aicoolies logo

OpenSpec

Spec-driven development for AI coding assistants

Share
open-sourceOpen Source
Visit Website →

OpenSpec is an open-source spec-driven development framework by Fission-AI for AI coding assistants. It adds a lightweight spec layer so developers and AI agents agree on what to build before any code is written. OpenSpec organizes changes in dedicated folders for proposals, specs, design docs, and tasks, and works across 21+ AI coding tools including Claude Code, Cursor, Windsurf, Continue, Gemini CLI, GitHub Copilot, and Amazon Q — bringing structured planning to agentic development.

OpenSpec is an open-source spec-driven development (SDD) framework by Fission-AI that formalizes how developers collaborate with AI coding assistants. Instead of ad-hoc prompting that leaves intent ambiguous, OpenSpec adds a lightweight spec layer so you and your AI agents agree on what is being built before any code is written. The framework organizes every change in dedicated folders for proposals, specs, design notes, and tasks — turning AI-assisted development from a series of one-off conversations into a reviewable, version-controlled workflow.

The key concept that makes OpenSpec practical for real codebases is the delta spec: rather than restating an entire system specification for each change, delta specs describe only what is changing. This approach makes OpenSpec a natural fit for brownfield development where most work involves extending or refactoring existing systems rather than greenfield builds. Workflows are deliberately fluid with no rigid phase gates, so developers can create artifacts in any order that matches how they actually think about a problem. The propose workflow generates a complete change proposal — design, specs, and tasks — from a single request.

OpenSpec is distributed as a CLI tool that integrates with 21+ AI coding assistants out of the box, including Claude Code, Cursor, Windsurf, Continue, Gemini CLI, GitHub Copilot, Amazon Q Developer, Cline, Aider, and more. Running openspec init configures the selected tool using your active profile and chosen workflow, so each AI assistant reads specs in a consistent format. The project is developed in the open on GitHub under the Fission-AI organization and is freely available for individual developers and teams adopting agentic development practices.

Pricing

Free / Open Source

Platforms

CLI tool; generates OpenAPI specs from code

Categories

Tags

Use Cases

Alternatives

Related Tools

Hermes Agent logo

Hermes Agent

Top Pick

Open-source AI agent framework with persistent memory, reusable skills, tools, and messaging gateways

Hermes Agent is an open-source AI agent framework with persistent memory, reusable skills, 40+ tools, cron jobs, and messaging gateways.

open-sourceOpen Source
BeeAI Framework logo

BeeAI Framework

Python and TypeScript framework for production multi-agent systems

BeeAI Framework is an Apache-2.0 toolkit for building production-ready AI agents and multi-agent systems in Python and TypeScript. Its docs cover agents, tools, RAG, memory, workflows, backend providers, serving, and A2A/MCP integration surfaces, making it a vendor-neutral option for teams comparing LangGraph, CrewAI, Mastra, and related agent runtimes.

open-sourceOpen SourceTelemetry
Superserve logo

Superserve

Open-source Firecracker sandboxes for long-running AI agents

Superserve is an open-source sandbox infrastructure layer for AI agents that need durable computers instead of short-lived shells. It runs isolated Firecracker microVMs, supports pause, resume, snapshot, fork, preview URLs, MCP connectivity, SDK/API control, Docker workloads, and self-hosting, while the hosted service adds pay-as-you-go agent sandboxes for teams.

open-sourceOpen Source

Anthropic Agent Skills

Official Claude Agent Skills examples, spec, and plugin marketplace for reusable agent capabilities

Anthropic Agent Skills is Anthropic's official reference repo and Claude Code plugin marketplace for reusable Skill folders. It packages example SKILL.md workflows, document skills, a Claude API skill, templates, and the Agent Skills spec so teams can turn repeatable instructions, scripts, and resources into on-demand Claude capabilities instead of copying prompts across sessions.

freeTelemetry
agmsg logo

agmsg

Cross-agent messaging for CLI coding agents

agmsg is an MIT-licensed Bash and SQLite messaging layer for CLI coding agents. It lets Claude Code, Codex, Gemini CLI, GitHub Copilot CLI, Antigravity, OpenCode, Hermes, and other terminal agents exchange messages through a shared local database instead of relying on a human copy-paste relay. It is intentionally not MCP, not a broker, and not a subagent framework.

open-sourceOpen Source
eve vercel

eve by Vercel

Filesystem-first framework for durable AI agents

Eve is Vercel's filesystem-first TypeScript framework for building durable AI agents as ordinary project files. It combines Markdown instructions and skills, typed tools, channels, connections, subagents, schedules, sandboxes, and evals with Vercel's agent runtime so teams can ship deployable agents without hand-rolling orchestration. The current beta fits Vercel-native backend agent projects.

open-sourceOpen Source