Awesome AI Agents › Virtual Assistants

arlanrakh/talk-to-girlfriend-ai

⭐ 552 Python repository created 2025-12-28

This project is a conversational assistant for Telegram that helps a user write messages in a personal chat. It has three parts. A FastAPI bridge written in Python wraps the Telegram client API and exposes messaging operations over a local HTTP port, authenticated with a session string the user generates from their own Telegram API credentials. A TypeScript command line agent runs on Bun, calls Claude Sonnet through the Vercel AI Gateway, and drives the bridge through more than twenty tools covering reading chats and message history, sending, replying, editing, deleting and forwarding messages, adding reactions, searching a conversation and checking whether a contact is online. A retrieval layer built on the hosted Nia semantic search service indexes a collection of over 500 curated opening lines together with guides on conversation technique, so the agent can look up a relevant line or a tip instead of generating one blind; users can index their own material by creating a source in that service. The agent is operated from a terminal in natural language, with slash commands for help, clearing history, connection status and exit, and typical prompts ask it to summarise recent messages, draft a reply to a specific message, or rewrite a draft in a different tone. The same Telegram component can be used on its own as a standalone MCP server registered with Claude Desktop or Cursor, exposing around sixty Telegram tools for messaging, contacts, groups, channels and reactions, which makes the repository useful as a worked example of wiring a chat platform into an agent. It is a small personal project rather than a maintained product, and the author notes the relationship it was written for ended.

https://github.com/arlanrakh/talk-to-girlfriend-ai

ai-agentstelegrammcpmcp-serverconversational-agentsemantic-searchclaudetypescriptpython

Also in Virtual Assistants

mem0ai/mem0

Mem0 is an open-source memory layer that enhances AI agents and assistants with personalized, adaptive memory capabilities for improved context-aware interactions across various applications.

CherryHQ/cherry-studio

Cherry Studio is a cross-platform desktop client that supports multiple large language model providers, offering extensive AI assistant features, document processing, and practical productivity tools in an open-source environment.

tinyhumansai/openhuman

Local-first personal AI harness combining a persistent memory brain, multi-agent orchestration, and autonomous web and data research.

khoj-ai/khoj

Khoj is a self-hostable personal AI platform that transforms any local or online large language model into a customizable, autonomous AI assistant for research, automation, and document retrieval.

xming521/WeClone

Open-source pipeline that fine-tunes an LLM on a person's chat history to create a personal digital avatar, deployable as a Telegram bot.

wangzan101/Mika

Android AI assistant that operates phone apps and the web on a hidden background screen from a single spoken or typed instruction, while you keep using your phone normally.

gptme/gptme

gptme is a versatile personal AI assistant that operates in your terminal, equipped with tools for coding, file editing, web browsing, and vision, providing a powerful local alternative to popular AI agents for diverse knowledge work.

CherryHQ/cherry-studio-app

Cherry Studio App is the official mobile application that enables powerful AI Large Language Models interaction on iOS and Android devices, supporting multiple LLM providers and offering tools for conversation management and data migration.