4o-mini | Chat-capable model used for replies |
| MIN_DELAY_SEC | no | 25 | Minimum delay (seconds) before each reply |
| MAX_DELAY_SEC | no | 75 | Maximum delay (seconds) before each reply |
| HISTORY_FILE | no | chat_history.jsonl | Path to local JSONL file for conversation history |
| MAX_TOKENS_HISTORY | no | 2200 | Rough token budget for messages passed to the model |
| MAX_MESSAGES_HISTORY | no | 30 | Hard cap on number of messages kept in rolling history |
| AUTO_OPENER_ENABLED | no | false | If true, send an initial opener only on fresh start when a target is resolved and no catch-up reply was needed |
| OPENER_TEXT | no | — | The opener text to send when AUTO_OPENER_ENABLED=true |
| TYPING_SIM_ENABLED | no | true | Show a "typing…" indicator before sending the message |
| TYPING_WPM | no | 22 | Approximate words per minute to estimate typing duration |
| TYPING_MIN_SEC | no | 2.0 | Minimum typing duration (seconds) |
| TYPING_MAX_SEC | no | 18.0 | Maximum typing duration (seconds) |
| PYTHONUNBUFFERED | no | 1 | If set, forces unbuffered output in some environments |
Notes:
- Set one of TARGET_USERNAME, TARGET_USER_ID, or TARGET_DISPLAY_NAME. If none are set, the first inbound DM will become the target automatically.
- The opener is disabled by default to avoid sending context-specific messages; enable explicitly with AUTO_OPENER_ENABLED and provide OPENER_TEXT.
- Increase delays if you hit Telegram flood limits.
License
MIT License — see LICENSE file for details.