You're reading this. The skill predicted it. A workflow that turns every post into a calibrated experiment—score, blind-predict, retro, evolve. The future doesn't reward effort, it rewards those who see the pattern first. 1M followers in a month — not luck, system.
Repository Index
83,087 visible repositories in the index
1–18 of 18 · Most stars
Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.
- ai-agents
- ai-workflow
- automation
- codex
Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)
Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.
- proof-assistant
- lean4
- ai-agents
- ai-for-math
A list of commands, scripts, resources, and more that I have gathered and attempted to consolidate for use as OSCP (and more) study material. Commands in 'Usefulcommands' Keepnote. Bookmarks and reading material in 'BookmarkList' CherryTree. Reconscan Py2 and Py3. Custom ISO building.
- oscp
- reconscan
- pentest
- penetration-testing
TEdit - Terraria Map Editor - TEdit is a stand alone, open source map editor for Terraria. It lets you edit maps just like (almost) paint! It also lets you change world settings (time, bosses downed etc), edit chests and change sign, make epic dungeons, castles, cities, and add rewards for your adventurers!
- tedit
- terraria
Clean PyTorch implementations of imitation and reward learning algorithms
- reward-learning
- inverse-reinforcement-learning
- imitation-learning
- gymnasium
[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation
- diffusion-models
- generative-model
- rlhf
- human-preferences
A package containing micro-interactions you can use to reward your users for little things and make them smile!
- react
- reactjs
- react-components
- rewards
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
Recipes to train reward model for RLHF.
For deep RL and the future of AI.
- deep-reinforcement-learning
- reinforcement-learning
- game
- reward
A concise and readable language for Firestore security rules, similar to Firebase Bolt.
- firebase-firestore
- haskell
- typescript
- parser-combinators
Solana validator health in 60 seconds: score, leader duties, rewards, disk forecast, Prometheus. One static binary, read-only, never touches your keys.
The repository host gives no description.
SubQuery API for saturating Nova Wallet as a data source. Focuses on the following use cases: 1) Provide complete operation history, including Transfers, Rewards/slashes, Other extrinsics 2) Provide data for staking analytics
- blockchain
- indexer
- polkadot
- kusama
An application to track and visualize the rewards from running an Algorand node, using Nodely API.
- algorand
- algorand-blockchain
- algorand-node
Configurable Hangman game for children with ASCII-art rewarding (Gitlab mirror)
- hangman-game
- children
- ascii-art