# fedden/poker_ai

🤖 An Open Source Texas Hold'em AI

Repository: https://github.com/fedden/poker_ai
Canonical: https://ross.abutalabs.com/products/poker_ai
Language: Python
License: NOASSERTION
License Family: other
Topics: texas-holdem-poker, pluribus, python, poker-engine, machine-learning, counterfactual-regret-minimization, artificial-intelligence, open-source
Archived: true
Last push: 2023-04-03T03:00:44+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2426, "days_push": 1248, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1584, forks 410 (observed 2026-08-28T04:05:07.420415+00:00)

## What it is
An open-source Python implementation of a Texas Hold'em poker AI based on Counterfactual Regret Minimization (CFR), inspired by Pluribus. It includes a poker engine, hand evaluator, information-set clustering, agent training, and a CLI for training and playing against the bot.

## Use cases
- train a texas holdem poker bot with counterfactual regret minimization
- play poker against an AI agent from the command line
- cluster poker information sets into lookup tables
- evaluate poker hands in python
- build a poker game engine for research
- reproduce a pluribus-style poker AI
- resume training a poker agent from a checkpoint

## When to choose
- you want an open-source CFR-based poker AI to study or extend
- you need a Python poker engine plus hand evaluator in one package
- you want to experiment with game-theoretic AI training on Texas Hold'em

## When to avoid
- you need a production-strength poker bot rivaling commercial solvers
- you want a graphical poker game or online casino integration
- you need real-money gambling features or multi-table tournament support
- you require a permissively licensed library (it is GPL v3)

## Facets
- artifact type: library
- maturity: experimental
- function: machine-learning, cli, game
- domain: artificial-intelligence, machine-learning, gaming-tools
- platform: python, cli, cross-platform
- tags: poker, texas-holdem, counterfactual-regret-minimization, pluribus, game-ai, hand-evaluation, card-games, algorithms

## Member repositories
- fedden/poker_ai (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:07.420415+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:55:56.948264+00:00, confidence not recorded.
  - readme: https://github.com/fedden/poker_ai (fetched 2026-08-28T04:05:07.420415+00:00, sha 72d55c869280)
  - registry_pypi: https://pypi.org/pypi/poker_ai/json (fetched 2026-08-29T11:26:28.547898+00:00, sha a5794e48f922)
- Data as of 2026-08-30T08:39:29.467469+00:00.