Chat with your 10-years-younger self.
Import your WhatsApp, Facebook, Instagram, Gmail, iMessage, Telegram, Twitter, or Discord history. A local AI learns your voice and lets you text past-you. No cloud. No API. Everything runs on your machine.
Export your chat history from any platform. Drop the files into Pratibmb. Messages are parsed and stored in a local SQLite database on your machine.
A local embedding model (84MB) creates semantic representations of your messages. This happens on your CPU/GPU. No text leaves your device.
A local LLM (2.3GB) analyzes your conversations to extract relationships, life events, interests, and communication style. All on-device.
Pick a year and start texting. Past-you responds in your voice, grounded in your real memories. Optional LoRA fine-tuning makes it even more authentic.
Export your history from any of these. Pratibmb auto-detects the format.
Export Chat as .txt
Download Your Information (JSON)
Download Your Information (JSON)
Google Takeout (MBOX)
macOS chat.db (SQLite)
Desktop Export (JSON)
Download Archive (.js)
DiscordChatExporter (JSON)
Free. Open source. Runs offline after first model download (~2.5GB one-time).
M1/M2/M3/M4 Macs. Native Metal acceleration for fine-tuning via MLX.
.dmg (arm64)Requires Python 3.10+ and ~4GB RAM. Models are downloaded on first launch. Setup guide
Optional LoRA training teaches the model your texting style. Here's what each platform uses:
| Platform | Training Backend | GPU Required? | Time (~1500 pairs) | Install |
|---|---|---|---|---|
| macOS (Apple Silicon) | MLX-LM | No (uses Metal) | ~20 min | pip install mlx-lm |
| Windows (NVIDIA GPU) | PyTorch + PEFT + QLoRA | Yes (6GB+ VRAM) | ~30 min | pip install "pratibmb[finetune-pytorch]" |
| Linux (NVIDIA GPU) | PyTorch + PEFT + QLoRA | Yes (6GB+ VRAM) | ~30 min | pip install "pratibmb[finetune-pytorch]" |
| Linux (CPU-only) | PyTorch (no quantization) | No | ~2 hours | pip install "pratibmb[finetune-pytorch]" |
Fine-tuning is optional. The base model works well out of the box with profile extraction and RAG. Fine-tuning adds your specific texting style (abbreviations, language mix, emoji patterns).
Not just a policy. The code enforces it.
Every computation runs on your hardware. Messages, embeddings, models, and profiles never leave your machine.
No OpenAI API, no cloud inference, no remote servers. Works with Wi-Fi off after the initial model download.
Zero analytics, no crash reports, no usage tracking, no phone-home. Check the source code yourself.
AGPLv3 licensed. Every line is auditable. Don't trust us — verify. Community contributions welcome.
Pratibmb is free software under the AGPLv3 license. The source code is on GitHub.
Your most intimate data — a decade of private messages — is the one dataset you should never upload to somebody else's API. That's why Pratibmb exists.