Organization repository on GitHub
The subjective gate for Impatient Programming: no PR merges while a reviewer would ask for the change to be simplified
- Forks
- 3
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Tools & CLIs
qualm (Impatient Programming gate)
A single-binary gate for Impatient Programming that fails a pull request when an experienced reviewer would ask for the change to be simplified: it asks Jev about each changed file and tells the coding agent what to fix, with no LLM or parser inside.
- Stars
- 10
- Language
- Go
- License
- MIT
- Reading time
- 3 min
- Published by
- Community
- Author
- tools4imps
- Last verified
- Oct 2026
- Platforms
- CLI
- Capabilities
- Open source
Highlights
- Fails a pull request when an experienced reviewer would ask for the change to be simplified, and tells the coding agent what to fix.
- The verdict comes from Jev: it reads a diff, answers typed questions with probabilities, and writes no prose; no LLM runs inside qualm.
- It has no parser, so it judges code in any language, and it ships as one binary with no dependencies.
- Sibling of exhale (tools4imps/exhale-ruby), whose checks are deterministic; qualm is the subjective gate for Impatient Programming.
- Install with gem install qualm or go install github.com/tools4imps/qualm/cmd/qualm@latest; binaries for macOS, Linux and Windows.
Quickstart
bash
go install github.com/tools4imps/qualm/cmd/qualm@latestWatch out
README reviewed 2026-10-17; the digest truncates the install section after the binary-download sentence, so CI wiring, configuration, and release links are not visible here. The README states no benchmarks, thresholds, or Jev model version, and the digest does not document how qualm authenticates its Jev calls.
Questions about this entry
Short answers drawn from the linked project or page.
A PR gate from tools4imps that fails a pull request when an experienced reviewer would ask for the change to be simplified, and reports what to fix. It is the subjective gate for the Impatient Programming project.
It asks Jev, TypeSafe's System One decision model, about every changed file: Jev reads the diff, answers typed questions with probabilities, and writes no prose. No LLM runs inside qualm; the agent reading the report does the reasoning and fixing.
It is deliberately subjective. Its sibling exhale has deterministic checks, while qualm asks whether a reviewer would push back on a change — a judgment call. It has no parser, so it is not language-specific.
With Ruby, add gem "qualm", require: false to a Gemfile or run gem install qualm; the gem carries a platform binary and a qualm command. With Go, run go install github.com/tools4imps/qualm/cmd/qualm@latest. Binaries for macOS, Linux, and Windows are also offered.
qualm itself is one dependency-free binary, but its judgment comes from Jev, so it needs access to the model. The digest does not show authentication, pricing, or GPU details, and no local model route is documented in the excerpt.
The README's framing: agents write more code than anyone reads, and when green merges itself something has to decide which changes still get human eyes. qualm answers the question 'would a reviewer push back on this?' for every changed file.
The tools4imps organization, as part of the Impatient Programming project. The repository is MIT licensed with 9 stars and 3 forks, created 2026-10-04 and last pushed 2026-10-05.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
Hacker News: Thread on Selmar's Jev code-review calibration notes and ordering.py comparisons.
Lectem2 pointsCalibrating Jev as a Code ReviewerRead the thread on Hacker NewsHacker News: Jev classifies agent PR hunks as P0, P1, or P2 so reviewers see P0 first.
namanbhulawat47 pointsJev Based Code ReviewRead the thread on Hacker NewsX: Magic Jev Ball for code review
X: jev-review: a local-first score loop for coding agents
Other listings of this project
Forks and copies of this project in the directory. This entry is the canonical one.
macOS menu bar screen-time app that reads the screen as text through the Accessibility API and asks a System One model one Choice per user rule plus a Noul on whether the page is a payment, login or banking screen, stepping in only when a rule's probability clears its threshold.
Jev Integrations & Adapters#community#macos#digital-wellbeing
Community
RoderickQiu/qualmPython
RoderickQiu/qualmPythonA TypeScript client for Jev where every decision must handle an unsure branch, so a low-confidence answer escalates instead of collapsing silently into a boolean.
Jev Tools & CLIs#community#jevbest#catalog-import
Community
qddegtya/qualmTypeScript
qddegtya/qualmTypeScriptMore Jev resources like this
Read-only Go CLI that semantically checks your files against your own rules with Jev, locally or in CI, printing text or JSON and caching results between runs.
Jev Tools & CLIs#community#github#go
Community
Alurith/jeffGo
Alurith/jeffGoAn unofficial Go CLI that puts Jev in a coding agent's toolbox: the agent can ask where an answer lives and read only those lines, or hand Jev a yes/no or multiple-choice call and get a calibrated verdict tuned to the cost of a wrong call.
Jev Tools & CLIs#community#github#go
Community
bragamat/jevkitGo
bragamat/jevkitGoA type-aware TypeScript linter that pins a public typescript-go compiler module and runs syntax- and type-aware rules in one AST pass per root file; its semantic mode reads changed files and asks TypeSafe Noul questions over bounded spans and candidates per policy.
Jev Tools & CLIs#community#github#typescript
An open-source merge gateway for repositories where agents write most commits: a System One model answers five fixed questions per pull request with calibrated probabilities in roughly 300 ms, a YAML policy turns them into pass, hold or block, and a planner lands non-conflicting PRs in waves.
Jev Tools & CLIs#community#github#go
Community
haalp/mergeonePython
haalp/mergeonePythonGo linter whose rules are plain-English questions: AST matchers select nodes and Jev answers one Noul per fragment above the rule's threshold. It runs standalone, under go vet, and as a golangci-lint plugin, with cached answers so runs only ask about changed code.
Jev Tools & CLIs#community#linter#go
Community
arturobermejo/semcheckGo
arturobermejo/semcheckGogrep, sort, cut and uniq that match by meaning: each line whose Jev Noul clears the threshold survives grev, sibling filters route by Choice and rank by Score, and the output is always your own input, never generated text.
Jev Tools & CLIs#community#cli#coreutils
Community
aurorainfra/grevGo
aurorainfra/grevGoFrom 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.