User repository on GitHub
Jev Turn Analysis is a Rust CLI for analyzing completed Claude Code and Codex sessions.
- Forks
- 1
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
Jev Turn Analysis
A Rust CLI that reads completed Claude Code and Codex sessions, scores each turn with Jev, and turns recurring patterns into suggested edits for your AGENTS.md, skills and tools. Ships as jta with init, analyze and report commands.
- Stars
- 0
- Language
- Rust
- Reading time
- 3 min
- Published by
- Community
- Author
- hobbs
- Last verified
- Oct 2026
Highlights
- jta reads Codex and Claude Code sessions in place: no transcript export or separate import step is needed.
- Two commands get you going: jta init stores the Jev API key, jta analyze finds sessions and scores them with live progress bars.
- jta report groups opportunities by project × category × remediation surface and has your codex or claude CLI investigate the top five groups.
- A recurring proposal needs three distinct supporting sessions within one project by default; --recurring-only removes the one-session fallback.
- Full-corpus statistics run locally; a fresh report with five groups normally runs five CLI investigations, per the README's usage section.
Quickstart
bash
cargo install --path . --locked
jta init
jta analyzeWatch out
Grounded in the truncated repo README and GitHub metadata read on 2026-10-15; the excerpt cuts off inside the LLM usage and budgets section. The repository declares no licence, and the full budget figures for CLI investigations were not captured in the available text.
Questions about this entry
Short answers drawn from the linked project or page.
A Rust CLI, invoked as jta, that analyzes completed Claude Code and Codex sessions to find where work went well or got stuck, then suggests specific changes to your agent instructions, skills and tools. It starts from whether the task succeeded and was checked, then looks at wasted effort.
Codex and Claude Code. jta init walks you through choosing a report CLI (codex by default, or claude) and stores the Jev API key; install and authenticate the selected CLI separately, because JTA manages only the Jev key.
Install from a checkout with cargo install --path . --locked using a stable Rust toolchain, then keep ~/.cargo/bin on your PATH. In a project where you use Codex or Claude Code, run jta init once and then jta analyze; re-run analyze whenever you have new sessions.
jta report turns recurring patterns into suggested edits to AGENTS.md, skills and tools. It groups opportunities, has the chosen CLI investigate the highest-priority groups, then reconciles findings into a Markdown report and a JSON companion with full-corpus statistics. Suggested edits are never applied automatically.
Full-corpus statistics are computed locally; Jev usage covers the per-session scoring. The README's LLM usage and budgets section says a fresh report with five selected groups normally runs five CLI investigations, but the truncated excerpt does not include the complete budget figures.
No. Run jta analyze again whenever you have new sessions; unchanged results are reused automatically and cached sessions are clearly marked, so re-runs do not re-score everything.
jta report --top 10 selects more project/category groups, --all covers all eligible groups within budget, --session investigates one session, --refresh bypasses the investigation and synthesis caches, and --dry-run --format json inspects the selection and contract without launching a CLI.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Decision outputs in Grep
Hacker News: jevmem keeps Claude Code project memory by asking Jev which turns are worth saving.
avinashjetwani61 pointsJevmem – automatic project memory for Claude Code, built on JevRead the thread on Hacker NewsX: A usage router for Grok Bot
X: The compaction plugin, in Chinese
More Jev resources like this
A stateless Rust CLI for typed semantic judgments with the Jev model: state and questions in, calibrated answers and exit codes out, as stable JSON on stdout. Ships with an Agent Skill for scripts, CI and agent workflows.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
model-clis/jevRust
model-clis/jevRustA Go linter that checks code against plain-language rules: Tree-sitter extracts code units, then each one is sent to Jev or another configured decision provider to decide whether it passes, with caching and eval fixtures.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
codegirl-007/jevlintGo
codegirl-007/jevlintGoA Rust CLI that searches code by meaning with Jev: describe a concept in plain English and get relevant files, line ranges, confidence scores and source snippets, with tunable file and match thresholds plus retry handling.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
peu77/jevfindRust
peu77/jevfindRustAn npm CLI that scans TypeScript, JavaScript and Python codebases for LLM calls that are really decisions, converts them into Jev modules with confidence-gated fallbacks, and shadow-tests them on recorded traffic before you swap.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
0xjba/jev-swapHTML
0xjba/jev-swapHTMLA toolkit that turns an agent skill into a project-specific Oxlint plugin: deterministic AST checks handle structural rules while Jev answers the narrow typed questions that need contextual judgment.
Jev Tools & CLIs#community#catalog-import#madewithjev
Community
cephalization/jev-oxlintTypeScript
cephalization/jev-oxlintTypeScriptRust coding-agent harness (MIT, ~20k stars) whose crates/jcode-base/src/jev.rs is a typed TypeSafe Jev decision transport, used for memory pruning (memory_jev.rs), browser navigation (browser_jev.rs), and voice routing (voice_intent.rs) with separate provider selectors per purpose.
Jev Tools & CLIs#community#rust#coding-agent
Community
1jehuang/jcodeRust
1jehuang/jcodeRustFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.