Updated
Topic
Agents
Loops where Jev picks the next action and another system carries it out. 17 stories.
On 492 tool calls, OpenRouter Armor's default Jev 1.13 scored 90.7%, 446 of 492
On 492 tool calls, OpenRouter Armor's default Jev 1.13 scored 90.7%, 446 of 492, at $0.0021 a call. On October 16, 2026, at 01:18 UTC, this desk's jev-1.13.0 noul was 0.98 on git push origin main and 0.01 on ls ./reports.
On 40 client requests, Jev and Opus both scored 37 of 40, at $0.0015 against $0.005 to $0.015
Akshay Pachaar's TrueForge agent scored 37 of 40 client-issue matches with Jev and 37 of 40 without it. The printed decision costs are $0.0015 and $0.005 to $0.015. Review caught 5 wrong Jev matches. On October 13 he wrote that 40 is too small to establish how reliably confidence routes errors to review. On October 14, 2026, at 02:34 UTC, this desk's jev-1.13.0 call picked the intended issue at confidence 1.0. A trap shortlist scored 0.51. This desk did not install TrueForge.
jevgrep solves the same 8 of 10 SWE-bench tasks, and the bill including Jev is 25.8% lower
David posted dzhng/jevgrep, MIT, a CLI that asks Jev which files matter and returns excerpts. The September 26 post said about 40% lower coding-agent cost. The September 28 file for package 0.4.3, ten tuned Python tasks, keeps 8 of 10 official solves and prints $5.6564 against a saved $7.6221, Jev included. Five of the ten tasks cost more than that saved baseline. We did not rerun it.
toolgate 0.15 separates writing a script from running it, 19 of 20 on the paired set
Risk Averse Technology Company posted toolgate 0.15, MIT, a Claude Code hook and MCP proxy that asks Jev before a risky tool call. Frozen set 6, ten matched pairs, scores 19 of 20 with every pair separated and no permissive allow. A 1,369-decision week on version 0.9.1, with 455 items labeled again blind, found no permissive miss. Laptop p50 on 1,368 calls was 1,060 ms. We did not rerun the sets.
astra-jev-harness cuts Astra input 27% on one two-file fixture
Louis posted Oranquelui/astra-jev-harness, MIT, version 0.5.0. On a completed coding run dated September 24, two files and six checks, Astra input tokens fall from 19,198 to 14,011, and the checks stay 6/6. An older three-task note cut files from 28 to 4 while Astra input fell 1.2%. The dollar column is the maintainer's formula, one trial per arm, not a Codex invoice. We did not rerun it.
jev-code's three-task ladder still fails after the call-nesting fixes
Roberto Montalti posted rhighs/jev-code on September 26. Jev picks grammar productions. The program builds the AST and runs a compiler. The guide's ladder, one run per task, dated September 18, still fails guessing-game, file-io-script, and multi-file-package on commit 517d0f0. A hello-world smoke test does pass, in 3 turns and 16 requests. package.json is 0.2.0 and has no license field. The root listing has no LICENSE file. We did not run it.
Jevrail scores a shell command before it runs, and the printed corpus leaves the model off
Saman Pandey posted jevrail, an MIT hook that asks Jev whether a shell command is likely to destroy something, then blocks, asks, or allows it. The published eval is an 80-line corpus with the model switched off: 22 of 22 catastrophic commands are caught, and 15 of 26 safe commands still raise a false ask.
One screenshot decision was $0.0002 on Jev and $0.032 on Opus 5
awlevin's macOS loop reads the screen with OCR and asks Jev which action comes next. On one shared screenshot the README prints $0.0002 and 0.13 to 0.38 seconds for Jev, against $0.032 and 5.2 seconds for Claude Opus 5 on the bare image. The same page says Opus read the dates off the pixels, and this loop annotates dates in code before the classifier runs.
AstroHan ran 30 coding tasks with a Jev context filter: 25 passed, 22 without it
AstroHan scored every tool result with Jev before it reached deepseek-flash, on the same 30 FrontierHarness tasks. Filtered 25/30 pass@1 versus 22/30 unfiltered. On meriyah the unfiltered run timed out at 0/49 tests; the filtered run passed 49/49. One run per arm. Token spend did not fall.
Jev macOS Loop clicks native Mac windows; Finder sorted nine files in 7.39 seconds
Josh C. Simmons open-sourced a computer-use loop for Apple silicon that keeps pixels on the Mac and asks Jev only over observed controls. A Finder demo moved nine dummy files in three group drags in 7.39 seconds, with a separate verifier checking locations and hashes.
Jevis is a Flutter integration-test agent that only taps what you registered
Jake Gwon released jevis, a Dart package that drives Flutter's integration_test loop with Jev. You register legal actions, write a goal, and set an action budget. Jev picks the next widget action and a Noul checks whether the goal is already on screen.
Sam Saffron tries Jev as a hidden control plane for GPT Live in term-llm
Discourse cofounder Sam Saffron opened a term-llm pull request that classifies each GPT Live voice turn with TypeSafe's System One API in about 650 milliseconds, instead of a tool-calling fast-model turn. Shadow mode is on by default. Failures pass the utterance through unchanged.
A hybrid Jev overlay sped up Postgres joins 12% on JOB, and made the planner slower
Michael Malis asked Jev to help plan Postgres joins on the join order benchmark. Letting it pick the join order made queries twice as slow. Estimating filters, then overriding Postgres only when Jev was confident, improved geometric-mean time by 12%. On September 30, 2026 this desk timed a 100,000-row table on Postgres 18.6. A Jev call of about 900 ms dominated queries that took 0.15 ms to 7.7 ms. The 12% figure was not rerun.
SREGym put Jev on a Codex agent: 24 passes out of 50, up from 20
Jackson Clark's team wired Jev into SREGym-Lite as a test ranker and evidence reviewer on a Codex agent that still diagnosed and repaired. With gpt-5.6-luna, the Jev-assisted agent passed 24 of 50 attempts against 20 without it. Two problems got worse.
Compaction without summarization: score the tool calls and drop them
Tamara Tran argued that agent context compaction is still a summarization prompt in 2026, and that Jev can instead keep or drop tool output verbatim. On September 30, 2026 this desk compared full text, a gpt-6-luna summary, and a Jev score filter on six short traces. All three kept the planted fact, and the filter did not cause a later miss.
LangChain ships a Jev classifier, then parks it on the agent loop
Official LangChain docs add langchain-typesafe, introducing a Runnable for classification alongside experimental middleware hooks for agent loops.
JevPilot is a playable driving sim that asks Jev which path to take
Justin Schroeder wired Jev into a Three.js driving simulator in under an hour, then open-sourced JevPilot the next day. The model sees compact tables of candidate paths, not pixels. Requests run up to four times a second in traffic. On September 30, 2026 a headless run of that simulator, jev-1.13.0, reached the town and city arrivals with no collisions and stopped both highway drives at a 240 second cap.