Skillget

Spice_personal

agent
Guvenlik Denetimi
Gecti
Health Gecti
  • License — License: NOASSERTION
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 10 GitHub stars
Code Gecti
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This is an AI-powered decision assistant that helps users think through choices and optionally delegate tasks to external AI agents. It acts as a decision-layer runtime that connects to language models and can close the loop from decision to action.

Security Assessment
Overall Risk: Low. The light code scan found no dangerous patterns, hardcoded secrets, or requests for overly broad permissions. By design, the tool requires you to manually provide your own API keys (such as an OpenRouter key) via environment variables, meaning it does not secretly harvest credentials. The tool does make network requests to interact with configured external AI models and agents. A note of caution: the documentation mentions the ability to "execute tasks" via external agents, which inherently involves shell access and command execution. Because this relies on your own external configuration, the risk is manageable but dependent on what third-party agents you connect it to.

Quality Assessment
The project appears healthy and actively maintained, with repository pushes happening as recently as today. It has a decent baseline of community trust for a new niche tool, reflected by 10 GitHub stars. The package is easily installable via PyPI, and the documentation is clear and thorough. The only minor downside is that the automated license check registered as "NOASSERTION," even though the README clearly displays an MIT license badge.

Verdict
Safe to use, but exercise standard caution when configuring external agents to ensure you fully trust the third-party tools you grant execution permissions to.
SUMMARY

An AI decision assistant that helps you think, decide, and act — powered by Spice.

README.md
spice

Spice Personal — Your Decision Assistant

PyPI Python License Discord

🧭 What is Spice Personal?

Spice Personal is a reference app built on top of:

👉 Spice Runtime

It helps you think through decisions — and optionally take action via external agents.

👉 Try it in seconds:

Install from source (latest features, for development)

# Clone both repos (Spice Personal depends on spice-runtime)
git clone https://github.com/Dyalwayshappy/Spice.git
git clone https://github.com/Dyalwayshappy/Spice_personal.git

python -m venv .venv
source .venv/bin/activate  # Windows: .venv\Scripts\activate

pip install -U pip
pip install -e ./Spice
pip install -e ./Spice_personal

Install from PyPI (stable, recommended)

pip install spice-personal

This will automatically install spice-runtime.

Upgrade to latest version

pip install -U spice-personal
spice-personal --version

Verify installation

spice-personal --help

🚀 Quick Start

Spice is a decision-layer runtime.

The easiest way to try Spice is through the reference application: Spice Personal.

1. Initialize your workspace

spice-personal init

This creates a local workspace at:

.spice/personal/
and generates a default configuration file.

2. Ask your first question

spice-personal ask "What should I do next?"

Since no model is configured yet, you will see a Decision Card guiding you to the next step:

Setup required (no model configured)

Next:

-> Edit .spice/personal/personal.config.json

-> Then run: spice-personal ask "What should I do next?"

3. Connect a model

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=...

4. Run your intent

spice-personal ask "your intent"

Now Spice will produce a real decision, not just a setup guide.

5. (Optional) Interactive mode

spice-personal session

6. (Optional) Connect external agents

Spice can delegate actions to external agents (e.g. Claude Code, Codex).

This enables:

  • gathering real-world evidence
  • executing tasks based on decisions
  • closing the loop from decision → action

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

📁 Project Structure

spice-personal/
├── spice_personal/            # 🧭 Personal reference app/CLI
│   ├── cli/                   #    User-facing commands (ask/init/session)
│   ├── app/                   #    Personal orchestration flow
│   ├── advisory/              #    Personal decision/advisory logic
│   ├── execution/             #    Execution intent + evidence round logic
│   ├── executors/             #    Personal executor wiring/factory
│   ├── wrappers/              #    External agent/model wrappers
│   ├── provider_bridges/      #    Provider bridge layer
│   ├── config/                #    Workspace/env config resolution
│   ├── profile/               #    Profile contract + validation
│   ├── domain/                #    Built-in personal domain assets
│   └── tests/                 # ✅ Personal test suite
├── pyproject.toml             # 📦 spice-personal package metadata
├── README.md                  # 📝 Personal product quick start
├── LICENSE                    # ⚖️ MIT
└── .gitignore                 # 🙈 Ignore rules

⭐ Star History

⭐ Star us if you find Spice interesting

Views

Everyone should have a Spice — a decision brain for thinking and action.

Yorumlar (0)

Sonuc bulunamadi