Welcome to OraClaw -- What should we build next?

[Whatsonyourmind]

Welcome!

OraClaw is a decision intelligence toolkit for AI agents -- 19 algorithms, 12 MCP tools, sub-25ms latency, zero LLM cost. Every tool runs deterministically, returns structured JSON, and costs nothing to compute.

We'd love to hear from you: What algorithms or capabilities would you like to see next?

Current Algorithm Suite (19)

Category	Algorithms
Optimization	Multi-Armed Bandit (UCB1, Thompson, Epsilon-Greedy), Contextual Bandit (LinUCB), CMA-ES, Genetic Algorithm
Simulation	Monte Carlo Simulation, Scenario Planning
Solvers	Constraint Solver (LP/MIP via HiGHS), Schedule Optimizer
Analysis	Decision Graph (PageRank, communities), Portfolio Risk (VaR/CVaR)
Prediction	Bayesian Inference, Ensemble Model, Time Series Forecast (ARIMA, Holt-Winters)
Detection	Anomaly Detection (Z-Score, IQR)
Scoring	Convergence Scoring, Calibration Scoring
Planning	A* Pathfinding

What we're considering

• Reinforcement learning (Q-learning, policy gradient)
• Game theory (Nash equilibrium solver)
• Causal inference engine
• Clustering (k-means, DBSCAN)
• Recommendation engine
• More forecasting models (Prophet-style, exponential smoothing variants)

Tell us

• What's your use case? (agent routing, financial modeling, ops optimization, etc.)
• What algorithm would unlock the most value for you?
• Are you using OraClaw via API, MCP, or npm SDK?

Drop a comment below or upvote ideas others have posted. We prioritize based on community demand.

Links:

• Live API: https://oraclaw-api.onrender.com
• npm: https://www.npmjs.com/org/oraclaw
• MCP setup: see README