EvoScientist 0.0.1b2

EvoScientist: Towards Self-Evolving AI Scientists for End-to-End Scientific Discovery

---

English | 简体中文

EvoScientist aims to harness vibe research by enabling self-evolving AI scientists that autonomously explore, generate insights, and iteratively improve. It is designed to be opinionated and ready to use out of the box, offering a living research system that grows alongside evolving agent skills, toolsets, and memory bases. Going beyond traditional human-in-the-loop systems, EvoScientist introduces an AI-in-human’s-loop paradigm, where AI acts as a research buddy that co-evolves with human researchers and internalises scholarly taste and scientific judgement.

✨ Features

• 🤖 Multi-Agent Team — 6 sub-agents (plan, research, code, debug, analyze, write) working in concert.
• 🧠 Persistent Memory — Context, preferences, and findings survive across sessions.
• 🔬 Scientific Workflow — Intake → plan → execute → evaluate → write → verify.
• 🌐 Multi-Provider — Anthropic, OpenAI, Google, NVIDIA — one config to switch.
• 📱 Multi-Channel — CLI as the hub; Telegram, Discord, Slack, Feishu, WeChat, and more — one agent session.
• 🔌 MCP & Skills — Plug in MCP servers or install skills from GitHub on the fly.

🎯 ᯓ➤ Roadmap

• 🖥️ TUI powered by Rich and Textual
• 📻 EvoMemory v1.0 shipped
• ⚒️ 200+ predefined skills built in
• 📑 Technical report on the way
• 📺 Demo and tutorial in the works
• 📊 Benchmark suite to be released
• ⏰ Scheduled tasks for the core system planned
• 🧩 More built-in skills and integrations ahead

🔥 News

• [27 Feb 2026] ⛳ EvoScientist officially debuts!

📖 Table of Contents

• 📦 Installation
• 🔑 Configuration
• ⚡ Quick Start
• 🔌 MCP Integration
• 📱 Channels
• 📚 Acknowledgments
• 🌍 Project Roles
• 🤝 Contributing

📦 Installation

[!TIP] Requires Python 3.11+. We recommend uv or conda for dependency management and virtual environments.

🪛 Install uv (if you don't have it)

curl -LsSf https://astral.sh/uv/install.sh | sh

Quick Install

uv tool install EvoScientist

Or install into the current environment instead:

uv pip install EvoScientist

Development Install

git clone https://github.com/EvoScientist/EvoScientist.git
cd EvoScientist
uv sync --dev

Using conda

conda create -n EvoSci python=3.11 -y
conda activate EvoSci
pip install -e ".[dev]"

Using PyPi

pip install EvoScientist          # quick install
pip install -e ".[dev]"           # development install

Optional: Channel dependencies

Messaging channel integrations require extra dependencies. Install only what you need:

uv pip install "EvoScientist[telegram]"     # Telegram
uv pip install "EvoScientist[discord]"      # Discord
uv pip install "EvoScientist[slack]"        # Slack
uv pip install "EvoScientist[wechat]"       # WeChat
uv pip install "EvoScientist[qq]"           # QQ
uv pip install "EvoScientist[all-channels]" # everything

Upgrade to the latest code base

git pull && uv sync --dev

🔝Back to top

🔑 Configuration

The easiest way to configure API keys is the interactive wizard:

EvoSci onboard

It walks you through provider selection, key validation, model choice, and workspace setup.

📟 Manual configuration via environment variables

Set at least one LLM provider key and (optionally) a search key:

# Pick one LLM provider
export ANTHROPIC_API_KEY="sk-..."   # Claude — console.anthropic.com
export OPENAI_API_KEY="sk-..."      # GPT   — platform.openai.com
export GOOGLE_API_KEY="AI..."       # Gemini — aistudio.google.com/api-keys
export NVIDIA_API_KEY="nvapi-..."   # NIM   — build.nvidia.com

# Web search (optional)
export TAVILY_API_KEY="tvly-..."    # app.tavily.com

Or use EvoSci config set to persist keys in ~/.config/evoscientist/config.yaml.

Alternatively, copy the example .env file for project-level configuration:

cp .env.example .env  # then fill in your keys

⚠️ Never commit .env files with real keys. It is already in .gitignore.

🔝Back to top

⚡ Quick Start

EvoSci  # or EvoScientist — interactive mode

Run EvoSci -h for all CLI options.

Common examples

EvoSci -p "your question"        # single-shot mode
EvoSci -m run                     # isolated per-session workspace
EvoSci --ui textual               # alternative TUI backend
EvoSci serve                      # headless mode — channels only, no interactive prompt

In-session commands

Command	Description
/new	Start a new session
/current	Show thread ID and workspace path
/channel	Start a messaging channel
/skills	List installed skills
/install-skill <src>	Install skill from path or GitHub
/mcp	List MCP servers and tool routing
/exit	Quit

Script Inference

from EvoScientist import EvoScientist_agent
from langchain_core.messages import HumanMessage
from EvoScientist.utils import format_messages

thread = {"configurable": {"thread_id": "1"}}
last_len = 0

for state in EvoScientist_agent.stream(
    {"messages": [HumanMessage(content="Hi?")]},
    config=thread,
    stream_mode="values",
):
    msgs = state["messages"]
    if len(msgs) > last_len:
        format_messages(msgs[last_len:])
        last_len = len(msgs)

🔝Back to top

🔌 MCP Integration

Add external tools via MCP servers with a single command:

# Usage
EvoSci mcp add <name> <command> [-- args...]

# Example
EvoSci mcp add sequential-thinking npx -- -y @modelcontextprotocol/server-sequential-thinking

[!TIP] For command options, config fields, tool routing, wildcard filtering, and troubleshooting, see the MCP Integration Guide.

🔝Back to top

📱 Channels

Connect messaging platforms so they share the same agent session as the CLI:

# Usage
EvoSci channel setup <channel>

# Example
EvoSci channel setup telegram

Multiple channels can run concurrently — comma-separate names in the config:

channel_enabled: "telegram,discord,slack"

The channel can also be started interactively with /channel in the CLI session.

[!TIP] For per-channel setup guides, capability matrix, architecture details, and troubleshooting, see the Channel Integration Guide.

🔝Back to top

📚 Acknowledgments

This project builds upon the following outstanding open-source works:

• LangChain — A framework for building agents and LLM-powered applications.
• DeepAgents — The batteries-included agent harness.

We thank the authors for their valuable contributions to the open-source community.

🔝Back to top

🌍 Project Roles

Xi Zhang†

Ziheng Zhang‡

Dinos Papakostas‡1

Yougang Lyu§

Xiaohui Yan§

Collaborators

Jan Piotrowski, Wiktor Cupiał, Yuyue Zhao, Xinhao Yi, Jakub Kaliski, Jakub Filipiuk, Shuyu Guo, Andreas Sauter, Jacopo Urbani, Zaiqiao Meng, Lun Zhou

^†Project Lead & Engineering Lead ^‡Core Developer ^§Project Correspondent

Xiaoyi DeepResearch Team and the wider open-source community contribute to this project.

For any enquiries or collaboration opportunities, please contact: [e-mail]

🔝Back to top

🤝 Contributing

We welcome contributions from developers and researchers at all levels. Please refer to our Contributing Guidelines to get started and help make EvoScientist more accessible.

❤️ Thanks go to these awesome contributors:

📈 Star History

🔝Back to top

📜 License

This project is licensed under the MIT License - see the LICENSE file for details.

🔝Back to top

---

Initiated and led by Xi Zhang, built with the open-source community.