No description provided.
Javascript build-in lib reinforce
A collection of various reinforcement learning solver. The library is an object-oriented approach (baked with Typescript) and tries to deliver simplified interfaces that make using the algorithms pretty simple.
***WIP*** A Git Commit CLI Tool to reinforce conventional commits
Worshopper style training to reinforce knowledge of node.js
Dynamic swarm composition — select, reinforce, and prune agents
iview二次封装及组合拓展
Deep Recurrent Neural Networks and LSTMs in Typescript. Ported, object-oriented and refactored version of Andrej Karpathy's recurrent-js (https://github.com/karpathy/recurrentjs).
A rewards system that helps you reinforce your good habits!
Automatically bump up global Jest thresholds whenever coverage goes above them
Coding Course api by Khai Pham
Component for quiz recapitulation in education.
Metal on Symbol PoC
No description provided.
Three-layer memory architecture for OpenCode with workspace memory and hot session state
A Divider component
Production-grade AI coding toolkit — 70 agents (incl. devil-mode adversarial crew), 194 skills, 97 commands, parallel multi-agent commands, semantic intent routing, self-learning memory, and a built-in MCP server (16 tools / 6 prompts / 377 resources) tha
Memory-native terminal coding agent. Talks to the BrainRouter MCP cognitive engine for recall, skills, capture, persona, focus scenes, and contradiction tracking.
Lightweight sub-agents for pi — spawn specialized agents with isolated sessions, tools, and models.
Create functions executed within a web worker and return promises
Automatically bump up global Jest thresholds whenever coverage goes above them
Scaffold a new Lore coding agent harness
Tuple-Space + Yool runtime execution prompt for coding agents (Claude, Codex, Hermes, Cursor, Cline). Any user input triggers the runtime — no 'Implement' keyword required. Status output is opt-in via YOOL_TUPLE_STATUS.
Research on Indigenous Data Governance Protocols (RIDAGOP).
Deep reinforcement learning algorithms for rlevo (internal crate — use `rlevo` for the full API)
Safe Rust. No Deps. RL for the CPU.
surge synthesizer -- toplevel synthesizer virtual instrument
OptiRS Neural Architecture Search and hyperparameter optimization
Predictive Coding Actor-Critic reinforcement learning framework — pure Rust, zero ML dependencies
Reinforcement learning for Rust. Backend-agnostic over modern Rust ML frameworks.
Forger is a library for reinforcement learning with Rust
Predictive Coding Actor-Critic reinforcement learning framework — pure Rust, zero ML dependencies
A deep reinforcement learning library based on Rust and Candle, providing complete implementations of Q-Learning and DQN algorithms, supporting custom environments, various policy choices, and flexible training configurations. Future support will include more reinforcement learning algorithms, such as DDPG, PPO, A2C, etc.
A fast, extensible reinforcement learning framework in Rust
Toy domains for reinforcement learning research in Rust.
Reinforcement learning library
A tool for extracting accurate build orders from Company of Heroes 3 replay files.
Assorted patches for Rails.
Favorite Tweets from the command line
SciRb-learn (pronounced "Sigh Ruby learn") is to become a collection of machine learning and reinforcement algorithms natively implemented in Ruby
This gem provides a class for interacting with the DopamineAPI from ruby. After you have received your API key and configured the actions and reinforcements relevant to your app on the [Dopamine Developer Dashboard](dashboard.usedopamine.com), you may use this gem to place 'tracking', and 'reinforcement' calls from inside your app that will communicate directly with the DopamineAPI.
This generates its own input string that is used to create a file called possible lines that the self-reinforcement dialogue framework used to learn on. Then orates a random line of dialogue from reinforced lines.
Memory trace system for brain-modeled agentic AI — consolidation, reinforcement, and decay
Models cognitive echo chambers — when thoughts reinforce themselves without external challenge, creating self-reinforcing belief loops. Tracks amplification, resonance, and breakthrough events when external input disrupts the echo.
Computes internal reward signals from cognitive outcomes, tracks reward prediction error, and drives reinforcement learning
Models ideas with mass (importance) and velocity (change rate). Heavy ideas resist change (inertia), reinforced ideas accelerate, friction slows unreinforced ideas. Based on Newtonian dynamics metaphor.
Models narrative construction through thread-weaving. Individual threads (experiences, beliefs, memories, emotions, narratives) are woven into coherent tapestry fabric. Threads can fray, be reinforced, or create new patterns when they intersect.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.