Back to directory

OSpec.ai

A spec-driven workflow framework for AI coding agents that turns a request into repository files tracking proposal, design, plan, tasks, review and verification evidence, so any assistant can resume the work.

OSpec.ai

OSpec brings spec-driven development and a repeatable plan-act-verify loop to AI coding agents such as Claude Code, Codex, Gemini and OpenCode. Instead of leaving requirements in chat history, it saves them as files in the repository, so a different assistant session can continue exactly where the previous one left off.

Its everyday flow, ospec change, moves one requirement through init, change and verify or finalize steps. A separate ospec goal mode handles larger or riskier work: the agent asks clarifying questions, writes an inspectable plan, implements it, runs tests, requests an independent review, updates project documentation, and continues until the result is proven. It installs as an npm package providing the ospec command.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.