# EvoScientist/EvoScientist

🔬 Harness Vibe Research with Self-evolving AI Scientists

Repository: https://github.com/EvoScientist/EvoScientist
Canonical: https://ross.abutalabs.com/products/evoscientist
Homepage: https://EvoScientist.ai/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai-agent, ai4science, multi-agent-system, vibe-research
Last push: 2026-08-25T11:10:54+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 98, longevity 15
- inputs: {"age_days": 219, "days_push": 8, "days_rel": 12, "gap_med": 5.0, "n_releases_24m": 29}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4501, forks 305 (observed 2026-08-28T04:08:51.521108+00:00)

## What it is
EvoScientist is a Python-based multi-agent framework for building self-evolving AI scientists that plan, research, code, analyze data, and write end-to-end scientific workflows. It includes persistent research memory (EvoMemory), dynamic agent orchestration, and a set of skills spanning ideation to publication.

## Use cases
- run end-to-end autonomous scientific research with AI agents
- automate deep research reports on a topic
- have an AI agent analyze code and datasets for a study
- build a multi-agent system that improves across research runs
- automate literature review and paper writing
- benchmark AI research agents on deep research tasks

## When to choose
- you want an autonomous multi-agent system for scientific discovery or deep research
- you need persistent memory across research runs
- you want a Python tool installable via pip/uv with Apache-2.0 licensing

## When to avoid
- you need a simple single-agent chatbot
- you require production guarantees for mission-critical pipelines
- you cannot run Python 3.11+ or lack access to capable LLM backends

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, machine-learning, llm-inference, data-science, workflow-automation
- domain: artificial-intelligence, large-language-models, data-science
- platform: python, cli, cross-platform
- tags: ai-scientist, multi-agent-system, self-evolving, ai4science, vibe-research, deep-research, scientific-discovery, evomemory, knowledge-graph, ai-agents, research-automation

## Member repositories
- EvoScientist/EvoScientist (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:51.521108+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 2026-08-29T18:20:24.724996+00:00, confidence not recorded.
  - readme: https://github.com/EvoScientist/EvoScientist (fetched 2026-08-28T04:08:51.521108+00:00, sha 7d756a83aba1)
  - homepage: https://EvoScientist.ai/ (fetched 2026-08-29T09:06:28.204989+00:00, sha cbe3413f2aae)
  - registry_pypi: https://pypi.org/pypi/evoscientist/json (fetched 2026-08-29T09:06:28.216056+00:00, sha 1e7ab6f91590)
- Data as of 2026-08-30T08:39:29.467469+00:00.