dsh-rivermind
Heads-up Texas Hold'em AI sparring partner and training workbench for DeepSeek Harness.
Install
$ dsh plugin --profile desktop add dsh-rivermindPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Heads-up Texas Hold'em game engine supporting BB/pot-ratio quick betting, chip/BB display, and all-in showdown mechanics
- Isolated Agent architecture equipped strictly with poker tools (get_observation, recall_opponent, estimate_equity, submit_action)
- Persistent long-term player memory tracking opponent tendencies, street/position stats, and condition profiles across sessions
- Detailed post-hand reviews with decision traces, model diagnostics, tool latencies, and exportable JSON diagnostics
- Dual operation modes supporting both real LLM-backed sparring and zero-cost local rule-based sparring
Useful For
- Practicing heads-up No-Limit Texas Hold'em against an adaptive, memory-retaining AI opponent
- Analyzing poker decision-making processes through step-by-step hand replays and LLM reasoning traces
- Studying agent decision architectures under restricted toolsets and structured game rules
Who It Fits
- Poker enthusiasts looking for interactive heads-up training with opponent memory
- DeepSeek Harness developers studying agent tool isolation and trace diagnostics
- AI researchers evaluating structured decision-making in imperfect-information games
Documented Limitations
- Restricted to 2-player heads-up games; 6-max tables and multi-way pots are not supported
- Equity calculation in rule sparring relies on random range sampling rather than a true GTO solver
- Does not support CFR/RL self-play strategy upgrades or resuming mid-game interrupted hands
- Changing the active model requires modifying DSH defaults and restarting DSH because Iris reuses initial session settings
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 8 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
package.json declares a prepare lifecycle script that may run during relevant package installation workflows.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- jiangzeyuan/dsh-rivermind
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- dbbeceb · 2026-10-19
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 4GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-10-08
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Agent skill and plugin that transforms concise Markdown drafts into standalone, visual single-page HTML explainers and videos.
View plugin →Agent skill for DeepSeek Harness that turns ideas, plans, and codebases into interactive architecture diagrams.
View plugin →Lingshu long-term auditable memory system and cognitive graph for DeepSeek Harness.
View plugin →Multi-account failover model pool, quota aggregator, and automation suite for DeepSeek Harness.
View plugin →