# openakita/openakita

An open-source AI assistant framework with skills and agent architecture

Repository: https://github.com/openakita/openakita
Canonical: https://ross.abutalabs.com/products/openakita
Homepage: http://openakita.ai
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: agent, ai, assistant, automation, clawd, clawdbot, openclaw, python, claw
Last push: 2026-08-14T02:58:23+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 97, release rhythm 85, longevity 15
- inputs: {"age_days": 215, "days_push": 19, "days_rel": 21, "gap_med": 0, "n_releases_24m": 68}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1973, forks 274 (observed 2026-08-28T04:06:01.103823+00:00)

## What it is
OpenAkita is an open-source multi-agent AI assistant framework in Python that orchestrates multiple cooperating agents with skills, plugins, long-term memory, and 89+ tools. It ships as a GUI desktop app (Tauri + React) and connects to IM channels like Telegram, Feishu, WeCom, DingTalk, and QQ, supporting 30+ LLM providers.

## Use cases
- run a personal AI assistant that executes tasks autonomously
- build a multi-agent AI team that automates workflows
- connect an AI assistant to Telegram or DingTalk
- schedule and automate recurring tasks with AI agents
- extend an AI assistant with custom skills and plugins
- self-host an AI assistant with sandboxed tool execution

## When to choose
- you want a ready-to-use, GUI-configured AI assistant rather than a bare agent library
- you need IM channel integration (Telegram, Feishu, WeCom, DingTalk, QQ) out of the box
- you want multi-agent orchestration with plugins, memory, and scheduled tasks in one package

## When to avoid
- you need a minimal, embeddable agent library to build into your own app
- AGPL-3.0 licensing is incompatible with your product
- you require a lightweight CLI-only or headless agent runtime

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, chatbot, llm-inference, plugin-system, workflow-automation, scheduling, chat-interface
- domain: artificial-intelligence, large-language-models, chatbots, developer-tools
- platform: python, cross-platform, windows
- tags: multi-agent, im-integration, self-evolving, skills, sandbox-security, desktop-app, tauri, agpl, ai-agents, automation, desktop, macos, linux, telegram, web-server

## Member repositories
- openakita/openakita (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:01.103823+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 2026-08-30T03:04:59.294970+00:00, confidence not recorded.
  - readme: https://github.com/openakita/openakita (fetched 2026-08-28T04:06:01.103823+00:00, sha 50c3f6b8571f)
  - homepage: http://openakita.ai (fetched 2026-08-29T10:44:17.246762+00:00, sha 0bdff1968d53)
  - site_page: https://openakita.ai/about (fetched 2026-08-29T10:44:17.249178+00:00, sha 8aef515d6c31)
- Data as of 2026-08-30T08:39:29.467469+00:00.