TrendWhat rose on GitHub, every day at 07:30 KST · 한국어

GitHub · as of November 8, 2026 · View on GitHub →

Fission-AI/OpenSpec

Spec-driven development framework

+676 stars in 7 days

Documenting agreement with AI coding assistants before writing code

Instructing an AI to write code immediately after deciding on a feature can lead to unexpected results. This tool organizes requirements and design proposals into Markdown files before any code is written, ensuring that humans and AI are aligned. OpenSpec is a tool that adds specification specs readable by AI coding assistants to your project.

The flow of spec-based development

OpenSpec divides the development process into four stages: explore, propose, apply, and archive. First, the /opsx:explore command is used to explore ideas, where the AI analyzes the current codebase and suggests the optimal approach. Next, using /opsx:propose generates a change folder, and the proposal, requirements specification, technical design, and task list are written as Markdown files. At this stage, developers can review and modify the plan written by the AI. Finally, executing /opsx:apply allows the AI to implement the code according to the task list, and completed changes are stored in the archive via /opsx:archive.

Sharing plans across teams

This tool is useful not only for personal projects but also in team environments. When developing features that span multiple repositories, the plan is stored in a separate repository called a 'store'. This store becomes a single source of truth readable by the entire team and all AI agents through git push. The platform team owns the requirements specification, and the product team can reference it in read-only mode, preventing the problem of scattered wiki documents. Since the store feature is currently in beta, it is recommended to start by referring to the guide.

Installation and initial setup

To use OpenSpec, a version of Node.js 20.19.0 or higher is required. On macOS or Linux, it can be installed via Homebrew by running the brew install openspec command. If using npm, run npm install -g @fission-ai/openspec@latest. This process can also be delegated to an AI coding assistant; selecting one of the 30+ supported tools automatically sets the slash command format suitable for that tool.

Pre-use considerations

This tool yields the best results when used with models that have high reasoning capabilities. The README recommends Codex 5.5 and Opus 4.7 for both planning and implementation. It is also important to clear the context window before starting implementation, and context hygiene must be maintained during the session. OpenSpec collects anonymous usage statistics, but only records command names and versions, not personal information or file contents. It is automatically disabled in CI environments and can be manually disabled via configuration files or environment variables if desired. The license is MIT, and when contributing, an OpenSpec change proposal must be written before adding new features or structural changes.

Written by AI from this repository's README on October 15, 2026. For the facts, the original on GitHub is the reference.

By the numbers

GitHub trending history
5 days between Jun 19, when Trend began recording, and Nov 8, 2026 · first on Jun 27 · best daily rank #8 (Sep 18)

Read from GitHub, as of November 8, 2026.

Language
TypeScript
Topics
ai · context-engineering · engineering · planning · prd · sdd · sdlc · spec
Stars
74,275
Stars gained in 7 days
+676
Contributors
150
Forks
5,097
Latest release
v1.16.1 · November 7, 2026
Commits
1,035
Last commit
November 7, 2026
Open issues
141
Open pull requests
59

Related repositories

View on GitHub → · Homepage

README badge

trend.ondo.sh · GitHub daily trending #8 · September 18, 2026

The badge above shows the highest this repository has ranked on GitHub's daily trending since June 19, 2026, and the day it did. Paste the Markdown below into your README. The badge opens this page, and it updates by itself when the repository climbs higher.

[![trend.ondo.sh](https://trend.ondo.sh/github/r/Fission-AI--OpenSpec/badge.en.svg)](https://trend.ondo.sh/github/r/Fission-AI--OpenSpec/en.html)