# DeepScientist
**Repository Path**: zdbloom/DeepScientist
## Basic Information
- **Project Name**: DeepScientist
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Apache-2.0
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 0
- **Forks**: 0
- **Created**: 2026-04-06
- **Last Updated**: 2026-04-06
## Categories & Tags
**Categories**: Uncategorized
**Tags**: None
## README
DeepScientist
DeepScientist is a local-first AI research studio, Bring your own AI scientist onto your machine in 15 minutes.
GitHub |
中文文档 |
English Docs |
Paper |
Website
15-minute local setup ·
One repo per quest ·
Visible research progress ·
Human takeover anytime
Quick Start •
Launch Your First Project •
Product Tour •
Model Setup
If you are tired of paper overload, broken baselines, scattered experiment logs, and late-night writing cleanup, give the project a star first, then keep scrolling to see how much research grunt work it can take off your plate.
---
https://github.com/user-attachments/assets/3c7abb44-2b25-4477-a011-10a3154d6d76
## Still Spending Your Time On Research Grunt Work?
What drains researchers is often not the lack of ideas. It is the endless cycle of low-leverage work:
- new papers keep coming, but only a small fraction turns into an actionable next-step research plan
- baseline repos fail on environment, dependency, data, and script issues before real work even starts
- experiment results get scattered across terminals, scripts, notes, and chats, making later review painful
- writing, figures, and analysis live in separate tools, so turning them into a coherent paper takes far too long
This is the problem DeepScientist is built to solve:
> turn fragmented, repetitive, easy-to-lose research work into a local AI workspace that can keep moving, keep accumulating, and keep getting stronger over time
## DeepScientist Is Not Just Another "Research Chatbot"
It is not a tool that summarizes papers, throws you a few ideas, and leaves the dirty work to you.
It is much closer to a real long-running AI research partner:
| What common AI tools often look like | What DeepScientist does instead |
|---|---|
| Great at chatting, but context disappears quickly | Turns tasks, files, branches, artifacts, and memory into durable state |
| Good at suggesting ideas, but weak at sustained execution | Pushes papers, baselines, experiments, and writing inside one workspace |
| Strong automation, but feels like a black box | Lets you inspect the process through the web workspace, Canvas, files, and terminal |
| Hard to take over once it goes off track | Lets you pause, take over, edit plans, change code, and continue at any time |
| Each run ends when the run ends | Preserves failed paths, winning paths, and reproduction lessons for the next round |
## About
> DeepScientist is not a one-shot agent demo. It is a system built for long-horizon research work.
## What Can It Actually Help You Get Done?
### 1. Start a real project from a paper or a research question
- feed it a core paper, a GitHub repository, or a natural-language research objective
- it turns those inputs into an executable quest instead of a chat that loses state after a few turns
### 2. Reproduce baselines and keep the reproduction reusable
- restore repositories, prepare environments, handle dependencies, and track the critical failures
- preserve what broke, what got fixed, and which steps are trustworthy for future rounds
### 3. Run experiments continuously instead of stopping after one pass
- propose the next hypothesis from existing results
- branch, ablate, compare, and record conclusions
- keep failed routes as assets instead of deleting them
### 4. Turn results into materials you can actually ship
- organize findings, conclusions, and analysis
- produce figures, reports, and paper drafts
- support local PDF and LaTeX compilation workflows
### 5. Follow the same research effort from multiple surfaces
- the web workspace in your browser
- the TUI workflow on a remote server
- external connector surfaces for collaboration and progress updates
The current docs already cover these collaboration channels:
- [Weixin](docs/en/10_WEIXIN_CONNECTOR_GUIDE.md)
- [QQ](docs/en/03_QQ_CONNECTOR_GUIDE.md)
- [Telegram](docs/en/16_TELEGRAM_CONNECTOR_GUIDE.md)
- [WhatsApp](docs/en/17_WHATSAPP_CONNECTOR_GUIDE.md)
- [Feishu](docs/en/18_FEISHU_CONNECTOR_GUIDE.md)
- [Lingzhu / Rokid](docs/en/04_LINGZHU_CONNECTOR_GUIDE.md)
## Why Is It Easier To Keep Using?
What retains users is not a flashy demo. It is a system that becomes more useful the longer you work with it.
DeepScientist tends to stick for four reasons:
### Local-first by default
- code, experiments, drafts, and project state stay on your own machine or server by default
- this is especially valuable for unpublished ideas, sensitive experiment history, and longer-running research loops
### One repo per quest
- every quest is a real Git repository
- branches, worktrees, files, and artifacts naturally express research structure
### The process is not a black box
- it does not only give you an output
- you can inspect what it read, what it changed, what it kept, and what it plans to do next
### Human collaboration is built in
- DeepScientist can move autonomously
- you can also step in, edit, redirect, and hand control back whenever you want
## Why Try It Now?
Because this is not just a concept. It is a real system with public docs, a public paper, and a public install path.
- `2026/03/24`: DeepScientist officially released `v1.5`
- `2026/02/01`: the paper went live on [OpenReview](https://openreview.net/forum?id=cZFgsLq8Gs) for `ICLR 2026`
- npm install path is already available: [`@researai/deepscientist`](https://www.npmjs.com/package/@researai/deepscientist)
- both Chinese and English docs are available, along with Web, TUI, and connector entry points
## Product Preview
### Architecture Overview
### Example Outputs
|
|
Example paper output 1
Paper-facing deliverables can be preserved directly inside the quest instead of being split across external tools.
|
Example paper output 2
DeepScientist can carry work through writing, review, figure polish, and export workflows.
|
### Workspace Preview
|
|
|
Start Research
Kick off a quest from a paper, repository, or natural-language goal.
|
Canvas
Inspect branches, baselines, and accumulated research structure as a visible map.
|
Studio + Details
Review metrics, traces, and project state without leaving the same workspace.
|
### Progress Reporting
### Projects surface after long-running work
## Who Will Love DeepScientist Most?
- graduate students and engineers who want to reproduce papers and push beyond existing baselines
- labs or research teams running long experiment loops, ablations, and structured result analysis
- people who want code, experiments, notes, and writing to live in one workspace
- users who do not want to hand unpublished ideas and intermediate results directly to a pure cloud workflow
- people who want to run work on servers while following progress from web, TUI, or messaging surfaces
## The Core Philosophy Behind DeepScientist
We believe a system that is actually suitable for research should at least satisfy these principles:
- one quest, one repository, instead of letting everything dissolve after a short conversation
- branches and worktrees should express research routes naturally instead of being forced into chat history
- failed paths should be preserved, summarized, and reused instead of overwritten
- human researchers should always retain takeover power instead of being locked outside the loop
- the research process should be reviewable, inspectable, and auditable instead of relying on "the model says it did it"
If that sounds like the way you want to work, DeepScientist is worth trying now.
## Get Started In 30 Seconds
If you want to try it right now, the shortest path is:
Platform note: DeepScientist fully supports Linux and macOS. Native Windows support is currently experimental (strongly recommend WSL2).
```bash
npm install -g @researai/deepscientist
codex --login
ds --here
```
To stop the managed local daemon and all currently running agents:
```bash
ds --stop
```
If `codex --login` is unavailable, run this once first:
```bash
codex
```
If `codex` still appears to be missing after installing DeepScientist, take the explicit repair path instead of assuming the bundled dependency was linked correctly:
```bash
npm install -g @openai/codex
which codex
codex --login
```
If `which codex` still prints nothing after that, fix the npm global bin path first, then retry `codex --login` and `ds doctor`.
After startup, the default local address is:
```text
http://127.0.0.1:20999
```
Local browser auth is now optional and disabled by default. If you want a per-launch local access password, start with:
```bash
ds --auth true
```
Then you only need to do three things:
1. click `Start Research`
2. fill in the research goal, baseline links, paper links, or local paths
3. let DeepScientist start a real research project that can keep evolving locally
If this is your first run, prefer an isolated environment, a non-root user, and a local machine. For the full details, see:
- [00 Quick Start](docs/en/00_QUICK_START.md)
- [15 Codex Provider Setup](docs/en/15_CODEX_PROVIDER_SETUP.md)
- [09 Doctor](docs/en/09_DOCTOR.md)
## Choose Your Starting Path
### I just want to get it running first
- [00 Quick Start](docs/en/00_QUICK_START.md)
- [12 Guided Workflow Tour](docs/en/12_GUIDED_WORKFLOW_TOUR.md)
### I want to launch a real project today
- [02 Start Research Guide](docs/en/02_START_RESEARCH_GUIDE.md)
- [01 Settings Reference](docs/en/01_SETTINGS_REFERENCE.md)
### I mainly work on servers and terminals
- [05 TUI Guide](docs/en/05_TUI_GUIDE.md)
### I want to connect my own models or external collaboration channels
- [15 Codex Provider Setup](docs/en/15_CODEX_PROVIDER_SETUP.md)
- [Weixin Connector Guide](docs/en/10_WEIXIN_CONNECTOR_GUIDE.md)
- [QQ Connector Guide](docs/en/03_QQ_CONNECTOR_GUIDE.md)
- [Telegram Connector Guide](docs/en/16_TELEGRAM_CONNECTOR_GUIDE.md)
- [WhatsApp Connector Guide](docs/en/17_WHATSAPP_CONNECTOR_GUIDE.md)
- [Feishu Connector Guide](docs/en/18_FEISHU_CONNECTOR_GUIDE.md)
### I want to understand the system design first
- [Docs Index](docs/en/README.md)
- [Core Architecture Guide](docs/en/13_CORE_ARCHITECTURE_GUIDE.md)
- [Prompt, Skills, and MCP Guide](docs/en/14_PROMPT_SKILLS_AND_MCP_GUIDE.md)
## Autonomous Research Systems
### End-to-End Autonomous Research Systems
| System | System Type | E2E | Research Map | Workshop | Keeps Growing | Channels | Figure & Rebuttal & Review |
|---|---|---|---|---|---|---|---|
| [autoresearch](https://github.com/karpathy/autoresearch) | Open-source | | | ✓ | | | |
| [RD-Agent](https://github.com/microsoft/RD-Agent) | Open-source | | | | ✓ | | |
| [Agent Laboratory](https://github.com/SamuelSchmidgall/AgentLaboratory) | Open-source | ✓ | | ✓ | ✓ | | |
| [AI-Scientist](https://github.com/SakanaAI/AI-Scientist) | Open-source | ✓ | | | | | |
| [AI-Scientist-v2](https://github.com/SakanaAI/AI-Scientist-v2) | Open-source | ✓ | | | | | |
| [AutoResearchClaw](https://github.com/aiming-lab/AutoResearchClaw) | Open-source | ✓ | | | ✓ | ✓ | |
| [ClawPhD](https://github.com/ZhihaoAIRobotic/ClawPhD) | Open-source | | | ✓ | | ✓ | |
| [Dr. Claw](https://github.com/OpenLAIR/dr-claw) | Open-source | ✓ | | ✓ | | ✓ | |
| [FARS](https://analemma.ai/fars/) | Closed-source | ✓ | | | | | |
| [EvoScientist](https://github.com/EvoScientist/EvoScientist) | Open-source | ✓ | | ✓ | ✓ | ✓ | |
| [ScienceClaw](https://github.com/beita6969/ScienceClaw) | Open-source | | | | ✓ | ✓ | |
| [claude-scholar](https://github.com/Galaxy-Dawn/claude-scholar) | Open-source | ✓ | | ✓ | ✓ | | |
| [Research-Claw](https://github.com/wentorai/Research-Claw) | Open-source | ✓ | | ✓ | ✓ | ✓ | |
| [DeepScientist](https://github.com/ResearAI/DeepScientist) | Open-source | ✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
## Documentation
- [English Docs Index](docs/en/README.md)
- [Chinese Docs Index](docs/zh/README.md)
## NLPCC 2026 AISB Challenge
If you want to benchmark or extend AI scientist systems in the wild, the NLPCC 2026 AISB shared task is a natural next stop:
- [Registration](http://tcci.ccf.org.cn/conference/2026/shared-tasks/)
- [Task Repository](https://github.com/ResearAI/NLPCC-2026-Task9-AISB)
## For Developers And Maintainers
If you are developing or maintaining DeepScientist, continue with:
- [Architecture](docs/en/90_ARCHITECTURE.md)
- [Development Guide](docs/en/91_DEVELOPMENT.md)
- [CONTRIBUTING](CONTRIBUTING.md)
## Citation
If DeepScientist helps your research or engineering work, please cite:
```bibtex
@inproceedings{
weng2026deepscientist,
title={DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively},
author={Yixuan Weng and Minjun Zhu and Qiujie Xie and QiYao Sun and Zhen Lin and Sifan Liu and Yue Zhang},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=cZFgsLq8Gs}
}
```
If this feels like the research workflow you have been waiting for, give the project a star. Every star makes it easier for more researchers who actually need it to find it.
## Community
Welcome to join the WeChat group for discussion.
## More From ResearAI
If you like DeepScientist, you may also want to explore the rest of the ResearAI ecosystem:
| Project | What it does | Stars |
|---|---|---|
| **[MeOS](https://github.com/ResearAI/MeOS)** | Fork yourself as a Skill, so agents understand you better |  |
| [AutoFigure](https://github.com/ResearAI/AutoFigure) | generate publication-ready figures |  |
| [AutoFigure-Edit](https://github.com/ResearAI/AutoFigure-Edit) | generate editable vector paper figures |  |
| [DeepReviewer-v2](https://github.com/ResearAI/DeepReviewer-v2) | review papers and suggest revisions |  |
| [Awesome-AI-Scientist](https://github.com/ResearAI/Awesome-AI-Scientist) | curated AI scientist landscape |  |