DEDUPED Hot AI repos, turned into use cases Get the Monday 5
238 stars · Python

How to use Phil: what you can do with it

What is Phil? Phil is an open-source Python project where an AI agent trades short-term prediction markets on paper, rewrites its own strategy after each settled bet, and can place small capped real-money twins through Pearl Connect.

How do I use it? git clone https://github.com/bennyjo/phil.git; then cd phil; python3 core/score.py --skip-mtm. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • Audit whether Phil beats the market price

    Run the offline score report to check if Phil's probabilities beat Polymarket's own prices.

    View prompt
    Clone https://github.com/bennyjo/phil, run `python3 core/score.py --skip-mtm` offline, and report the calibration results and the brier_delta value. Verify that the report states whether the agent's probabilities beat the market price, and say so if it does not.

  • Run your own paper-trading agent from a fork

    Fork Phil, run a few paper cycles with Claude Code, and watch the agent edit its own strategy.

    View prompt
    Fork bennyjo/phil, clone the fork, and run `./loop.sh 10 45` for paper cycles. Report how many cycles committed, which files under strategy/ changed, and the output of `python3 core/validate.py`. Verify that no file under core/ or config/protected.json changed.

  • Trace which strategy edits Phil kept or reverted

    Read the strategy commit history and daily retros to see what the agent learned and reverted.

    View prompt
    Clone https://github.com/bennyjo/phil, list commits that touch strategy/, and match each to a retro in journal/retros/. Output a table of edit, decision (keep, sharpen, or revert), and the evidence cited. Verify that every row cites a retro file that exists.

  • Place capped real-money twins of paper bets

    Set up Pearl Connect and run one real-mode cycle with per-bet caps in place.

    View prompt
    In a clone of https://github.com/bennyjo/phil, with PEARL_CONNECT_STORE set to <workspace path>, run `python3 core/real.py doctor` and report whether it says ready. Then run `./loop.sh 1 45 --real` and report the real fills and caps applied. Verify that per-bet stakes do not exceed the cap in config/protected.json.

Quick start with Phil

  1. Check you have what it needs: Python 3 (CI runs on Python 3.12); the engine uses the standard library only; git and a clone of the repository; A Claude Code account and the `claude` command on your PATH, for running cycles.
  2. Open bennyjo/phil on GitHub and read the README and license.
  3. git clone https://github.com/bennyjo/phil.git
  4. cd phil
  5. python3 core/score.py --skip-mtm (inferred, check the README)
  6. Read the calibration section and find brier_delta.

These steps come from our top use case, Audit whether Phil beats the market price, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for bennyjo/phil

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Phil alternatives · Best AI repos for Money

About this repo

  • Who it is forDevelopers and researchers who study AI agent self-improvement or prediction-market calibration, and operators considering a small, capped real-money run.
  • Why it is hot238 stars, launched 88 days ago
  • LanguagePython
  • Sourcegithub.com/bennyjo/phil · Back to Hot repos

Requirements

  • Python 3 (CI runs on Python 3.12); the engine uses the standard library only
  • git and a clone of the repository
  • A Claude Code account and the `claude` command on your PATH, for running cycles
  • A fork with write access to origin, or no origin remote for local-only runs
  • Pearl Connect installed from pearl.you/connect and a funded Safe, only for real-money mode

Add this badge to your README

Maintain Phil? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/bennyjo/phil.svg)](https://dedupedai.com/use-cases/bennyjo-phil/?utm_source=github&utm_medium=badge&utm_campaign=bennyjo-phil)

HTML 

<a href="https://dedupedai.com/use-cases/bennyjo-phil/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=bennyjo-phil"><img src="https://dedupedai.com/badge/bennyjo/phil.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Phil

What is Phil?

Phil is an open-source Python project where an AI agent trades short-term prediction markets on paper, rewrites its own strategy after each settled bet, and can place small capped real-money twins through Pearl Connect. It is an open-source project on GitHub: https://github.com/bennyjo/phil.

How do I use Phil?

git clone https://github.com/bennyjo/phil.git; then cd phil; python3 core/score.py --skip-mtm. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Phil for?

Developers and researchers who study AI agent self-improvement or prediction-market calibration, and operators considering a small, capped real-money run.

What can I do with Phil?

4 use cases so far, for example: Audit whether Phil beats the market price; Run your own paper-trading agent from a fork; Trace which strategy edits Phil kept or reverted. Each has steps and a copy-paste agent prompt.

What do I need to run Phil?

Python 3 (CI runs on Python 3.12); the engine uses the standard library only; git and a clone of the repository; A Claude Code account and the `claude` command on your PATH, for running cycles; A fork with write access to origin, or no origin remote for local-only runs.

What are alternatives to Phil?

Other hot AI repos in Money: Fincept Terminal, Freqtrade, Vibe Trading, Day Trader Skill, Tick Stock Panel.

Is Phil safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.