ClaudeScope

What is ClaudeScope?

ClaudeScope is a small tool from the Fervon studio that makes your Claude Code history searchable. Claude Code stores transcripts as raw .jsonl files under ~/.claude/projects, and the built-in resume command shows IDs without content or search. Running npx claudescope-cli finds that folder, streams the transcripts into memory, tolerating corrupt lines, and opens a dashboard at 127.0.0.1:4317. From there you can run full-text search over prompts, responses and tool calls, open a session to read the whole conversation, and see sessions, messages, tokens, API cost per model and how much prompt caching saved. Extra views include a day-by-hour heatmap, a daily timeline, typical session cost at median and p90, and a Wrapped card for a yearly summary. It also reads sessions from Codex, Cursor, Aider, Gemini and Copilot CLI. The tool is free, MIT licensed, read-only and makes no network requests or API calls.

Use cases

• Search old Claude Code conversations
• Track token and API spend by model
• See how much prompt caching saved
• Review usage habits by day and hour
• Export session data to Markdown, CSV or JSON
• Merge usage reports across team machines

Who it's for

• Claude Code users
• Developers
• Engineering leads

Why use ClaudeScope

• You can find the session where a bug was fixed without scrolling through a list of IDs.
• Spend and cache savings become visible even when your subscription hides per-session numbers.
• Everything stays on your machine: it is read-only, runs on localhost and needs no API key.
• Nothing to install and no dependencies, so trying it takes a single command.
• A free MIT license means you can inspect the code and use it at work.

ClaudeScope features

• Full-text search over prompts, responses and tool calls with highlighting
• Session reader that opens a whole conversation in place
• Usage overview of sessions, messages, tokens and cost
• Cost per model and cache savings display
• Activity heatmap by day and hour plus daily timeline
• Median and p90 figures for a typical session
• Weekly plain-text report through the --weekly flag
• Local-only server bound to 127.0.0.1
• Reads Codex, Cursor, Aider, Gemini and Copilot CLI sessions too
• Export to Markdown, CSV or JSON

ClaudeScope integrations

• Claude Code
• Codex
• Cursor
• Aider
• Gemini CLI
• GitHub Copilot CLI

How to get started with ClaudeScope

1. Run npx claudescope-cli in a terminal; nothing needs to be installed first.
2. The tool locates your Claude Code data folder automatically.
3. It streams every transcript into memory, skipping corrupt lines, without changing the files.
4. Your browser opens a dashboard on 127.0.0.1:4317 where you search, read sessions and view usage charts.
5. Optionally schedule claudescope --weekly with cron to print a weekly report.

ClaudeScope limitations

• Reads transcript files on the machine where you run it
• Needs Node 18 or newer
• Showing real cost is an opt-in setting rather than the default

ClaudeScope pricing

ClaudeScope is open source, so you can use and self-host it for free.

ClaudeScope plans

• ClaudeScope

  Free

  • No paid tier
  • MIT license
  • Runs with npx claudescope-cli

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.

ClaudeScope alternatives

The main ClaudeScope alternatives listed on Debuly are SpecStory, claude-mem, OpenLIT, agenttrace, LeanCTX and AIPM. The table compares pricing and platforms; order is A–Z.

1. Ag

   agenttrace

   Local-first Rust terminal app that audits AI coding agent sessions for cost, tokens, latency and failures from logs on disk.

   Developer platformsCodingProductivity
   Open sourceVisit agenttrace (official site)
2. 

   AIPM

   Package registry and command-line installer for versioned agent skills that install into Claude Code, Codex and Cursor projects.

   Developer platformsCodingProductivity
   Visit AIPM (official site)
3. 

   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)
4. 

   LeanCTX

   Open-source context gateway that trims what AI coding tools read, caches repeat reads and logs what each agent was given.

   Developer platformsCodingAutomation and agents
   FreemiumVisit LeanCTX (official site)
5. 

   OpenLIT

   Open-source, OpenTelemetry-native platform for tracing, evaluating and guarding AI agents, with cost and GPU monitoring

   Developer platformsCodingAutomation and agents
   Open sourceVisit OpenLIT (official site)
6. 

   SpecStory

   Saves AI coding agent conversations as local Markdown files, with a free CLI and extensions plus a cloud to search, share and mine them.

   CodingDeveloper platformsProductivity
   FreemiumVisit SpecStory (official site)

ClaudeScope 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 fervon.dev · fetched 23 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.