sparc  by ruvnet

CLI tool for AI-assisted software development using the SPARC framework

Created 11 months ago
378 stars

Top 75.2% on SourcePulse

GitHubView on GitHub
Project Summary

The SPARC Framework is a comprehensive methodology for developing robust and scalable applications, targeting software engineers and teams seeking a structured, AI-assisted development process. It aims to enhance quality, collaboration, and intelligent evolution through a defined five-step lifecycle.

How It Works

SPARC guides development through Specification, Pseudocode, Architecture, Refinement, and Completion. It integrates advanced AI tools like Perplexity for research and AIDER.chat for coding, leveraging symbolic reasoning and "pseudo consciousness" for enhanced decision-making and self-improvement. The framework emphasizes documentation, reflective practices, and adaptive optimization.

Quick Start & Requirements

  • Install from PyPI: pip install sparc
  • Requires Python 3.8+
  • API keys for LLM providers (Anthropic, OpenAI, OpenRouter) must be configured via environment variables (.env file).
  • Official documentation and example project available.

Highlighted Details

  • SPARC CLI (v0.87.7) offers AI-assisted development with autonomous research and implementation capabilities.
  • Supports multiple LLM providers (Anthropic, OpenAI, OpenRouter) and models.
  • Features human-in-the-loop controls and an optional "cowboy mode" for autonomous shell command execution.
  • Integrates PolarisOne for enhanced token weighting, memory management, and context-aware development.
  • Includes a tool system for file operations, directory navigation, shell commands, research, and web scraping (via Scape tool).

Maintenance & Community

  • Contributions are welcomed via pull requests.
  • Project acknowledges contributions from Perplexity, AIDER.chat, OpenAI, RA.Aid, Playwright, and Langchain.

Licensing & Compatibility

  • Licensed under the Apache 2 License.
  • Permissive license suitable for commercial use and integration with closed-source projects.

Limitations & Caveats

The tool executes shell commands and makes code changes, with a strong warning to use at your own risk, especially in version-controlled repositories. The "cowboy mode" bypasses approval prompts for shell commands.

Health Check
Last Commit

7 months ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
16 stars in the last 30 days

Explore Similar Projects

Starred by Edward Z. Yang Edward Z. Yang(Research Engineer at Meta; Maintainer of PyTorch), Anton Osika Anton Osika(Cofounder of Lovable), and
3 more.

gptme by gptme

0.3%
4k
CLI tool for terminal agent workflows
Created 2 years ago
Updated 21 hours ago
Feedback? Help us improve.