sopify  by evidentloop

AI coding workflow protocol for resumable, traceable development

Created 5 months ago
288 stars

Top 91.0% on SourcePulse

GitHubView on GitHub
Project Summary

Summary

Sopify provides a protocol layer for AI coding, addressing rework and lost context by making AI-assisted development resumable and traceable. It ensures that plans, decisions, and verification evidence are stored as project files within the repository, allowing developers to seamlessly continue work across different hosts and machines. This benefits users who require auditable development processes and consistent AI assistance.

How It Works

Sopify integrates with AI coding hosts like Codex, Claude, Qoder, and Copilot, enforcing a "plan before code" methodology. When requirements are unclear, Sopify prompts the AI to stop, plan, and score tasks before generating code. All generated plans, design decisions, and verification receipts are persistently stored in the .sopify/ directory and tracked by git. This enables users to open the same repository on any supported host and automatically resume work from the last checkpoint, maintaining context and auditability.

Quick Start & Requirements

  • Install: curl -fsSL https://github.com/evidentloop/sopify/releases/latest/download/install.sh | bash -s -- --target codex:en-US (See Installation section for other hosts and Windows PowerShell).
  • Prerequisites: Integrates with existing AI coding hosts; no specific non-default hardware or software dependencies mentioned beyond standard shell environments for installation.
  • Usage: Initiate or resume managed workflows using the ~go command within the host environment.
  • Links: Quick Start, Installation, Getting Started.

Highlighted Details

  • Cross-Host Resumability: Seamlessly continue AI coding sessions across different hosts (Codex, Claude, Qoder, Copilot) without losing context.
  • Git-Tracked Artifacts: Plans, decisions, and verification records are stored in .sopify/ and managed via git, creating a persistent, auditable development history.
  • Decision Traceability: Every code change is linked back to a specific requirement, design decision, and review, enhancing accountability.
  • Workflow Consistency: Ensures uniform AI coding rules and processes are applied irrespective of the host environment.

Maintenance & Community

  • Contribution guidelines are available via ./CONTRIBUTING.md.
  • No explicit community channels (e.g., Discord, Slack) or sponsorship details are provided in the README snippet.
  • Version history is indicated by a badge, suggesting regular updates.

Licensing & Compatibility

  • Code & Config: Apache 2.0 License.
  • Documentation: CC BY 4.0 License.
  • Compatibility: Apache 2.0 is permissive for commercial use. CC BY 4.0 requires attribution for documentation.

Limitations & Caveats

  • Copilot support is currently designated as "BASELINE_SUPPORTED" with planned payload uplifts, potentially indicating a less mature integration compared to other supported hosts.
  • Different tiers of host support (PROTOCOL_VERIFIED vs. BASELINE_SUPPORTED) are noted, implying varying levels of feature completeness across integrations.
Health Check
Last Commit

2 days ago

Responsiveness

Inactive

Pull Requests (30d)
4
Issues (30d)
2
Star History
120 stars in the last 30 days

Explore Similar Projects

Feedback? Help us improve.