Does my session data leave the machine if I never enable Jev analysis?

No. The viewer reads the local JSONL files in ~/.claude/projects/ and does not require sending traces anywhere. If you turn on analysis, it shows the exact redacted payload and requires your confirmation before sending, so you see what goes out.

Will the macOS app open without fighting Gatekeeper?

Yes, which is the stated reason for the design. Releases ship an unsigned .app.tar.gz installed by a curl script rather than a .dmg, so the quarantine flag is never set and there is no xattr step. Apple Silicon only.

Can I run this on a headless box instead of my laptop?

Only web mode is supported in Docker, on port 1421, with $HOME/.claude mounted read-only; a redeploy script stores the Jev key in a Docker-managed volume. The desktop and TUI modes are for a local machine.

How much should I trust the efficiency scores?

They come from the optional Jev integration and are one cached result per session, marked stale when the trace or the analysis formula changes. Token efficiency deliberately covers tokens, context growth, turns, and tool activity without evaluating monetary cost.

What does the Jev analysis actually score?

It evaluates agent behaviour using typed probabilities across progress, tool use, focus, exploration, recovery, and token efficiency, and links each finding back to the relevant Claude Code messages.

Where are Jev and provider API tokens stored?

In the OS credential store: macOS Keychain, Windows Credential Manager, or Linux Secret Service. The Docker web deployment instead keeps the key in a Docker-managed volume mounted read-only.

How do I run it in web or terminal mode?

One binary covers all three: cctrace for the desktop app, cctrace --web to open a browser, and cctrace --tui for a terminal UI, with Docker supported for web mode only on port 1421.

CommunityJev Tools & CLIs

Claude Code Trace

Claude Code Trace renders the JSONL session files in ~/.claude/projects/ as browsable conversations with expandable tool calls, MCP tool names, and token counts, with an optional Jev pass that scores agent efficiency.

See highlights

Open github.com

Stars: 376
Language: Rust
License: MIT
Published by: Community
Author: delexw
Last verified: Oct 2026

delexw/claude-code-trace

User repository on GitHub

View on GitHub

Claude Code session log viewer for JSONL files in ~/.claude/projects. Browse conversations, tool calls, tokens, and live tail sessions on desktop, web, and TUI.

Forks: 24
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

Claude Code Trace is a Claude Code session log viewer and Jev-powered AI agent efficiency analyzer for local JSONL files stored in /.claude/projects/. It combines real-time Claude Code trace observability with structured behavioural analysis from Jev, TypeSafe AI's System One Model.

Quoted from the project's README. Read the full README.

Tagscommunity jevbest

Works forJev for Classification Jev for Tool calling

Used inJev for Software & DevTools

Languages: Rust

Highlights

Desktop app, browser mode, and terminal UI from one binary: cctrace, cctrace --web, and cctrace --tui.
Search sessions by user message, tail a live run, and expand individual tool calls instead of reading raw JSONL.
Jev analysis is opt-in: the exact redacted payload is shown and needs confirmation before anything is sent.
Tokens are stored in Keychain, Credential Manager, or Secret Service, and cached results are marked stale when the trace changes.

Watch out

The Jev analysis is optional and this is an independent integration, not an official TypeSafe AI one; the README does not document the scoring thresholds or how the efficiency formulas are calibrated. macOS builds are Apple Silicon only and unsigned, so hand-downloading the macOS build is unsupported. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

james_library

R.A.I.N. Lab is a local-first research environment. Four constrained perspectives investigate a question, quoted spans are checked against a local paper corpus, and experiments are pre-registered with host code, not a model, deciding pass, fail or inconclusive.

Jev Tools & CLIs#community#jevbest

Community

topherchris420/james_libraryRust

jackalope

A Tauri desktop workspace for running coding agents side by side: parallel task queues in isolated Git worktrees, your existing agent sign-ins, and a review step before anything is merged.

Jev Tools & CLIs#community#jevbest#catalog-import

Community

Jackalope-Dev/jackalopeRust

prism-liquidity-agent

124

Prism is an autonomous liquidity agent for Solana concentrated liquidity pools, currently Meteora DLMM. Every ten minutes it recalls past outcomes, reads pool state, scores volume authenticity and decides HOLD, REBALANCE, EXIT or ENTER behind a risk gate.

Jev Tools & CLIs#community#jevbest

Community

irfndi/prism-liquidity-agentTypeScript

Stratum

Docker Compose log intelligence stack: Rust ingest and retrieval crates over ClickHouse and Qdrant with a Next.js dashboard, where the decision model is an optional query classifier.

Jev Tools & CLIs#community#jevbest

Community

YEDASAVG/StratumRust

doc-router

Rust CLI that checks each PDF page for a usable text layer, extracts text pages locally, sends only the rest to an OCR model via LiteLLM, and merges a page-ordered result.

Jev Tools & CLIs#community#jevbest#catalog-import

Community

misbahsy/doc-routerRust

SmartMoney-Cub

Local-first trading journal and review harness that is read-only over markets, captures runs into frozen envelopes and evidence packs, and requires explicit human promotion before any rule returns.

Jev Tools & CLIs#community#jevbest#catalog-import

Community

myc0576/SmartMoney-CubPython

From the Jev guides

Original write-ups on what this entry is for.

Jev on the Gateways: Vercel, Workers AI, and OpenRouter

Oct 12, 2026

The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.

Jev Tools & CLIs#gateway#vercel#cloudflare

Read article

Exporting Decision Models: GGUF, ONNX, and Device Runtimes

Oct 10, 2026

Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.

Jev Tools & CLIs#open-models#local#onnx

Read article

Records at Rest: Documents, Inboxes, and Risk Queues

Sep 28, 2026

Jev labels a record that already exists. Code moves, flags, or holds it. How the document, mail, and transfer tools keep the action out of the model.

Jev Tools & CLIs#classification#email#security

Read article

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai