Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies using a multi-agent framework. It leverages Google's Gemini 2.5 Flash and OpenAI's GPT-5.1 on the backend for inference.
| Date | Stars |
|---|---|
| 2026-07-24 | 2177 |
| 2026-07-25 | 2181 |
| 2026-07-28 | 2181 |
| 2026-07-30 | 2181 |
| 2026-07-31 | 2198 |
| 2026-08-06 | 2198 |
Today
— stars today
This week
+17 stars this week
This month
— stars this month
Momentum
32.0
growth rate 0.78%/day
[](https://github.com/guy-hartstein/company-research-agent/blob/main/README.md)
[](https://github.com/guy-hartstein/company-research-agent/blob/main/README.zh.md)
[](https://github.com/guy-hartstein/company-research-agent/blob/main/README.fr.md)
[](https://github.com/guy-hartstein/company-research-agent/blob/main/README.es.md)
[](https://github.com/guy-hartstein/company-research-agent/blob/main/README.jp.md)
[](https://github.com/guy-hartstein/company-research-agent/blob/main/README.kr.md)
# Agentic Company Researcher 🔍
A multi-agent tool that generates comprehensive company research reports. The platform uses a pipeline of AI agents to gather, curate, and synthesize information about any company.
✨Check it out online! https://companyresearcher.tavily.com ✨
https://github.com/user-attachments/assets/0e373146-26a7-4391-b973-224ded3182a9
## Features
- **Multi-Source Research**: Gathers data from various sources, including company websites, news articles, financial reports, and industry analyses
- **AI-Powered Content Filtering**: Uses Tavily's relevance scoring for content curation
- **Asynchronous Processing**: Efficient polling-based architecture for tracking research progress
- **Dual Model Architecture**:
- Gemini 2.5 Flash for high-context research synthesis
- GPT-5.1 for precise report formatting and editing
- **Modern React Frontend**: Responsive UI with progress tracking and download options
- **Modular Architecture**: Built using a pipeline of specialized research and processing nodes
## Agent Framework
### Research Pipeline
The platform follows an agentic framework with specialized nodes that process data sequentially:
1. **Research Nodes**:
- `CompanyAnalyzer`: Researches core business information
- `IndustryAnalyzer`: Analyzes market position and trends
- `FinancialAnalyst`: Gathers financial metrics and performance data
- `NewsScanner`: Collects recent news and developments
2. **Processing Nodes**:
- `Collector`: Aggregates research data from all analyzers
- `Curator`: Implements content filtering and relevance scoring
- `Briefing`: Generates category-specific summaries using Gemini 2.5 Flash
- `Editor`: Compiles and formats the briefings into a final report using GPT-5.1
### Content Generation Architecture
The platform leverages separate models for optimal performance:
1. **Gemini 2.5 Flash** (`briefing.py`):
- Handles high-context research synthesis tasks
- Excels at processing and summarizing large volumes of data
- Used for generating initial category briefings
- Efficient at maintaining context across multiple documents
2. **GPT-5.1** (`editor.py`):
- Specializes in precise formatting and editing tasks
- Handles markdown structure and consistency
- Superior at following exact formatting instructions
- Used for:
- Final report compilation
- Content deduplication
- Markdown formatting
- Real-time report streaming
This approach combines Gemini's strength in handling large context windows with GPT-5.1's precision in following specific formatting instructions.
### Content Curation System
The platform uses a content filtering system in `curator.py`:
1. **Relevance Scoring**:
- Documents are scored by Tavily's AI-powered search
- A minimum threshold (default 0.4) is required to proceed
- Scores reflect relevance to the specific research query
- Higher scores indicate better matches to the research intent
2. **Document Processing**:
- Content is normalized and cleaned
- URLs are deduplicated and standardized
- Documents are soExcerpt of 12,238 characters
Read on GitHub
220
22
2
2
1
BigNounce
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:bf5e3dca8d0f2b21, topic:agents, topic:multi-agent-systems, readme:ai agents