# GSD Core — AI Coding Tool Review & Pricing

> GSD Core ("Git. Ship. Done.") is a light-weight meta-prompting, context-engineering and spec-driven development system for AI coding agents. It runs each milestone through a Discuss, Plan, Execute, Verify, Ship loop and pushes heavy research, planning and execution into fresh-context subagents to avoid context rot in the main session.

Source: https://ai.dosa.dev/tools/gsd-core · Updated Nov 8, 2026 · Category: Developer Productivity & Workflow · Published by dosa.dev

## At a glance

- **Tool**: GSD Core
- **Company**: Open GSD
- **Category**: [Developer Productivity & Workflow](https://ai.dosa.dev/category/productivity)
- **Pricing model**: Open Source
- **Official website**: https://opengsd.net

## Key features

- Five-step phase loop: Discuss, Plan, Execute, Verify, Ship
- Heavy work runs in fresh-context subagents, executed in parallel waves
- `STATE.md` and `CONTEXT.md` artifacts that survive session boundaries
- Verify step walks through what was built and writes fix plans before a phase is done
- One installer (`npx @opengsd/gsd-core@latest`) for Claude Code, OpenCode, Antigravity CLI, Kimi CLI, Kilo, Codex, Copilot, Cursor, Windsurf and more
- `/gsd-new-project` for greenfield work and `/gsd-onboard` for existing codebases

## Pricing

**Model**: Open Source

Free and open-source under the MIT License; it runs inside the coding agent you already use, so your only costs are that agent's subscription or API usage.

## Who it is for

- **Best for**: Developers running multi-phase features with a coding agent who want structured planning, verification and clean context without adopting a new IDE.
- **Not ideal for**: Quick one-off edits, or users who want minimal token use, since the subagent-heavy workflow trades extra tokens for quality.

## Verdict

A popular, actively shipped spec-driven workflow layer that works across most coding agents; worth trying if context rot is hurting long agent sessions.

## Recent updates

v1.20.1 was released on Nov 5, 2026, two days after v1.20.0, fixing fork-probe cache handling and installer path rewriting for nested config directories across runtimes.

## Frequently asked questions

### Is GSD Core free?

Yes - GSD Core is Open Source. Free and open-source under the MIT License; it runs inside the coding agent you already use, so your only costs are that agent's subscription or API usage.

### Is GSD Core open source?

Yes - GSD Core is open source. Free and open-source under the MIT License; it runs inside the coding agent you already use, so your only costs are that agent's subscription or API usage.

### Who is GSD Core best for?

Developers running multi-phase features with a coding agent who want structured planning, verification and clean context without adopting a new IDE.

### Who is GSD Core not ideal for?

Quick one-off edits, or users who want minimal token use, since the subagent-heavy workflow trades extra tokens for quality.

### What are the best GSD Core alternatives?

The closest GSD Core alternatives on ai.dosa.dev are Pieces for Developers, agenttrace, Vibe Kanban - all listed under Developer Productivity & Workflow.

### Who makes GSD Core?

GSD Core is developed by Open GSD. It is listed in the Developer Productivity & Workflow category on ai.dosa.dev.

## Top alternatives

- [Pieces for Developers](https://ai.dosa.dev/tools/pieces-for-developers) (Paid) — Developers who work across multiple tools, IDEs, and environments and need to maintain a persistent, searchable history of code snippets, research, and workflow context.
- [agenttrace](https://ai.dosa.dev/tools/agenttrace) (Open Source) — Developers and teams needing to monitor and debug the efficiency, cost, and health of AI coding agents across multiple workflows.
- [Vibe Kanban](https://ai.dosa.dev/tools/vibe-kanban) (Open Source) — Software engineers who use multiple AI coding agents and need a structured environment to manage, plan, and review their output in parallel.
- [ai-memory](https://ai.dosa.dev/tools/ai-memory) (Open Source) — Developers or teams using multiple AI coding agents who need consistent context and project history persistence across different tools, machines, and sessions.
- [smolvm](https://ai.dosa.dev/tools/smolvm) (Open Source) — Running isolated coding agent sandboxes, untrusted code, and persistent local development environments that require a real Linux kernel boundary.
- [coop](https://ai.dosa.dev/tools/coop) (Open Source) — Running autonomous AI coding agents that require broad system access while maintaining a strong security boundary for the host machine.
- Full alternatives guide: https://ai.dosa.dev/tools/gsd-core/alternatives