Skip to main content

AI Ledger

See what your coding agents did, what it cost, and where they got stuck.

AI Ledger reads your Claude Code and Codex transcripts and turns them into seven local dashboards. Your agents delete old transcripts; AI Ledger keeps every line.

Tour of the pages

Quick start

uvx ai-ledger    # opens http://127.0.0.1:8765/ in your browser

Needs uv. Runs on macOS and Linux. Your data stays on your machine (see Privacy).

What you get

Page Shows
Activity What got done per day or week, by project, and what needs your attention.
Cost Estimated spend at API list prices, per project, model and session, compared with your plan.
Context How full the context window gets, how fast it grows, and what fills it.
Errors Failed tool calls by type, the time they cost, and a fix to paste into CLAUDE.md or AGENTS.md.
Limits Each plan limit window, what used it, and a forecast to its reset.
Insights How Claude Code's /insights judged your sessions.
Live Every active session as it runs, sorted by who needs you first.
Project One project across all of the above, opened from the Page link on the navigation's project filter, its sheet, or its name in the command palette.

Press Cmd+K to jump anywhere, for example >errors #myproject #7d. Right-click a project, session, tool or error type for its actions, such as copying a session's resume command. Every page works by keyboard and screen reader, and each chart has a data table.

The user guide describes each page in detail.

ActivityCost
ErrorsLimits
InsightsLive

Install

uv tool install ai-ledger
ai-ledger                   # serve on http://127.0.0.1:8765/ and open it
uv tool upgrade ai-ledger   # new version and new prices

The first start reads every transcript, about 4 minutes for 3.4 GB. After that, the app picks up new lines every 60 seconds.

Option Default
--port 8765
--no-open off (opens the browser)
--projects ~/.claude/projects
--codex ~/.codex
--usage-data ~/.claude/usage-data
--db ~/Library/Application Support/ai-ledger/ai-ledger.duckdb (macOS), ~/.local/share/ai-ledger/ai-ledger.duckdb (Linux)

With the app stopped, ai-ledger ingest reads new lines once and ai-ledger rebuild recomputes the derived tables. After an upgrade that asks for it, run ai-ledger rebuild once.

To set your own model prices or plan prices, or to hide more automated projects, see Configuration.

Privacy

  • The server listens on 127.0.0.1 only, and refuses requests that another site makes from your browser.
  • The store keeps every transcript line, including any secrets that appeared in a session. Only your user can read it. Do not share it.
  • On macOS, the Limits page sends your Claude Code OAuth token from the Keychain to Anthropic's usage endpoint every 5 minutes. The token goes nowhere else and is never stored or logged. On Linux, Limits estimates from transcripts.
  • Live's Full text puts transcript content on screen, secrets included. Turn it off before you share your screen.
  • Your browser loads the font from Google Fonts. No transcript data goes with it.

Contributing

See CONTRIBUTING.md.

License

MIT

Metadata

Release files for ai-ledger 0.4.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ai-ledger 0.4.0
File Size Uploaded Provenance Actions
ai_ledger-0.4.0.tar.gz 427.9 kB With provenance Details for ai_ledger-0.4.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for ai-ledger 0.4.0
File Interpreter ABI Platform Actions
ai_ledger-0.4.0-py3-none-any.whl Python 3 none any Details for ai_ledger-0.4.0-py3-none-any.whl

Total release size: 874.1 kB

Release files / ai_ledger-0.4.0.tar.gz

Download URL ai_ledger-0.4.0.tar.gz
Size 427.9 kB
Tags Source
SHA-256 checksum
How to use checksums
260f984dba4fd21b3d227bfa55aaaf80408e9479a733b52b3a5b6fd7553a8c6c
BLAKE2b-256 checksum
How to use checksums
fe1944a9962528e6272a178bc45be1a706d064f8676c382e04189bf454e0dc56
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 15, 2026.

Transparency log

Release files / ai_ledger-0.4.0-py3-none-any.whl

Download URL ai_ledger-0.4.0-py3-none-any.whl
Size 446.2 kB
Tags Python 3
SHA-256 checksum
How to use checksums
e3ff59ffde5034a6d03d57fba3f91b86a25d3bdedc4db6cacd8ac3fda78f600e
BLAKE2b-256 checksum
How to use checksums
57475c399d67749f1191e4c2c92aa3a8b957b62585ae8167b474e27195bdb5ac
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 15, 2026.

Transparency log

Security for ai-ledger 0.4.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for ai_ledger-0.4.0.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 15, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page