# ANative-Lab/EvoAgentX

🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents

Repository: https://github.com/ANative-Lab/EvoAgentX
Canonical: https://ross.abutalabs.com/products/evoagentx
Homepage: https://evoagentx.github.io/EvoAgentX/
Language: Python
License: NOASSERTION
License Family: other
Topics: agent, ai, ai-agents, llms, multi-agent-systems, natural-language-processing, self-evolving, memory, rag, tool, tools
Last push: 2026-08-14T02:38:40+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 97, release rhythm 90, longevity 36
- inputs: {"age_days": 505, "days_push": 20, "days_rel": 66, "gap_med": 1.0, "n_releases_24m": 5}
- 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 3261, forks 296 (observed 2026-08-28T04:07:52.636015+00:00)

## What it is
EvoAgentX is an open-source Python framework for building, evaluating, and automatically evolving LLM-based agents and agentic workflows. It provides workflow auto-construction from a single prompt, built-in evaluation, and a self-evolution engine that iteratively improves agents through feedback loops.

## Use cases
- build multi-agent workflows from a single prompt
- automatically evaluate LLM agent performance on tasks
- evolve and optimize agentic workflows over time
- integrate OpenAI or Qwen models into agent pipelines
- build RAG-enabled agents with memory and tools
- research self-evolving AI agent ecosystems

## When to choose
- you want automated construction and optimization of multi-agent workflows rather than manual prompt chaining
- you need built-in evaluation and iterative self-improvement of LLM agents
- you are researching self-evolving agent systems in Python

## When to avoid
- you need a simple single-prompt chatbot without workflow orchestration
- you require a framework with a long track record in large-scale production deployments
- you need a non-Python or low-level agent runtime

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, rag, machine-learning, workflow-automation
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cross-platform
- tags: self-evolving-agents, multi-agent-systems, agentic-workflows, llm-orchestration, agent-evaluation, ai-agents, retrieval-augmented-generation

## Member repositories
- ANative-Lab/EvoAgentX (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:52.636015+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 2026-08-29T18:43:52.030720+00:00, confidence not recorded.
  - readme: https://github.com/ANative-Lab/EvoAgentX (fetched 2026-08-28T04:07:52.636015+00:00, sha 559d7029edec)
- Data as of 2026-08-30T08:39:29.467469+00:00.