ai-planning

🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

A simple HTN planner based around the principles of the Builder pattern.

Create a plan from a description in minutes

AI Automated Planning with STRIPS and PDDL in Node.js

Plan-then-build AI coding for Claude Code & Codex CLI — you approve the plan before the model writes a line of code. SPEC → PLAN → TEST → CODE → REVIEW → LEARN

A thinking process, not a template. 4-stage planning framework with 21 anti-pattern checks, adversarial hardening, and 8-domain detection for Claude Code.

Entropy-controlled contexts in Python

In this project a gardening system has been automated using IoT in the Raspberry Pi platform.

An AI planning project based on the 2019 international university timetabling competition which used commercial software IBM CPLEX to generate feasible course timetables with minimum penalty.

Total-order Forward Decomposition Algorithm: HTN Planning

The MightyVern bot

Resources and references on solved and unsolved problems in agentic AI.

T20: Multi-Agent. Orchestrator-delegate model. TAS. Goal -> plan -> delegate. Agents: Gemini family. Autonomous, traceable. Logs sessions. CLI. Usage: `t20-cli "goal string"`. Artifacts of high value.

A local, open-source tool that turns a rough idea, or a change to an existing codebase, into ordered development phases written for a coding agent, plus an optional UI mock and a deployment plan. Seven planning agents run in order; everything they write is a file under .spec4/ in your project. Apache 2.0. Bring your own model provider.

A Single-Outcome Replanner for Computing Strong Cyclic Solutions in Fully Observable Non-Deterministic Domains

Collaborative definition of HDDL Temporal extension

AI agent game competition - Reinforcement learning (Monte Carlo Tree Search, Deep Q-learning, Minimax)

limps your Local Intelligent MCP Planning Server across AI assistants. No subscriptions, no cloud—run it locally. Version control your planning docs in git. No more context drift—one shared source of truth across Claude, Cursor, Copilot, and any MCP tool.

🦾 ⚡ Paladinus: An Iterative Depth-First Search FOND Planner.

A simple framework to run multiple planners in parallel.