Planning Python Packages

pypose

A library for differentiable robotics on manifolds.

20K 2K 127

pddl

Unquestionable PDDL 3.1 parser

6K 174 42

krystal-quorum

Preflight plan review for AI coding agents.

3K 2 0

pyrddlgym

A toolkit for auto-generation of OpenAI Gym environments from RDDL description files.

3K 93 23

xer-reader

Read and parse tables in P6 xer file.

3K 20 3

pyrddlgym-jax

JAX compilation of RDDL description files, and a differentiable planner in JAX.

3K 16 3

gridpath

A versatile simulation and optimization platform for power-system planning and operations.

2K 134 66

gui-agents

Agent S: an open agentic framework that uses computers like a human

2K 12K 1K

kodeagent

The minimal AI agent engine

2K 39 3

rddlrepository

Hosts domain and instance RDDL files, covering problems from a wide range of disciplines, integration with the pyRDDLGym ecosystem.

2K 14 5

nxdo

Generate the next 10 project tasks from project state, git history and an LLM prompt.

2K 0 0

mcpaisuite-ltpmcp

Compile-once planning (LTP) — turn a goal into a verifiable, token-cheap plan with static safety verification before execution. Python lib · CLI · MCP server · FastAPI.

2K 0 0

challenge-plans

Agent skill + CLI for multi-agent adversarial review of plans & specs before you execute them. Runs on the Claude Code / Codex subscriptions you already have — no API keys.

2K 4 0

taskledger

taskledger is a task-first durable state layer for staged coding work.

2K 0 0

pyrddlgym-rl

Wrappers for reinforcement learning algorithms (i.e. stable baselines 3, RLlib) to work with pyRDDLGym.

2K 5 2

pyrddlgym-gurobi

Gurobi compilation of RDDL description files to mixed-integer programs, and optimization tools.

2K 2 1

kgraphplanner

Part of the Vital Agent Ecosystem

2K 0 0

mcpaisuite-planningmcp

Goal-to-plan decomposition for AI agents, backed by compile-once LTP planning. Python lib · CLI · MCP server · FastAPI.

2K 0 0

certflow

Certified route planning under drifting costs: conformal certificates (LB<=OPT<=UB), certificate-directed sensing, proof-gated ns-us preprocessing, and an observable-coverage layer (WATCH + Shiryaev-Roberts). 250 tests, validated on real METR-LA.

1K 1 0