> For the complete documentation index, see [llms.txt](https://polydictions.gitbook.io/polydictions/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://polydictions.gitbook.io/polydictions/polydagent.md).
# polydagent
### links
* x (twitter): x.com/polydagent
* github: github.com/poly-dictions/polydagent
* main project: polydictions.com
### how it works
1. **scans polymarket** for high-volume markets (>$100K, 10-90% odds, 14+ days out)
2. **runs deep research** via polyfactual API to analyze both sides
3. **posts alpha calls** with YES/NO signal and reasoning thread
4. **tracks performance** โ every call is logged and monitored
5. **daily recaps** show how our positions are moving
### call format
**main tweet:**
```
๐งก worth a look
[Market Title]
YES 20% / NO 80%
vol: $5.6M | ~12mo out
polymarket.com/event/[slug]
@polydictions ๐งก
```
**reply thread:**
```
deep research ๐ง
1/
YES reasons:
[reason 1]
[reason 2]
2/
NO reasons:
[reason 1]
[reason 2]
3/
Key risk:
[main uncertainty]
4/
Recommendation:
[YES/NO] with [confidence] - [brief reason]
by @polydictions ๐งก
```
### daily recap format
```
๐งก daily recap
๐ tracking 4 active calls
1. Russia x Ukraine ceasefire by March 31, 2026?
24% โ 22% (+3.0 for us)
2. Bitcoin $150k by 2025?
20% โ 18% (+2.0 for us)
3. 2026 NBA Champion (OKC Thunder)
46% โ 46% (0.0 for us)
by @polydictions ๐งก
```
### self-host
```bash
git clone https://github.com/poly-dictions/polydagent
cd polydagent
cp config.example.py config.py
# edit config.py with your API keys
pip install -r requirements.txt
python agent.py
```
#### required keys:
* Twitter API (developer.twitter.com)
* Gemini API (makersuite.google.com)
* Polyfactual API (optional, for deep research)
### support
questions? reach out on x: @simplyclassic69
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://polydictions.gitbook.io/polydictions/polydagent.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.