# hexdocom/lemonai

Lemon AI is the first Full-stack Open-source Self-Evolving General AI Agent, offering a fully local alternative to Agentic platforms like Manus & Genspark AI.🔔 Official updates   X(twitter) @LemonAI_cc

Repository: https://github.com/hexdocom/lemonai
Canonical: https://ross.abutalabs.com/products/lemonai
Homepage: https://lemonai.cc
Language: JavaScript
License: NOASSERTION
License Family: other
Topics: agent, agentic-ai, ai, fullstack, javascript, llm, nodejs, vue3, desktop, genspark, manus
Last push: 2026-02-03T10:39:31+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 65, release rhythm 57, longevity 33
- inputs: {"age_days": 463, "days_push": 211, "days_rel": 289, "gap_med": 7.0, "n_releases_24m": 9}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1559, forks 314 (observed 2026-08-28T04:05:03.605927+00:00)

## What it is
Lemon AI is a full-stack open-source general AI agent platform that runs locally, offering an alternative to Manus and Genspark AI. It combines planning, action, reflection, and memory loops with a Docker-based VM sandbox for code execution, supporting local LLMs via Ollama/VLLM as well as cloud model APIs.

## Use cases
- run a local AI agent for deep research reports
- self-hosted alternative to Manus or Genspark AI
- generate and execute code in a sandboxed VM
- analyze data and create documents with an AI agent
- build a self-evolving agent with personal memory
- browse the web and automate tasks with a local LLM
- create web apps and HTML content via an AI agent

## When to choose
- you want a fully local, privacy-focused agentic platform with zero cloud dependency
- you need a code interpreter sandbox for safe agent-driven execution
- you want to run local LLMs like DeepSeek, Qwen, or Llama via Ollama or VLLM
- you need deep research, data analysis, and content generation in one tool

## When to avoid
- you need a lightweight library to embed agent capabilities in your own app
- you require a fully permissive open-source license (license is non-standard)
- you lack the local hardware or Docker setup to run VM sandboxes and local models
- you need a battle-tested enterprise-grade agent framework

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, rag, chatbot, web-scraping
- domain: artificial-intelligence, large-language-models, self-hosted, developer-tools
- platform: self-hosted, cross-platform
- tags: general-ai-agent, local-llm, ollama, vm-sandbox, self-evolving, code-interpreter, deep-research, manus-alternative, vue3, privacy, ai-agents, retrieval-augmented-generation, docker, nodejs, desktop

## Member repositories
- hexdocom/lemonai (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:03.605927+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 2026-08-30T04:29:50.459504+00:00, confidence not recorded.
  - readme: https://github.com/hexdocom/lemonai (fetched 2026-08-28T04:05:03.605927+00:00, sha b48d5ba6dbf6)
  - homepage: https://lemonai.cc (fetched 2026-08-29T11:29:52.043198+00:00, sha bae5c85f3726)
- Data as of 2026-08-30T08:39:29.467469+00:00.