Zero is a self-hosted, alpha-stage Telegram AI companion with a user-session listener, management bot, local web panel, terminal UI, SQLite memory, provider routing, web search, and optional Office document generation.

Stars

6

7-day growth

No data

Forks

1

Open issues

0

License

Apache-2.0

Last updated

2026-07-27

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It combines a Telegram user-session AI, owner-only management bot, local admin panel, and curses TUI in a single alpha project, with careful feature status marking and a security-focused design.

Who it is for

  • Telegram power users wanting a self-hosted AI companion
  • Self-hosters and homelab enthusiasts
  • Developers exploring modular Telegram bot architectures
  • Security-conscious users who want local control

Use cases

  • Personal AI assistant in allowed Telegram groups via user session
  • Owner-only management and monitoring via Telegram bot and web panel
  • Local administration and diagnostics through terminal TUI
  • Optional Office document creation (DOCX, XLSX, PPTX) via Telegram commands

Strengths

  • Modular architecture with separate listener, panel, TUI, and provider routing
  • Rich local administration: web panel, curses TUI, and health checks
  • Flexible provider routing with key pools, cooldowns, quotas, and fallback
  • Memory system with V3 service and migration tooling from older versions

Considerations

  • Alpha status: no live Telegram or paid-provider E2E verification
  • Separate legacy YAML and canonical JSON configuration layers
  • Docker Compose not turnkey; requires manual provisioning of legacy YAML path
  • Conflicting licensing files; not officially open source

README quick start

Installation

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482