---
title: "Repos: coding agents, orchestration, memory, browser and computer use, integrations"
type: community
source_tier: community
tags: [community, repos, coding-agents, browser-use, integrations]
created: 2026-09-21
updated: 2026-09-21
confidence: medium
sources:
  - raw/x-repos/INDEX.json
  - raw/x-repos/tamaratran__fast-jev-compaction.md
  - raw/x-repos/GhalebDweikat__winnow.md
  - raw/x-repos/thruwire__foreman.md
  - raw/x-repos/qkal__Canny.md
  - raw/x-repos/devagrawal09__jev-review.md
  - raw/x-repos/devagrawal09__stanley-code.md
  - raw/x-repos/0xNatoshi__jev-codex-router.md
  - raw/x-repos/gargpratyush__jev-router.md
  - raw/x-repos/kunchenguid__compact-adviser.md
  - raw/x-repos/DevMortimer__pi-warden.md
  - raw/x-repos/EliaAlberti__jev-rules.md
  - raw/x-repos/mrnugget__jev-shell-history.md
  - raw/x-repos/ellipsis-dev__blink.md
  - raw/x-repos/dbreunig__building-with-jev-skill.md
  - raw/x-repos/browser-use__jev-ultrafast.md
  - raw/x-repos/trycua__cua.md
  - raw/x-repos/awlevin__typesafe-computer-use.md
  - raw/x-repos/droidrun__mobile-jev.md
  - raw/x-repos/moritzkremb__jev-voice-browser.md
  - raw/x-repos/kitze__unclutter.md
  - raw/x-repos/nekuda-ai__WindTunnel.md
  - raw/x-repos/kitze__skillbox.md
  - raw/x-repos/codejunkie99__agentic-stack-desktop.md
  - raw/x-repos/codejunkie99__continual-memory-policy-model.md
  - raw/x-repos/leotavares26__octavus-dual-brain.md
  - raw/x-repos/jkudish__jev-mcp.md
  - raw/x-repos/itsmostafa__typesafe-mcp.md
  - raw/x-repos/sharziki__semdecide.md
  - raw/x-repos/Anil-matcha__awesome-jev-by-typesafe.md
  - raw/x-repos/vercel-labs__json-render.md
  - raw/x-repos/kerpopule__hermes-jev-skills.md
  - raw/x-repos/ryana__jevify.md
  - raw/x/mathfax-2102111616175403215.md
  - raw/x/trycua-2101437979180904640.md
  - raw/x/VladTerin-2100448995415863323.md
jev_version: "jev-1.13.0"
summary: "32 community repos that put Jev inside a coding agent, an orchestrator, a browser or computer-use loop, or an MCP/CLI integration surface."
---

# Repos: coding agents, orchestration, memory, browser and computer use, integrations

> **TL;DR** The agent-side half of the community repo catalogue. Index and the vetting checklist: [[ideas/community-repos]]. Data, document, judging, real-time, market and replica repos: [[ideas/repos-apps]]. Stars and languages are the 2026-09-20 capture (roundup repos 2026-09-21; see [[ideas/community-repos]] on star drift). **Unaudited code**, most of it with shell, browser or editor reach.

## Coding agents and developer workflow

| repo | stars/lang | what it does, and how it uses Jev | maps to |
|---|---|---|---|
| [fast-jev-compaction](https://github.com/tamaratran/fast-jev-compaction) | 4918/TS | Replaces Claude Code compaction. Conversation as state → 2 `noul` per unpinned call (keep call? keep result?) → drop or truncate below 0.5. | [[cookbooks/classifying-rag-passages]], [[ideas/patterns-agents]] P07 |
| [winnow](https://github.com/GhalebDweikat/winnow) | 40/Py | Claude Code function-hook sieve. Splits each large tool result into ~25-line blocks, asks one `Noul` per block ("needed now?") in one call, hides blocks below `WINNOW_DROP` 0.1 behind a recall stub, keeps the uncertain band 0.1–0.5 verbatim, and hides nothing if the judge says the output shows an error. A second hook ranks project memory files per prompt and injects the top 3 above 0.5. `winnow replay` scores a judge offline on your own transcripts (weak labels plus blind hand labels) and prints calibration (ECE) beside ordering (ROC AUC); the `strict` question set was overconfident — 23% of its bottom bin was needed. Falls back to TypeSafe's `system-one-adapter` on Haiku 4.5 with no key. | [[cookbooks/classifying-rag-passages]], [[reference/system-one-adapter]], [[ideas/patterns-agents]] P07 |
| [foreman](https://github.com/thruwire/foreman) | 425/Py | Supervises coding agents. Factory events → 10 `noul`s (`worker_stuck`, `work_off_track`, `needs_human`…) in one call → a deterministic policy picks STEER/STOP/VERIFY | [[patterns/confidence-routing]], [[ideas/patterns-agents]] P04 |
| [Canny](https://github.com/qkal/Canny) | 19/TS | Warden for Claude Code and Codex CLI: "facts go to code, judgments go to Jev, only facts can block." Two `Noul`s — "does this edit break a rule in `CLAUDE.md`/`AGENTS.md`" (a note above 0.9) and "does this message claim the work is done" (treated as *not* a claim below 0.1). Jev can only **relax** the done-gate; the block itself comes from an append-only ledger with no passing check since the last edit. Requests are cached by content hash, so `canny replay` re-derives verdicts offline. | [[cookbooks/llm-guardrails]], [[ideas/patterns-agents]] P04 |
| [jev-review](https://github.com/devagrawal09/jev-review) | 400/TS | Staged review. `Noul` risk matrix → `Choice`+`Score` file profiles → `Choice` evidence → `Choice` mechanism → `Score` severity → routing | [[patterns/composite-scoring]], [[ideas/patterns-agents]] P10 |
| [stanley-code](https://github.com/devagrawal09/stanley-code) | 98/TS | Bounded agent workflows. One `choice` over workflow metadata + `cannot_tell`, gated on confidence ≥ 0.6, probability ≥ 0.55, margin ≥ 0.15; then per-hunk `choice` | [[patterns/intent-routing]], [[ideas/patterns-agents]] P10 |
| [jev-codex-router](https://github.com/0xNatoshi/jev-codex-router) | 152/Py | Per-call model **and** effort routing for Codex. Three independent `Choice` questions in one request: does the mandatory-Astra policy apply, the cheapest sufficient tier (luna/sol/astra), and the minimum thinking depth (low→max). Jev sees only a bounded dossier — task, step type, intent tail, tool name, tool-output tail, image flag — while the executing model gets Codex's full replay. Fail-open to astra/medium on any error, sentinel-file kill switch, shadow mode, decisions logged locally for calibration. | [[patterns/intent-routing]], [[ideas/patterns-agents]] P02 |
| [jev-router](https://github.com/gargpratyush/jev-router) | 245/JS | Per-turn model routing. Prompt + tier + context tokens → four scored dimensions + confidence → fast or strong tier | [[patterns/intent-routing]], [[ideas/patterns-agents]] P02 |
| [compact-adviser](https://github.com/kunchenguid/compact-adviser) | 146/TS | "Compact now?" Two one-sentence questions per request → one composed score against a floor sliding 0.90→0.50 as context fills. | [[patterns/confidence-routing]], [[ideas/patterns-agents]] P07 |
| [pi-warden](https://github.com/DevMortimer/pi-warden) | 102/TS | Pi guardrails. Tool call + project Markdown rules → Jev judges irreversible calls, rule breaches, stuck loops and unverified "done", then steers rather than blocks. Questions live only in `docs/guards.md` | [[cookbooks/llm-guardrails]], [[ideas/patterns-agents]] P03 |
| [jev-rules](https://github.com/EliaAlberti/jev-rules) | 43/JS | Injects only the relevant standing rules. Prompt text → one `noul` per rule and map doc in one call → inject ≥ 0.6; shows all on error | [[cookbooks/skill-suggestion]], [[ideas/patterns-agents]] P08 |
| [jev-shell-history](https://github.com/mrnugget/jev-shell-history) | 69/TS | zsh suggestions. Typed prefix + 100 id-tagged history entries → `Choice` over ids + `Noul` "does any complete this?" → show if top ≥ 0.3 and Noul ≥ 0.5 | [[cookbooks/semantic-find]] |
| [blink](https://github.com/ellipsis-dev/blink) | 38/TS | Codebase search with no index and no embeddings. Jev scores file and folder **names**; likelier paths get more of N walkers, each descending to a file, and the result is the share of walkers that ended there (74%/16%/10% in the README's example). Every walker writes a trace with each choice and probability, so a search is auditable. Quotes $0.042/Mtok input with free output — `verified`. | [[cookbooks/semantic-find]], [[ideas/patterns-data]] P17 |
| [building-with-jev-skill](https://github.com/dbreunig/building-with-jev-skill) | 124/— | Agent skill for *writing* Jev programs, not a caller: question design, state, thresholds; targets `jev-1.13`. | [[reference/agent-skill]] |
| [jevify](https://github.com/ryana/jevify) | 37/— | **A prompt, not code** (no licence): one brief you paste into a coding agent working in your repo. The agent reads the official docs plus the architecture probe study ([[ideas/field-reports]]), finds where the project pays for model calls, generates text only to parse a decision out of it, or falls back on brittle rules, then proposes three kinds of opportunity — direct savings, better outcomes, new capabilities — and names the assumptions that exist only because semantic computation was expensive. It also demands what most Jev pitches skip: a comparison against deterministic code, caching, embeddings, conventional classifiers or a small generative model; an evaluation designed to prove the idea wrong; vendor claims, measured results and hypotheses kept apart. Cited as a good example by [@mathfax](https://x.com/mathfax/status/2102111616175403215), who appears to work at TypeSafe. | [[ideas/consult]], [[reference/agent-skill]] |

## Browser, computer and mobile use

| repo | stars/lang | what it does, and how it uses Jev | maps to |
|---|---|---|---|
| [jev-ultrafast](https://github.com/browser-use/jev-ultrafast) | 11208/Py | Browser agent, no screenshots. Indexed DOM element table → one request: `operation` (CLICK/TYPE_TEXT/SELECT/SCROLL/WAIT/DONE/BLOCKED) plus a speculative target question per operation. | [[patterns/fan-out]], [[ideas/patterns-interface]] P12 |
| [trycua/cua](https://github.com/trycua/cua) | 25014/HTML | Computer-use platform with a `jev-use` recipe. Not in the README; per the team's article, code builds candidate actions with ids, Jev picks one, code validates, executes, re-observes | [[concepts/state]], [[ideas/patterns-interface]] P14 |
| [typesafe-computer-use](https://github.com/awlevin/typesafe-computer-use) | 582/Py | macOS computer use, ~$0.0002/step (author). OCR + accessibility tree → candidates → three `Choice`s plus an `offscreen` question per request; a `Noul` verifies the typed field; aborts below 0.4 | [[patterns/fan-out]], [[ideas/patterns-interface]] P14 |
| [mobile-jev](https://github.com/droidrun/mobile-jev) | 264/JS | Android agent, no ADB. Screen + installed apps → operation plus compatible-target questions per request; code rejects stale targets. Typed text is a span of the goal; `DONE` is not proof | [[patterns/fan-out]], [[ideas/patterns-interface]] P12 |
| [jev-voice-browser](https://github.com/moritzkremb/jev-voice-browser) | 148/JS | Voice to Playwright, acting on partial speech. 9–11 questions per transcript: intent/target/site/spans (`Choice`), complete/is_command/destructive (`Noul`), scroll_amount (`Score`), each thresholded. | [[patterns/confidence-routing]], [[ideas/patterns-interface]] P14 |
| [unclutter](https://github.com/kitze/unclutter) | 143/TS | Hides page clutter. DOM candidates → typed keep/ad/promotion/newsletter/social/cookie/uncertain choices → hides only when probability **and** confidence are ≥ 0.9 | [[cookbooks/llm-guardrails]], [[ideas/patterns-data]] P18 |
| [WindTunnel](https://github.com/nekuda-ai/WindTunnel) | 72/HTML | WebMCP interface benchmark. Jev + Mercury 2.5 is 1 of 21 configs (49/49 with WebMCP, 25/49 with DOM controls); Jev decides, Mercury writes arguments. Runner in `experiments/jev/` | [[concepts/workflow-evals]], [[ideas/patterns-interface]] P13 |

`vlad-terin/jev-browser`, announced 2026-09-17 as a Codex browser adapter ("Codex plans, Jev selects, the browser moves"), 404'd at capture; an unrelated `jkudish/jev-browser` named in the jev-mcp README was not captured.

## Agents, orchestration and memory

| repo | stars/lang | what it does, and how it uses Jev | maps to |
|---|---|---|---|
| [skillbox](https://github.com/kitze/skillbox) | 214/TS | Self-hosted skills library over MCP. Task + skill descriptions → an **uncalibrated 0–4 rubric score** per skill (not a probability); returns ≥ 3, search fallback | [[cookbooks/skill-suggestion]], [[ideas/patterns-agents]] P08 |
| [agentic-stack-desktop](https://github.com/codejunkie99/agentic-stack-desktop) | 64/Py | Knowledge graph across four coding agents. Not in the README; the linked post is about finding Jev-shaped decisions in a workflow | [[ideas/consult]] |
| [continual-memory-policy-model](https://github.com/codejunkie99/continual-memory-policy-model) | 5/Py | Memory policy with delayed feedback. Not in the README; its WRITE/UPDATE/DELETE/LINK/COMPACT/NOOP action set is Jev-shaped, but it trains its own policy | [[concepts/primitives]], [[ideas/patterns-agents]] P09 |
| [hermes-jev-skills](https://github.com/kerpopule/hermes-jev-skills) | 387/Py | Nine agent-agnostic `SKILL.md` skills (Hermes, Claude Code, Codex) handing small decisions to Jev: per-turn model routing over your own catalogue, which retrieved passages to read, which turns survive a cut, which of 377 installed skills a turn needs, message triage, mailbox lanes, and the next GUI or browser action **from a table you already approved** — Jev can only return an id you supplied. Author's numbers: ~0.4 s per routed turn, 377 skills in ~2.8 s, 71 turns in 0.95 s, $0.00006 per triage, $0.00002 per mail message, 60 passages per memory request. All of it fails open (no key, timeout or low confidence → model kept, nothing dropped). Honest negative: a Jev-digested handoff recalled *less* than the plain transcript, so they ship the transcript. The key goes to the OS secret store, never to the agent, and the README lists what leaves the machine per skill — a routed turn sends the user's turn redacted (2,500 chars) before the agent can object. MIT. | [[patterns/intent-routing]], [[cookbooks/skill-suggestion]], [[ideas/patterns-agents]] P02, P07, P08 |
| [octavus-dual-brain](https://github.com/leotavares26/octavus-dual-brain) | 0/HTML | Write-up placing Jev as System 1 before an orchestrator. `intent` (`Choice`) + `risk_score` (`Score` 0–3) in parallel; 10 filings in one call | [[patterns/intent-routing]] |

## Integrations and catalogs

| repo | stars/lang | what it does, and how it uses Jev | maps to |
|---|---|---|---|
| [jev-mcp](https://github.com/jkudish/jev-mcp) | 214/TS | Ten MCP judgment tools: `jev_verify`, `jev_screen`, `jev_find`, `jev_rerank`, `jev_classify`, `jev_decide`, `jev_compare`, `jev_extract`, `jev_review`, `jev_gate`. The validation is the value — a returned choice must belong to the requested set **and** be a maximum-probability option; a distribution must carry exactly the expected keys, finite, in `[0,1]`, summing to 1 within `0.01`; a malformed answer fails closed for that item while valid siblings survive. `jev_extract` chooses among candidates a regex already found, so the model picks a value and never writes one. Thresholds (`auto_accept` 0.8, `block_at` 0.75, `review_at` 0.25) are cookbook starting points, not tuned. Providers: direct TypeSafe, OpenRouter (`typesafe/jev-1.13`), Cloudflare Workers AI, Vercel AI Gateway or any `/v1/systemone`-compatible endpoint — the gateway routes are `unverified` against first-party docs. | [[reference/http-api]], [[cookbooks/citation-check]], [[cookbooks/llm-guardrails]] |
| [typesafe-mcp](https://github.com/itsmostafa/typesafe-mcp) | 133/Go | MCP server with one `evaluate` tool. Passes `state` + a `questions` map (`{type, instructions, criteria?}`) to `POST /v1/systemone`, default `jev-latest`; validates criteria locally | [[reference/http-api]] |
| [semdecide](https://github.com/sharziki/semdecide) | 18/Py | "`grep` for meaning and `jq` for judgment" — typed decisions as Unix exit codes. `is` (Noul), `choose` (Choice over named options), `score` (ordered rubric), `filter` (JSONL, order preserved, `_semdecide` metadata added), and a `guard` recipe asking narrow signals (authorization, destructiveness, ambiguity, secret exposure, consequence) that deterministic code turns into allow/escalate/block. Exit codes keep false (`1`), uncertain (`3`) and provider failure (`4`) distinct; `guard` fails closed to escalate. Its `--json` sample shows `"confidence": null` for `is` — `verified`, Noul answers carry no `confidence` ([[reference/http-api]]). `--max-input-bytes` defaults to 1,000,000, a local cap far above the documented 64k-token request budget. | [[cookbooks/llm-guardrails]], [[ideas/patterns-agents]] P03 |
| [awesome-jev-by-typesafe](https://github.com/Anil-matcha/awesome-jev-by-typesafe) | 684/Py | Curated use cases and starter code; a directory, not a caller. Quick start matches SDK 0.6.0; patterns mirror the official four | [[patterns/overview]] |
| [json-render](https://github.com/vercel-labs/json-render) | 17848/TS | Vercel Labs generative-UI framework — **not Jev-specific**; listed because @charliejhills' roundup links it. Its only Jev mention is an unreleased "Experimental Jev composition" path (`experimental_composeSpec`, `experimental_createEvaluator`). Nothing about the state, questions or thresholds it would send is in the capture. | — |

## Related

- [[ideas/community-repos]] — the index, top picks and vetting checklist; [[ideas/repos-apps]] — data, documents, judging, real-time, markets, replicas
- [[ideas/patterns]] — the patterns these repos share, with fit verdicts; [[ideas/consult]] — "could Jev help this project?"
- [[ideas/field-reports]] — independent evaluations; [[entities/github-repos]] — the official repos

## Sources

- raw/x-repos/INDEX.json and the per-repo captures in this page's frontmatter (metadata + README; 2026-09-20, roundup repos 2026-09-21)
- raw/x/trycua-2101437979180904640.md — only source for trycua/cua's Jev usage
- raw/x/VladTerin-2100448995415863323.md — only source for vlad-terin/jev-browser