Skip to main content

cc-transcript

Grep every Claude Code session you've ever run. The lossless Rust parser reads Claude Code's on-disk JSONL at 169 MB/s; the compiled CLI greps it and renders one line per event, 25 ms cold.

CI PyPI License PolyForm Noncommercial

Get started

uvx cc-transcript list

Every session is already on disk under ~/.claude/projects. list finds them newest first, and stats collapses one into a screenful:

Terminal running 'uvx cc-transcript stats' — one session summarized as counts, kinds, models, and tool names

Driving with an agent? Paste this:

/plugin marketplace add yasyf/cc-transcript
/plugin install cc-transcript@cc-transcript

The plugin's skill teaches Claude to answer "what did I ask you yesterday" from its own history, funneling through the CLI instead of reading raw JSONL.

No Claude Code? Point any agent at the CLI
Use `uvx cc-transcript` to investigate my Claude Code sessions: `list` finds
transcripts on disk, `stats` summarizes one, `grep` searches content, and `show`
renders one compact line per event. Start by listing my newest sessions and
summarizing the most recent one. Docs: https://yasyf.github.io/cc-transcript/

Use cases

Ask Claude what you asked Claude yesterday

Yesterday's session is a megabyte of JSONL, and pasting it into a chat blows the context window. Render the spine instead:

uvx cc-transcript show --signal --tail 20 ~/.claude/projects/<project>/<session>.jsonl

--signal keeps only the substantive user and assistant turns. One line per event, a few hundred tokens for the whole exchange. With the plugin installed, skip the command and ask Claude directly; its skill runs this funnel for you.

Find the session where you fixed that bug

The fix happened weeks ago, in one of a few hundred transcripts. Search them all:

uvx cc-transcript grep "TranscriptExpiredError" --project cc-transcript

Hits print under their transcript's path, each line carrying its raw event index; feed an index back into show --range to re-read the conversation around the fix. grep searches your newest 50 transcripts by default; --all takes it to every session on disk, and a no-match run exits 1 so it scripts cleanly.

Debug a token blowup from transcript evidence

A session burned through the context window and you want the culprit, not a guess. Rank the evidence:

uvx cc-transcript stats --per-file --project myapp

Each block reports text, thinking, and tool-io bytes plus per-tool call counts; the blowup stands out as an outsized tool io line. Then grep --tool <name> --with-result pins it to the exact calls.

Script it from Python

The CLI's funnel is four commands; your own tooling wants the events themselves. parse turns a path into a Transcript of typed lazy views, with the noise already dropped inside the engine:

from cc_transcript import NOISE_SPEC, discover, parse

transcript = parse(discover()[0], drop=NOISE_SPEC)
print(len(transcript.events), "events after the noise drop")

discover() lists every transcript on disk newest first, stream fans a whole corpus across the parse pool, and resolve finds one session by UUID. parse also reads OpenAI Codex CLI rollouts — hand it a path from ~/.codex/sessions and the same typed events come back. The getting-started guide builds this out to a composed filter and a sentiment score.

JSON output schema

show --json and grep --json emit JSONL, with one object per event. Each event uses the envelope {i, kind, meta, model, text, blocks, stop_reason, usage}; fields that do not apply to its kind are omitted. Every object in blocks has a type discriminator such as text, thinking, tool_use, tool_result, or fallback.

More in the docs

  • The Python library turns a transcript into typed lazy views, a composed filter, and a score in a dozen lines.
  • Filtering events covers composable clauses, specs, and the ready-made NOISE_SPEC.
  • Sentiment scoring buckets conversations and scores them around any inference engine.
  • Feedback mining runs detectors, confidence calibration, and LLM verdict passes over your corpus.
  • The Rust engine is the implementation — parsing, filtering, scoring, and mining — its correctness pinned by hand-owned literals and golden fixtures.
  • Codex rollouts make the parser two-provider: OpenAI Codex CLI sessions lower into the same typed events, with rollout discovery, subagent joins, and per-session lifecycle and token totals. list --provider codex finds them from the shell.
  • API reference documents the complete typed surface, from TranscriptEvent to SessionActivity.

Read the docs for the full guide. Licensed under PolyForm Noncommercial 1.0.0.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cc_transcript-14.16.1.tar.gz (12.2 MB view details)

Uploaded Source

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

cc_transcript-14.16.1-cp313-abi3-manylinux_2_28_x86_64.whl (28.0 MB view details)

Uploaded CPython 3.13+manylinux: glibc 2.28+ x86-64

cc_transcript-14.16.1-cp313-abi3-manylinux_2_28_aarch64.whl (27.7 MB view details)

Uploaded CPython 3.13+manylinux: glibc 2.28+ ARM64

cc_transcript-14.16.1-cp313-abi3-macosx_11_0_x86_64.whl (27.8 MB view details)

Uploaded CPython 3.13+macOS 11.0+ x86-64

cc_transcript-14.16.1-cp313-abi3-macosx_11_0_arm64.whl (27.6 MB view details)

Uploaded CPython 3.13+macOS 11.0+ ARM64

File details

Details for the file cc_transcript-14.16.1.tar.gz.

File metadata

  • Download URL: cc_transcript-14.16.1.tar.gz
  • Upload date:
  • Size: 12.2 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for cc_transcript-14.16.1.tar.gz
Algorithm Hash digest
SHA256 01e7ea4490d815f7ea75d3e66f21c85aad2895150c204a8309857ac749409ca7
MD5 4bd63f38bf55831436ad4035bc2b38e6
BLAKE2b-256 884da2fb480a0e1e602c42ab562915bfef205e50efc748f9f311b290fc5c86b3

See more details on using hashes here.

Provenance

The following attestation bundles were made for cc_transcript-14.16.1.tar.gz:

Publisher: release-pypi.yml on yasyf/cc-transcript

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file cc_transcript-14.16.1-cp313-abi3-manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for cc_transcript-14.16.1-cp313-abi3-manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 9cbd566433e744131dde9b4ce239784cd1d48550c78a77a325cf6c61852305ce
MD5 c9057bc632ca54c59059e4053d04a385
BLAKE2b-256 ba3b9c28c382becacc2c19c8c5e009607bf561900e30f9397a0b55e7f50f02ba

See more details on using hashes here.

Provenance

The following attestation bundles were made for cc_transcript-14.16.1-cp313-abi3-manylinux_2_28_x86_64.whl:

Publisher: release-pypi.yml on yasyf/cc-transcript

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file cc_transcript-14.16.1-cp313-abi3-manylinux_2_28_aarch64.whl.

File metadata

File hashes

Hashes for cc_transcript-14.16.1-cp313-abi3-manylinux_2_28_aarch64.whl
Algorithm Hash digest
SHA256 076afaa4d73374846085b1072d0ac9fa56ee24c39f9cbcf24aeed8b1f673d50f
MD5 8deb3cab2a1fe0f568f437b8ab9d0fcd
BLAKE2b-256 d90ace50ca0e69883be56a67b39ff0b4f2b2de0ad8333914d4c68f57a7bd9f9d

See more details on using hashes here.

Provenance

The following attestation bundles were made for cc_transcript-14.16.1-cp313-abi3-manylinux_2_28_aarch64.whl:

Publisher: release-pypi.yml on yasyf/cc-transcript

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file cc_transcript-14.16.1-cp313-abi3-macosx_11_0_x86_64.whl.

File metadata

File hashes

Hashes for cc_transcript-14.16.1-cp313-abi3-macosx_11_0_x86_64.whl
Algorithm Hash digest
SHA256 9f9491bffc4ffffb4787dfab615931fecb57a9b1ede94d69a7cc5d76b42cfb8d
MD5 4075b4808ea8367afb233a083b3edc1a
BLAKE2b-256 31be429a4d58532c1299a405769477eb6bb14de1ff01906c862f72a19851f285

See more details on using hashes here.

Provenance

The following attestation bundles were made for cc_transcript-14.16.1-cp313-abi3-macosx_11_0_x86_64.whl:

Publisher: release-pypi.yml on yasyf/cc-transcript

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file cc_transcript-14.16.1-cp313-abi3-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for cc_transcript-14.16.1-cp313-abi3-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 eaec791c2d5c47e4d249de01da250045cb9914af9131318366448451a1b09926
MD5 1d3af45ca5e93ba03d60fbec4e625fb0
BLAKE2b-256 2e44efb5a8a69a5e55ef264a7775b7892c80d531e60bdfbdb34b536a9f338d5c

See more details on using hashes here.

Provenance

The following attestation bundles were made for cc_transcript-14.16.1-cp313-abi3-macosx_11_0_arm64.whl:

Publisher: release-pypi.yml on yasyf/cc-transcript

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

14.17.0

5 files

This release

14.16.1 This release

5 files

14.16.0

5 files

14.15.0

5 files

14.14.0

5 files

14.13.0

5 files

14.11.1

5 files

14.10.0

5 files

14.9.0

5 files

14.8.0

5 files

14.7.0

5 files

14.6.1

5 files

14.6.0

5 files

14.5.0

5 files

14.4.0

5 files

14.2.0

5 files

14.1.1

5 files

14.1.0

5 files

14.0.0

5 files

13.2.0

5 files

13.1.0

5 files

13.0.0

5 files

12.1.1

5 files

12.1.0

5 files

12.0.0

5 files

11.0.0

5 files

10.8.0

5 files

10.7.0

5 files

10.6.0

5 files

10.5.0

5 files

10.4.0

5 files

10.3.0

5 files

10.2.0

5 files

10.1.0

5 files

10.0.0

5 files

9.1.0

5 files

9.0.1

5 files

9.0.0

5 files

8.1.0

5 files

8.0.0

5 files

7.1.0

5 files

7.0.2

5 files

7.0.1

5 files

7.0.0

5 files

6.0.0

5 files

5.0.0

5 files

4.1.0

5 files

4.0.0

5 files

3.3.0

5 files

3.2.0

5 files

3.1.0

5 files

3.0.1

5 files

3.0.0

5 files

2.0.0

5 files

0.9.0

5 files

0.8.0

5 files

0.7.1

5 files

0.7.0

5 files

0.6.0

5 files

0.5.0

5 files

0.4.0

5 files

0.3.0

5 files

0.1.0

5 files

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