🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.
ai-planning 开源项目推荐(116 个)
ai-planning 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 116 个仓库A simple HTN planner based around the principles of the Builder pattern.
几分钟内从描述制定计划
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.
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/ai-planning。
- 该话题在 GitHub 上共有 116 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 2167 Star,覆盖 10 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。