logo

Fission-AI/OpenSpec

Spec-driven development (SDD) for AI coding assistants.

View on GitHub ↗Jump to charts ↓

Fission-AI/OpenSpec has 72k+ stars and 4.5k+ forks on GitHub, is written in TypeScript, and was last pushed on Oct 17, 2026. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 1 hour ago
Type:FrameworkCategory(s):AI Coding AgentsMCP Servers, Agent Skills & PromptsAI Agents & LLM Apps
Added to GitGenius on August 30th, 2026
Created on August 5th, 2025
Open Issues & Pull Requests: 193 (+0)
GitHub issues: Enabled
Number of forks: 4,945
Total Stargazers: 72,334 (+3)
Total Subscribers: 287 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 2.6 days
Mean response time: 30.0 days
90th percentile: 139.8 days
Tracked items: 690

Most active contributors

Sign in to see contributor activity.
Sign in

Related repositories by overlapping contributors

Maintainer activity

3 people did triage or write work on this repository in the last 12 months.

Counts unlabeled, assigned, unassigned, milestoned, demilestoned, locked, unlocked over the last 12 months. These are issue and pull request events that require triage or write permission. Commits and code review are not counted. labeled and renamed are excluded because GitHub issue forms record the issue author as the actor. Figures from October 18, 2026. This count is not comparable across projects: each project's automation decides which of these events a person emits. How this is counted.

How this project is maintained

About 8% of issues opened in the past year have never received a reply. 84% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Work labelled "backlog" is answered fastest, typically in about 19 hours, while "design-review" waits about 5 days. Almost all tracked open issues have seen activity in the last three months. 82% of issues opened in the past year have been closed, leaving a working backlog.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 130
New in 7 days: 14
Closed in 7 days: 12
Avg open age: 80 days
Stale 30+ days: 76
Stale 90+ days: 4

Recent activity

Opened in 7 days: 13
Closed in 7 days: 12
Comments in 7 days: 4
Events in 7 days: 20

Top labels

  • design-review (104)
  • bug (83)
  • enhancement (36)
  • backlog (25)
  • needs-triage (13)
  • P0-critical (6)
  • future-roadmap (6)
  • integration (6)

Most active issues this week

Sign in to see which issues are moving.
Sign in
Explore full issue details

Detailed Description

OpenSpec is a framework for spec-driven development that enables AI coding assistants to work from detailed specifications.

The tool addresses the challenge of directing AI assistants toward consistent, well-planned code generation by establishing a specification-first workflow. Rather than relying on conversational prompts alone, OpenSpec structures development around formal specifications that define requirements, architecture, and implementation details upfront. This approach provides AI assistants with clear context and constraints, reducing ambiguity and enabling more reliable code generation aligned with intended design.

Teams adopting OpenSpec should consider it when they want to integrate AI coding assistants into a more structured development process. It suits projects where specifications can be written before implementation and where maintaining consistency across AI-generated code matters. The framework is particularly relevant for teams already practicing specification-driven methodologies or those seeking to impose discipline on AI-assisted development workflows.

The project shows active development with regular commits addressing core functionality and user-facing improvements. Work spans both the framework's specification handling capabilities and the developer experience of the tooling. The maintainers are responsive to issues and incorporate feedback into the codebase at a steady pace.