# OpenBMB/XAgent

An Autonomous LLM Agent for Complex Task Solving

Repository: https://github.com/OpenBMB/XAgent
Canonical: https://ross.abutalabs.com/products/xagent
Homepage: https://blog.x-agent.net/blog/xagent/
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-07-31T03:30:54+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 95, release rhythm 8, longevity 75
- inputs: {"age_days": 1052, "days_push": 33, "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 8544, forks 903 (observed 2026-08-28T04:10:23.441666+00:00)

## What it is
XAgent is an open-source, LLM-driven autonomous agent framework for automatically solving complex tasks. It features a dispatcher and planner architecture, extensible tools and agents, sandboxed Docker execution, and both GUI and CLI interfaces with human collaboration support.

## Use cases
- automatically solve complex multi-step tasks with an LLM agent
- build and extend autonomous agents with custom tools
- run AI agent tasks safely inside a docker sandbox
- collaborate with an AI agent that can ask for human help
- decompose a task into subtasks and execute them automatically
- interact with an autonomous agent via a web GUI or command line

## When to choose
- you want a general-purpose autonomous LLM agent that plans and executes tasks with minimal human input
- you need extensible agent architecture where you can add new tools and agents
- safety matters and you want agent actions constrained in docker containers
- you want both a GUI and CLI for interacting with agents

## When to avoid
- you need a lightweight single-purpose agent library with minimal dependencies
- you require a production-hardened, stable agent platform rather than an early-stage experimental project
- you cannot run docker containers in your environment
- you need fine-grained deterministic control over every agent step

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, workflow-automation, cli, gui
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cross-platform, self-hosted
- tags: autonomous-agent, llm-agent, task-solving, tool-use, human-in-the-loop, docker-sandbox, ai-agents, automation, docker

## Member repositories
- OpenBMB/XAgent (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:23.441666+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 2026-08-29T17:26:19.600393+00:00, confidence not recorded.
  - readme: https://github.com/OpenBMB/XAgent (fetched 2026-08-28T04:10:23.441666+00:00, sha be9ee31098c1)
- Data as of 2026-08-30T08:39:29.467469+00:00.