Metadata-Version: 2.4
Name: ai-sci-agent
Version: 0.8.1
Summary: Full-process autonomous scientific research agent — from literature search to LaTeX paper
Project-URL: Homepage, https://github.com/ai-sci-agent/ai-sci-agent
Project-URL: Repository, https://github.com/ai-sci-agent/ai-sci-agent
Project-URL: Issues, https://github.com/ai-sci-agent/ai-sci-agent/issues
Author: AI-Sci Contributors
License: MIT
License-File: LICENSE
Keywords: agent,arxiv,deepagents,experiment,langgraph,latex,literature-review,llm,paper,reproducibility,research,scientific
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Classifier: Topic :: Text Processing :: Markup :: LaTeX
Requires-Python: >=3.12
Requires-Dist: deepagents>=0.6.11
Requires-Dist: langchain-openai>=1.3.3
Requires-Dist: langgraph-checkpoint-sqlite>=2.0
Requires-Dist: python-dotenv>=1.2.2
Provides-Extra: all
Requires-Dist: mlflow>=2.14; extra == 'all'
Requires-Dist: numpy>=1.26; extra == 'all'
Requires-Dist: pymupdf>=1.24; extra == 'all'
Requires-Dist: requests>=2.31; extra == 'all'
Requires-Dist: scikit-learn>=1.4; extra == 'all'
Requires-Dist: scipy>=1.12; extra == 'all'
Provides-Extra: dev
Requires-Dist: pytest-asyncio>=0.24; extra == 'dev'
Requires-Dist: pytest>=8.0; extra == 'dev'
Provides-Extra: papers
Requires-Dist: pymupdf>=1.24; extra == 'papers'
Provides-Extra: search
Requires-Dist: requests>=2.31; extra == 'search'
Provides-Extra: stats
Requires-Dist: numpy>=1.26; extra == 'stats'
Requires-Dist: scikit-learn>=1.4; extra == 'stats'
Requires-Dist: scipy>=1.12; extra == 'stats'
Provides-Extra: tracking
Requires-Dist: mlflow>=2.14; extra == 'tracking'
Description-Content-Type: text/markdown

# 🧪 AI-Sci: Autonomous Scientific Research Agent

One command from research question to LaTeX paper. Built on [DeepAgents](https://github.com/langchain-ai/deepagents) + [LangGraph](https://github.com/langchain-ai/langgraph), incorporating the ARIS research methodology.

## Install

```bash
uv tool install ai-sci-agent
ai-sci setup          # interactive wizard — pick provider, enter key
ai-sci run "improve LoRA with adaptive rank" --paper paper.pdf --repo ~/code
```

Or with pip:

```bash
pip install ai-sci
ai-sci setup
```

## 9-Phase Research Pipeline

```
search → analyze → refine → experiment_plan → reproduce → implement → experiment → review → write
```

| Phase | What it does |
|-------|-------------|
| **search** | Multi-source literature search with 3-layer anti-hallucination verification |
| **analyze** | PICO-M deep reading, 4-axis critical scoring, cross-paper synthesis |
| **refine** | Problem Anchor freeze, 7-dim iterative method scoring |
| **experiment_plan** | Claim-driven experiment design with 5-block evidence storyline |
| **reproduce** | Clone repos, install deps, run baselines, compare with paper claims |
| **implement** | Map method proposal to code changes, edit codebase, verify |
| **experiment** | Code integrity audit → sanity check → execute → stats → iterate |
| **review** | Structured peer review with weakness grading |
| **write** | LaTeX paper + 5-pass sciwrite audit + verified citations |

## Usage

```bash
# Full pipeline
ai-sci run "research question" \
  --paper https://arxiv.org/abs/2106.09685 \
  --repo ~/code \
  --data ~/datasets

# Interactive mode
ai-sci run "explore and improve this codebase" \
  --repo ~/code --interactive

# List/resume sessions
ai-sci sessions
ai-sci run "..." --resume sci-20260623-094430

# Single-phase commands
ai-sci search "query"
ai-sci analyze "Paper Title"
```

## Configuration

Run `ai-sci setup` for interactive setup, or create `~/.ai_sci/.env`:

```bash
MODEL_NAME=deepseek-chat
API_KEY=sk-your-key
BASE_URL=https://api.deepseek.com/v1
TAVILY_API_KEY=           # optional
```

Supports any OpenAI-compatible API: DeepSeek, OpenAI, SiliconFlow, Ollama, vLLM, Groq.

## Key Features

- **Autonomous end-to-end**: one command from question to paper
- **Honest**: no repo → skips experiments with `[NOT VALIDATED]`. No data → clearly reported. No GPU → tagged.
- **Persistent**: SqliteSaver + RESEARCH_WIKI.md + sessions + memory across restarts
- **ARIS methodology**: Problem Anchor, 7-dim scoring, claim-driven, code-review-first
- **Anti-hallucination**: 3-layer paper verification, never fabricates citations or results

## License

MIT
