# Openspec

**Canonical:** https://apis.io/providers/openspec/  
**Website:** https://openspec.dev  
**APIs profiled:** 0

OpenSpec (by Fission-AI) is an open-source, lightweight spec-driven development (SDD) framework for AI coding assistants. It adds a durable spec layer so you and your coding agent agree on what to build before any code is written: each change gets its own folder with a proposal, specs, design, and tasks, following a propose - apply - archive workflow. OpenSpec is a CLI and agent contract (installed via npm, no API keys or MCP required) that works with 30+ AI tools including Claude Code, Cursor, Windsurf, and Copilot via slash commands. A Y Combinator company, OpenSpec has 60k+ GitHub stars and is building Workspaces for teams needing multi-repo planning and collaboration.

## Kin Score — 16.2 / 100 (emerging)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 16.2).

| Facet | Score |
|---|---|
| Discoverability | 57.4 |
| Contract Quality | 0.0 |
| Governance | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 18.4 |
| Developer Ergonomics | 40.5 |
| Commercial Clarity | 0.0 |
| Access Clarity | 0.0 |

## Agent readiness — 0.0 (human-only)

| Dimension | Value |
|---|---|
| Spec Presence | no |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | no |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Open access — onboarding: open, pricing: unknown, trial: no (confidence: medium).

## Security (1)

- **Openspec Domain Security** — TLSv1.3

## Tags

Spec-Driven Development, AI Coding Assistants, Developer Tools, CLI, Specifications, Context Engineering, Open-Source, Coding Agents

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/openspec/). Scores are computed from the provider's own public artifacts under a published rubric.