SpecStory

What is SpecStory?

SpecStory records the prompts and decisions from your AI coding sessions so you can reread them, reuse them and share them. Extensions for Cursor and for VS Code with GitHub Copilot write each conversation to Markdown files in your project, and a command-line tool captures terminal agents, exports earlier sessions and can resume work. Optional SpecStory Cloud collects synced sessions from every project and machine, lets you search them, share a session through a public link with control over which exchanges show, and exposes an API. Paid Cloud plans add analytics, a dashboard covering activity, conversation depth, a grade for how well each opening prompt was specified, and estimated spend. They also add skills: the cloud mines your history for repeatable workflows and lets you install them as agent skills for tools such as Claude Code, Codex and Cursor. You can use the extensions and the CLI at no cost, the CLI's source is open under the Apache 2.0 license, and Cloud offers a free plan. The vendor does not publish prices for the Pro or Team plans on the page, so check the official site for current figures. A separate product, RunStory, is in private alpha.

Use cases

• Save AI chat history as Markdown
• Search past coding agent sessions
• Share a session with teammates
• Resume sessions across agents
• Track AI coding activity and spend
• Turn repeated workflows into agent skills

Who it's for

• Developers using AI agents
• Engineering teams
• Open source maintainers
• Engineering leaders

Why use SpecStory

• Conversations that would otherwise vanish become files in your repository that you can read and reference in later prompts.
• The extensions and CLI cost nothing, and local capture works without a Cloud account.
• Cloud search helps you find a past prompt or decision across projects and machines.
• Sessions stay private unless you enable sharing, and you pick which projects sync.
• Analytics and skills turn your session history into insight about spend and reusable workflows.

SpecStory features

• Markdown capture of agent conversations
• Extensions for Cursor and VS Code with GitHub Copilot
• CLI for terminal agents with sync, export and resume
• Cloud search across projects and machines
• Public-link sharing with visibility controls
• Cloud API for projects and sessions
• Analytics dashboard with Spec Score and estimated spend
• Skills mined from synced sessions
• Install skills into Claude Code, Codex and Cursor
• Local-only mode that keeps sessions off Cloud

SpecStory integrations

• Cursor
• VS Code
• GitHub Copilot
• Claude Code
• Codex
• Antigravity
• Droid
• Qwen Code

How to get started with SpecStory

1. Install the SpecStory extension in Cursor or VS Code, or install the CLI.
2. Work with your coding agent as usual while sessions are written to .specstory/history as Markdown.
3. Reference a saved file in a later prompt to give an agent the earlier context.
4. Log in to Cloud and sync chosen projects to search and share sessions.
5. On a Pro or Team plan, review analytics and install skills mined from your history.

SpecStory limitations

• Analytics and skills depend on a paid Cloud plan
• Skills need a Pro or Team plan and a Cloud login
• Reusing a session means referencing its Markdown file; it is not written back into the editor's chat database
• RunStory is in private alpha

SpecStory pricing

Yes, SpecStory has a free plan.

SpecStory plans

• Free

  Free

  extensions, CLI and a free Cloud plan

  • Local Markdown capture
  • Open source CLI
  • Cloud sync and search
  • Public-link sharing

• Pro

  Price on vendor site

  • Analytics dashboard
  • Skills mined from your sessions

• Team

  Price on vendor site

  • Skills mined from your sessions

Plans as listed on the official pricing page on 24 Oct 2026. Prices can change and may vary by country or exclude tax. Check the official pricing page.

SpecStory alternatives

The main SpecStory alternatives listed on Debuly are Langfuse, Helicone, Cursor, Claude Code, Cline and claude-mem. The table compares pricing and platforms; order is A–Z.

1. 

   Claude Code

   Anthropic's coding agent that fixes bugs, writes tests and runs migrations from your terminal, IDE, desktop app, web or Slack.

   CodingAutomation and agentsDeveloper platforms
   PaidVisit Claude Code (official site)
2. 

   claude-mem

   Open-source memory engine that saves what your coding agent does, summarizes it and brings it back in later sessions.

   CodingDeveloper platformsProductivity
   FreemiumVisit claude-mem (official site)
3. 

   Cline

   Open-source AI coding agent for VS Code, JetBrains, the terminal and desktop that edits files and runs commands with your approval.

   CodingDeveloper platformsAutomation and agents
   Open sourceVisit Cline (official site)
4. 

   Cursor

   AI code editor and coding agent with cloud agents, Bugbot code review and multi-provider models, sold with Grok and X plans.

   CodingAutomation and agentsDeveloper platforms
   FreemiumVisit Cursor (official site)
5. 

   Helicone

   Open-source LLM observability and AI gateway that logs requests, tracks cost and latency, and routes to 100+ models through one API.

   Developer platformsCoding
   FreemiumVisit Helicone (official site)
6. 

   Langfuse

   Open-source LLM observability and evaluation platform for tracing agents, managing prompts and scoring outputs.

   Developer platformsAutomation and agentsCoding
   FreemiumVisit Langfuse (official site)

SpecStory FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from specstory.com · fetched 24 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.