# zhayujie/bot-on-anything

A large model-based chatbot builder that can quickly integrate AI models (including ChatGPT, Claude, Gemini) into various software applications (such as Telegram, Gmail, Slack, and websites).

Repository: https://github.com/zhayujie/bot-on-anything
Canonical: https://ross.abutalabs.com/products/bot-on-anything
Homepage: https://cowagent.ai
Language: Python
License: MIT
License Family: permissive
Topics: chatgpt, gmail, telegram, slack, web, claude, gemini
Last push: 2026-07-05T13:17:22+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 91, release rhythm 8, longevity 92
- inputs: {"age_days": 1301, "days_push": 59, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4216, forks 912 (observed 2026-08-28T04:08:39.206171+00:00)

## What it is
Bot on Anything is a lightweight Python framework for building AI chatbots that connect large language models (ChatGPT, Claude, Gemini, ERNIE Bot, etc.) to messaging channels like Telegram, Slack, Discord, Gmail, WeChat, and web. Models and channels are decoupled via a single config file, so any model can run on any channel and both can be swapped independently.

## Use cases
- connect chatgpt to telegram
- build a slack ai chatbot
- add an llm bot to discord
- hook up claude or gemini to gmail
- deploy a chatbot on wechat official account
- run one llm across multiple chat channels
- quickly spin up an ai bot from a config file

## When to choose
- you want a lightweight, config-driven way to wire one LLM to one or more chat channels
- you need to support overseas channels like Telegram, Slack, Discord, or Gmail
- you want to swap models or channels without code changes
- you prefer a pure-Python deploy with minimal dependencies

## When to avoid
- you need a full agent with task planning, long-term memory, skills, or MCP support
- you need a hosted or managed chatbot service
- you want deep customization of a single channel beyond what the framework's channel adapters offer
- you require Python versions outside the recommended 3.7–3.10 range

## Facets
- artifact type: framework
- maturity: active
- function: chatbot, agent-framework, llm-inference, plugin-system, webhook
- domain: chatbots, large-language-models, messaging-platforms, developer-tools
- platform: python, windows, cross-platform, self-hosted
- tags: chatgpt, claude, gemini, multi-channel, slack, gmail, wechat, config-driven, llm-integration, ai-agents, linux, macos, telegram, discord

## Member repositories
- zhayujie/bot-on-anything (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:39.206171+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:22:26.451213+00:00, confidence not recorded.
  - readme: https://github.com/zhayujie/bot-on-anything (fetched 2026-08-28T04:08:39.206171+00:00, sha 0f86bf5d8761)
  - homepage: https://cowagent.ai (fetched 2026-08-29T09:12:36.506511+00:00, sha 38576bd88aae)
  - site_page: https://docs.cowagent.ai (fetched 2026-08-29T09:12:36.508976+00:00, sha 2623220cfa0d)
  - site_page: https://docs.cowagent.ai/skills/index (fetched 2026-08-29T09:12:36.510730+00:00, sha bb3abf717e73)
- Data as of 2026-08-30T08:39:29.467469+00:00.