
Rudel
Rudel is an analytics layer for Claude Code and Codex that automatically ingests session transcripts to power dashboards and “Wrapped”-style insights on usage, performance, and cost.
https://app.rudel.ai/wrapped?ref=producthunt

Product Information
Updated:May 19, 2026
What is Rudel
Rudel is a tool for ingesting, storing, and analyzing AI coding-agent session data—especially Claude Code and Codex—to help teams understand how coding agents are actually being used. It provides a dashboard of metrics such as token usage, session duration, model mix, activity patterns, and outcomes (e.g., success/commit rates), and can generate shareable “Claude Code Wrapped” summaries. Rudel is typically used via a CLI plus a web dashboard (e.g., app.rudel.ai), and it’s positioned as a practical analytics layer rather than a benchmark or evaluation suite.
Key Features of Rudel
Rudel is an analytics tool for Claude Code and OpenAI Codex that ingests full coding-agent session transcripts and related metadata to produce a dashboard of insights such as token usage, session duration, activity patterns, model mix, and outcomes (e.g., success/commit rates). It can be enabled to auto-upload sessions when a coding-agent run exits, and it emphasizes that transcripts may include sensitive material (code, prompts, tool/file/command outputs, URLs, and secrets), so it should only be used in environments where uploading that data is acceptable.
Session transcript ingestion: Captures and uploads full Claude Code/Codex session transcripts plus metadata for analysis; includes prompts, tool output, file contents, command output, URLs, and potentially secrets.
Usage and cost analytics dashboard: Provides rollups like input/output/total tokens, spend, sessions, active days, average/longest session length, and other usage metrics.
Productivity and outcome metrics: Tracks indicators such as commit rate and success rate to help teams understand how often sessions translate into code changes and successful outcomes.
Model and workflow breakdowns: Surfaces patterns like Claude vs. Codex usage share, commands used, skills used (e.g., refactor), sub-agent usage, and repos touched.
CLI-based setup and automation: Installs and runs via CLI (e.g., login, enable) with the ability to auto-upload sessions when Claude Code/Codex exits.
Privacy-conscious enablement guidance: Explicitly warns users to enable only on projects/environments they’re comfortable uploading due to sensitive transcript contents.
Use Cases of Rudel
Engineering team governance and reporting: Track spend, token consumption, and session outcomes across repos to inform budgeting, policy, and ROI discussions for coding-agent adoption.
Developer productivity and workflow optimization: Identify high-friction patterns (long sessions, low commit rate) and optimize prompts, tooling, and practices based on commands/skills/sub-agent usage.
Model evaluation and A/B comparisons: Compare Claude vs. Codex usage patterns and outcomes (success/commit rates, duration, tokens) to choose the best model for specific tasks.
Internal enablement and training: Use aggregated insights (common skills, workflows, activity patterns) to coach developers on effective agent usage and standard operating procedures.
Ops/FinOps for AI tooling: Monitor cost drivers (tokens, long sessions, repo breadth) and set guardrails for AI usage in cost-sensitive environments.
Pros
Clear, quantifiable visibility into coding-agent usage (tokens, time, spend) and outcomes (commit/success rates).
CLI-based enablement with auto-upload makes it easy to instrument workflows with minimal ongoing effort.
Rich breakdowns (models, skills, commands, repos, sub-agents) support actionable optimization and comparisons.
Cons
High sensitivity risk: full transcripts/metadata may include source code, secrets, and other confidential data.
Requires comfort with uploading session data to a service; may be unsuitable for regulated or locked-down environments without strict controls.
How to Use Rudel
1) Install the Rudel CLI: Install Rudel globally with npm so you can authenticate and enable session uploads: `npm install -g rudel`.
2) Log in (authenticate): Run `rudel login` and complete the browser-based authentication flow.
3) Enable automatic session uploads for Claude Code / Codex: Run `rudel enable`. This registers a Claude Code hook that runs when a session ends (on exit) and uploads the session transcript to Rudel.
4) Use your coding agent normally: Run Claude Code or Codex sessions as usual. When you exit a session, Rudel’s hook will auto-upload the transcript and related metadata.
5) View analytics in the Rudel dashboard: Open the hosted dashboard at `app.rudel.ai` to see insights such as token usage, session duration, activity patterns, model usage, and more (e.g., a “Claude Code Wrapped” summary).
6) Review data-sensitivity guidance before enabling in new environments: Rudel uploads full coding-agent session data, which may include sensitive material (source code, prompts, tool output, file contents, command output, URLs, and secrets). Only enable Rudel in projects/environments where you’re comfortable uploading that data.
7) Understand hosted-service privacy positioning (if using app.rudel.ai): If you use the hosted service at `app.rudel.ai`, Rudel states they do not have access to personal data contained in uploaded transcripts and cannot read that data.
Rudel FAQs
Rudel is a product that ingests, stores, and analyzes Claude Code and Codex session transcripts, and can generate a “Claude Code Wrapped” usage summary.
Rudel Video
Popular Articles

Nano Banana SBTI: What It Is, How It Works, and How to Use It in 2026
Apr 15, 2026

Atoms Review — The AI Product Builder Redefining Digital Creation in 2026
Apr 10, 2026

Kilo Claw: How to Deploy and Use a True "Do‑It‑For‑You" AI Agent(2026 Update)
Apr 3, 2026

OpenAI Shuts Down Sora App: What the Future Holds for AI Video Generation in 2026
Mar 25, 2026







