percept everything and make the 'best' decision for you. Your second 'brain' 感知万物，做最适合你的决策，你的“第二大脑”
# Add to your Claude Code skills
git clone https://github.com/Dyalwayshappy/SpiceAgents can execute.
But they don’t know what to do next.
Spice is a decision-layer runtime — a brain above agents. inspired by the rise of execution agents like OpenClaw and the idea of world model.
While execution agents (Claude Code, OpenClaw, Codex) are getting better at doing things,
Spice focuses on the missing layer:
👉 What should be done next — and why.
To gain a more intuitive understanding of Spice,
please visit our carefully prepared demo about conflicts between life and work events: Spice-live-demo
Click the image to watch the full demo video of using Spice to handle conflicts between the digital and physical worlds.
Click the image to watch the full demo video of using Spice to handle conflicts between the digital and physical worlds.
Today, we have powerful agents that can do almost anything:
But when you sit down to use them, you still face the same problem:
What should I do next?
That’s the hard part.
The real bottleneck is:
Decision-making.
Spice is designed to solve that.
No comments yet. Be the first to share your thoughts!
Spice provides a structured cognitive loop inspired by the concept of world model :
perception → state model → simulation → decision → execution → reflection
It allows AI systems to:
Spice is a general decision runtime. —
To make this concrete, we built our first reference application:
It is not just a demo.
It is an AI that helps you:
From:
question → reasoning → decision → action → outcome
All in one loop.
"I want to quickly build a lightweight tool for a small group of friends."
A simple, real-world goal with clear constraints
Spice focuses on the decision layer.
In a full workflow, the selected decision can be passed to external agents (e.g. codex and claude code) for execution.
This example stops at decision + next step.
➡️ Next, we will take this exact scenario and connect it to an external agent to actually build the tool end-to-end.
Decision → Execution → Outcome → Reflection
This is the full loop Spice is designed to enable.
Spice Personal is just one reference.
The underlying model is domain-agnostic.
Spice is a general decision runtime that can be applied to any domain where:
This includes:
Spice is not limited to one use case.
It is a foundation for building decision systems.
Install from source (latest features, for development)
git clone https://github.com/Dyalwayshappy/Spice.git
cd Spice
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -U pip
pip install -e .
Install from PyPI (stable, recommended)
pip install spice-runtime
pip install -U spice-runtime
spice-runtime --version
Spice is a decision-layer runtime.
The easiest way to try Spice is through the reference application: Spice Personal.
spice-personal init
This creates a local workspace at:
.spice/personal/ and generates a default configuration file.
spice-personal ask "What should I do next?"
Since no model is configured yet, Spice will guide you with a structured Decision Card:
This helps you understand the next step instead of failing silently.
Edit the generated config file:
.spice/personal/personal.config.json
Configure your model provider (e.g. OpenRouter) and set your API key:
export OPENROUTER_API_KEY=...
spice-personal ask "your intent"
Now Spice will produce a real decision, not just a setup guide.
spice-personal session
Spice can delegate actions to external agents (e.g. Claude Code, Codex).
This enables:
To enable this, configure your agent in:
.spice/personal/personal.config.json
This is where Spice moves beyond reasoning — into action.
Now Spice can:
search for relevant information
call external tools(Currently supports wrappers for CodeX and ClaudeCode.)
and make decisions grounded in real-world signals
Spice transforms your world into a structured decision system.
It enables a new way to think, decide, and act:
Perception
Understand your world and extract meaningful signals
State Modeling
Turn it into a structured decision model
Simulation
Explore possible futures before taking action
Decision
Compare trade-offs and then give you decision-making assistance.
Execution (optional)
Delegate actions to external agents (e.g. Claude Code, Codex)
Reflection
Learn from outcomes and continuously improve decisions
SDEP is the protocol defined by Spice for connecting the decision layer with external execution agents.
Spice decides what should be done.
SDEP handles how that decision is executed and how results flow back.
Most AI systems tightly couple reasoning and execution.
SDEP introduces a clean separation:
Decision layer (Spice) → determines intent and direction
Execution layer (agents/tools) → performs real-world actions
This allows Spice to act as a brain above agents, instead of being tied to any single tool.
SDEP is responsible for:
Encoding execution intent
Turning decisions into structured, executable requests
Dispatching to external agents
(CLI tools, subprocesses, remote services, etc.)
Receiving structured results
Capturing outputs, status, and signals from execution
Feeding outcomes back into the system
Enabling state updates, reflection, and next decisions
Decision → ExecutionIntent → Agent → Result → Outcome → Reflection
Spice is not an execution agent.
It is the decision layer above agents.
Spice supports an open wrapper ecosystem.
Even if an external agent does not natively support SDEP, it can still be integrated through a wrapper.
A wrapper is a protocol bridge between Spice and external agents.
Spice