08 · 229 projects

Jev for safety & guardrails

Screening messages, tool calls and outputs before they cause trouble. Jev gives a fast, calibrated verdict that can sit in front of every request or agent action.

What Jev decides: Allow, flag or escalate a message, tool call or action.

Projects, newest first

Safety & guardrailssnapifRust crate and CLI that scores one agent tool call against a shipped policy and returns Auto, Review or Escalate, using TypeSafe Jev…GitHub · ★ 2 · snapifSafety & guardrailsjev-sec.github.ioJev IDS website: one flow.GitHub · ★ 2 · jev-secSafety & guardrailsclaudetiquetteClaude Code plugin that rewrites a hostile prompt into a plain request.GitHub · ★ 2 · zahlekhanSafety & guardrailsdsh-backdoor-guardGuard for DeepSeek Harness: every model-requested tool call is judged by a decision model, hosted TypeSafe Jev or a self-hosted LiquidAI d1, before…GitHub · miketako3Safety & guardrailsopencode-auto-classifierOpenCode plugin that sends each shell command, file read, and edit to TypeSafe Jev for typed classifications, then folds those answers into…GitHub · schemaitatSafety & guardrailspi-thunder-guardSafety guard for Pi: before each bash call (and writes outside the repo) TypeSafe Jev must be at least 85% sure the call keeps to a short restriction…GitHub · Mandalorian007Safety & guardrailsagent-on-agent-idsIntrusion detection for tool-using AI agents: a portable judge spec reads your observability traces (Comet Opik today) and flags prompt injection and…GitHub · stanibajSafety & guardrailsbouncer (Faycall1l)Programmable live-chat moderator that applies per-server rules in one System One pass (~30ms).GitHub · Faycall1lSafety & guardrailspi-rm-guardPi extension that auto-approves safe recursive rm commands via a decision model (default typesafe/jev-latest) and defers or denies everything else.GitHub · sdougbrownSafety & guardrailsDubOpen-source link attribution platform that calls typesafe-ai/jev in malicious-link-check.ts before a short link is created, so the URL is gated by a…GitHub · ★ 25kSafety & guardrailsSkill ScannerCisco's security scanner for agent skills added a System One analyzer: it sends the full skill text to POST /v1/systemone as one advisory Noul…GitHub · ★ 2.6kSafety & guardrailspi-verdictMinimal Pi permission gate (allow/ask/deny) with an optional TypeSafe Jev decisions-model classifier adapter.GitHub · ★ 13 · jessetSafety & guardrailsjev-runtime-securityRing Zero Security: runtime security for AI agents, enforced at the kernel layer.GitHub · ★ 11 · ringzerosecSafety & guardrailsEdwardSupervisor for unattended coding agents (CI, overnight runs) that wraps any subprocess with deterministic rules and an optional advisory scorer;…GitHub · ★ 8 · VeridicalTechSafety & guardrailsProfanity CheckerCloudflare Worker that asks Jev on Workers AI for literal profanity in text or usernames and, for usernames, a second Noul for phonetic or look-alike…GitHub · ★ 1Safety & guardrailsR2r JevAgent governance integration where Jev judges two Noul checks per tool call (beyond scope, destructive), an admission policy decides which judgments…GitHub · ★ 1Safety & guardrailsjev-secret-guardClaude Code hook: block known secret formats locally; send masked unknowns to TypeSafe Jev so checks never leak the secret.GitHub · BasmaAbouzied0Safety & guardrailsopenclaw-jev-leakguardOpenClaw outgoing-message guard: TypeSafe Jev (or local Kev) judges content × destination so client names, credentials, and internal details are…GitHub · yousanSafety & guardrailsApproval Judge BridgeOpenAI-compatible /v1/chat/completions proxy that answers an agent host's approval-guardian call with APPROVE, DENY or ESCALATE.GitHubLSafety & guardrailsLaya DemoThe official Laya playground: eight tabs that show choice, score, and noul decisions on ticket triage, phishing, guardrails, RAG filtering,…Site · Convai InnovationsSafety & guardrailsSAP S/4HANA Procurement FraudProof of concept that flags suspicious purchase orders in SAP S/4HANA: ABAP computes risk indicators, a Fiori Elements app sends seven typed…GitHubSSafety & guardrailsSecurity-One 27BSuperagent's security triage model: a continual fine-tune of AutoJev-27B that returns calibrated probabilities for prompt-injection and content…Site · SuperagentSafety & guardrailsawesome-trustworthy-jevJev+Security Resources | Jev+安全相关论文资料集合: Papers, projects, and other resources on Jev trustworthiness, and Jev-based cybersecurity applications.GitHub · ★ 7 · dongtsiSafety & guardrailsjev-comment-triageAsync Jev-powered WordPress comment triage: background spam, scam/phishing, and toxicity moderation that keeps comment submission fast.GitHub · ★ 3 · soderlindSafety & guardrailsjev-injection-guardFind prompt injection in what an AI agent reads (web pages, tool and MCP results) with Jev, and block the source in Claude Code.GitHub · ★ 2 · stas4000Safety & guardrailsDiscord Policy CheckerExperimental Chrome extension that checks your outgoing Discord messages and edits against plain-language policies with TypeSafe Jev and holds…GitHub · kennethwoltersSafety & guardrailsNucleiSniperSecurity-testing pipeline that fingerprints each authorised target and has TypeSafe Jev score every Nuclei template's relevance (0–4) in batches,…GitHub · ★ 23 · MorDavidSafety & guardrailsjev-safety-gatewayGo reverse-proxy in front of LLM backends: extracts user input per request, asks TypeSafe Jev, blocks harmful traffic, passes the rest through.GitHub · ★ 17 · dark-hxxSafety & guardrailspi-automode-classifierAuto mode for the Pi coding agent: built-in rules decide most tool calls, then a classifier model — hosted Jev (e.g.GitHub · ★ 7 · deepu105ESafety & guardrailsEmDash moderates its plugin registry with ClefEvery plugin listing is screened before it appears in the catalog.Site · EmDash CMSSafety & guardrailsjevlineIncident-timeline proof of concept for security analysts: start from one confirmed-malicious process and Jev scores, process by process, which other…GitHub · ★ 40 · tsaleSafety & guardrailsjev-risk-check-providerx402 risk-check provider: TypeSafe Jev typed decisions plus ES256-signed attestations facilitators can verify for agent paymentsGitHub · ★ 12 · caiovicentinoSafety & guardrailspi-reply-guardPi extension that checks each agent reply against installed skills you choose: a classifier — Jev by default (openrouter/typesafe/jev-1.13) — returns…GitHub · ★ 4 · amalavetSafety & guardrailsBilibili noise filter for Firefox (JEV)Firefox (and Chrome) port of littlewindy123/jev-bili-filter: toggles for spoilers, trolling, ads and partisan chants, plus your own one-sentence…GitHub · Ray4AISafety & guardrailsjev-hook-guardStandard-library Python module and example hook implementing the checks a Claude Code hook should run before sending session text to TypeSafe Jev or…GitHub · tsetse012Safety & guardrailspi-safelyPi package that re-implements the core of Claude Code's auto mode for the Pi agent, gating every non-allowlisted tool call through a System One…GitHub · dcowsillSafety & guardrailsJev-ModOpen-source Discord moderation bot where TypeSafe Jev rules detect spam, phishing, harassment, hate, threats and explicit text, with…GitHub · i098Safety & guardrailsTiny BouncerScreens shell commands that LLM agents request in the OpenCode V2 harness: each command goes to TypeSafe Jev (default) for a judgment, and code…GitHub · radupopescuSafety & guardrailsjev-permission-gateA Jev classifier for Claude Code auto mode, built on native mods.GitHub · ★ 29 · madisonrickertSafety & guardrailsdsh-jev-interceptorDeepSeek Harness plugin: TypeSafe Jev risk-classifies tool calls (fail-closed / shadow→enforce) and can score session-reference messages instead of…GitHub · ★ 7 · AskTheWaySafety & guardrailsclaude-refereeClaude Code referee/guard plugin that asks TypeSafe Jev before risky tool actions.GitHub · ★ 6 · ismaildasciSafety & guardrailsreflex (ursuciprian)Pre-execution risk gate and prompt-injection guard for coding agents; optional TypeSafe Jev (or local Laya) for uncovered commandsGitHub · ★ 4 · ursuciprianSafety & guardrailspi-typesafe-approvePi extension that auto-approves routine Bash commands with a System One / Jev decision model and escalates flagged or unsure commands to a human.GitHub · ★ 2 · DavidasxSafety & guardrailsjev-fuseGoverned reverse proxy between callers (Claude Code, MCP, SDKs) and TypeSafe Jev or local Laya: turn probabilities into ALLOW/ASK/DENY-style actions…GitHub · ★ 1 · 0xshikharSafety & guardrailsjev-home-assistant-sentinelA safety boundary for AI-assisted Home Assistant decisions, with explicit policy checks and deterministic state verification.GitHub · ★ 1 · bojansandhausSafety & guardrailsPermitMCPGates MCP agent tool execution with deterministic policy, Jev decisions, explicit human approval, and one-use execution permits.GitHub · ★ 1 · qinpei-devSafety & guardrailspi-jev-eyeUltra-lean supervisor for Pi: zero-token regex guardrails, test verification tracking, and TypeSafe Jev semantic slop gate.GitHub · ★ 1 · bismawySafety & guardrailsCatching colluding agents by reading their chatJev named the colluders 85% of the time.X post · Aditya RaoSafety & guardrailsjev-classifies-botsA jev intelligence layer for event stream to classify the app traffic into human vs aiagent vs seotool vs scraper vs otherautomation with badintent…GitHub · gitcommitshowSafety & guardrailsguardrails-mdBerget AI plugin for opencode, pi and Claude Code (plus a git pre-commit hook) that scores every bash command with a System One decision model…GitHub · ★ 1 · berget-aiSafety & guardrailssystem-one-securityRerunnable security experiments on System One models (TypeSafe Jev, Cloudflare Clef): truncation, injection, poisoning, tripwires.GitHub · ankushchadhaSafety & guardrailsPrompt RejectorMCP server and local HTTPS API that screen prompts, skill files, and MCP tool descriptions before an agent acts: deterministic checks plus TypeSafe…GitHub · ★ 2 · revsmokeSafety & guardrailsAgent GuardClaude Code PreToolUse hook that screens Bash, file edits, and tool calls with Jev risk, policy, and allow-ask-deny judgments before execution.GitHub · ★ 2 · NieXiSafety & guardrailsDsh Auto Review JevDeepSeek Harness approval guardian fork that lets a reviewer model allow, deny, or defer tool requests via chat completion or one System One call…GitHub · ★ 1 · xlennartSafety & guardrailsInstagram Safe FeedChrome proof of concept that sends Instagram post text to Jev and sampled images to Gemini, then overlays a colored border with expandable harm and…GitHub · ★ 1 · Aagamsheth0601Safety & guardrailsJev Agent GuardrailPython guardrail that intercepts agent tool calls, sends agent state plus tool details to Jev, and allows, blocks, or reroutes execution based on…GitHub · ★ 1 · bhanuprakashk90-techSafety & guardrailsMrsecretChrome MV3 extension blurring secrets and PII in-page with instant regex plus a Jev classifier for ambiguous snippets, keeping the rest of the page…GitHub · ★ 1 · vkpdeveloperSafety & guardrailsPi Jev GatePi extension that checks file-mutating tool calls against written rules in constraints.md, asking Jev which rule a change violates and offering…GitHub · ★ 1 · hcl-zSafety & guardrailsSystemOne-ModerationGo moderation service that returns allow, review, or block with per-class reasons over HTTP or RabbitMQ, backed by Jev with a versioned JSON policy…GitHub · ★ 1 · AliAkbariAlashtiSafety & guardrailsJEV-Dual-Spectrum-Phishing-GuardianJapanese-focused phishing analyzer scoring messages on classic pressure tactics and GenAI tells, with a 0-100 threat gauge and report export.GitHub · YuyaForestSafety & guardrailsJEV-Prompt-Injection-GuardianTypeScript dashboard that scores prompts with Jev Choice, Score, and Noul, maps scores to block-through-allow actions, and falls back to Gemini or…GitHub · YuyaForestSafety & guardrailsScoring support calls for policy breaksSean Brownell scores sample call transcripts in a harness, including a case where the agent reads out card details, and compares that pass with a…YouTube · Sean BrownellSafety & guardrailsHermes JevAsync supervisory layer for Hermes Kanban workers: locked DoD contracts, evidence tracking, budgeted trajectory checks, and Jev only for unresolved…GitHub · ★ 41 · keeltraceSafety & guardrailsDsh Jev — buberloJev decision layer for DeepSeek Harness that narrows visible tools, gates risky calls, guards retry loops and routes models, with Jev permitted only…GitHub · ★ 25 · buberloSafety & guardrailsPi-Jev-GuidePi guard plugin that checks inputs and tool calls with local rules plus Jev semantic judgements, with redaction and verification reminders.GitHub · ★ 21 · zszz3Safety & guardrailsJev DecisionsHermes plugin that puts an agent's plans, drafts and claimed completions up for review — plan_review, evidence_review, action_verify — plus local…GitHub · ★ 3 · bojansandhausSafety & guardrailsJev IdsIntrusion detection that puts one NSL-KDD flow plus five labeled examples into a single Jev request, asking an is_attack probability and a category…GitHub · ★ 3 · jev-idsSafety & guardrailsOpen Jev ApprovalsApproval gate for Claude Code where hooks send each tool call to Jev and a local policy returns allow or deny without changing the harness model,…GitHub · ★ 3 · alexj11324Safety & guardrailsRh GuardHook-level gate for coding agents that watches tool use for grader tampering, hidden-test edits, and eval-process interference, steering toward…GitHub · ★ 3 · 24601Safety & guardrailsTripwireTypeScript guardrail that puts seven Jev checks in front of an AI SDK model or an OpenAI-compatible endpoint, blocks on high-confidence hard checks,…GitHub · ★ 3 · noelzappySafety & guardrailsJevGuardClaude Code / Codex plugin that turns project rules (from CLAUDE.md / AGENTS.md) into typed Jev checks on PreToolUse and Stop hooks, so the agent…GitHub · ★ 2 · Jhonnyr97Safety & guardrailsTypeSafe AI FirewallShadow-mode validation of a pre-execution firewall that batches five typed Jev hazard questions plus a blast-radius score into one call, leaving…GitHub · ★ 2 · AnshChoudharySafety & guardrailsbarmkin-modClaude Code mods security layer: secret redaction on every tool call, untrusted-content taint tracking with an injection screen and a Rule-of-Two…GitHub · ★ 1 · samfrmrSafety & guardrailsProgressgateAn npm package that supervises a running agent: one Jev systemOne call per check returns six semantic signals about recent steps, and a deterministic…GitHub · ★ 1 · AshutoshVJTISafety & guardrailsjev-supervisorDeepSeek Harness macOS plugin that supervises agent execution with TypeSafe Jev decisions and budgets.GitHub · ryyyzerSafety & guardrailsScamCheckPaste a suspicious message and get a scam verdict and risk score: one TypeSafe Jev call answers about eleven typed questions, and code can only raise…GitHub · AkashNaickarSafety & guardrailsyour-cto-jevSharp-tongued CTO agent hook that uses Jev to block leaked secrets and destructive commands from coding agents.GitHub · raindaySafety & guardrailsjev-llm-guardContextual OWASP LLM Top 10 guardrail powered by TypeSafe Jev, with a Turkish interactive demo.GitHub · ★ 14 · gulbakiSafety & guardrailsskill-scannerOffline static analysis for Agent Skills (prompt-injection, exfil, hidden text) before install; optional TypeSafe Jev second opinion.GitHub · ★ 3 · FrancoisChastelDSafety & guardrailsDetecting compromised AI coding agents with Jev and GryphHacker News link to SafeDep's write-up on Gryph telemetry plus narrow Jev yes/no checks against developer policy.GuideSafety & guardrailsdsh-jev-loopTypeSafe Jev judgments at DeepSeek Harness agent-loop gates (no UI dependency).GitHub · JWE24-codeSafety & guardrailshak-jev-pluginHedera Agent Kit policy plugin: TypeSafe Jev gates sensitive tool calls (v0: SaucerSwap swaps) before sign; decisions notarized to HCS.GitHub · jmgomezlSafety & guardrailsjev-tools (CMaintz)TypeScript tools on TypeSafe Jev: agent tool-call guardrail and related decision helpers.GitHub · CMaintzSafety & guardrailsLeashJev-powered coding-agent guardrail that judges each turn against un-lintable project rules with a one-way accepted-debt ratchet.GitHub · CMaintzSafety & guardrailsjev-copsContext-aware tool-call policing for coding agents with graduated Jev-backed verdicts (allow→kill).GitHub · FrancoisChastelDSafety & guardrailsDetecting compromised coding agents with JevKunal Singh records coding-agent actions with Gryph and asks Jev yes-or-no questions against a short profile of how that developer usually works.Guide · Kunal SinghJSafety & guardrailsJev DetectorA no-login page that scores pasted prose sentence by sentence with Jev, using a 0–4 style rubric, and highlights only the sentences that cross its…SiteJSafety & guardrailsJevditA link-and-discussion site run by Tom Nick.Site · Tom NickJSafety & guardrailsJevdit on Hacker NewsTom Nick's Show HN for a discussion site where Jev moderates every post, with a link to the irony-detection write-up.Guide · TN1ckSafety & guardrailsjev-agent-kit (nanoDBA)Give your coding agent a second opinion on risky tool calls—TypeSafe Jev as an evidence layer (shadow by default).GitHub · ★ 1 · nanoDBASafety & guardrailsjev-pi (weiping)Jev for pi: TypeSafe System One judgments in the agent loop—permission gate, output ladder, conditional context, agent router.GitHub · ★ 1 · weipingSafety & guardrailsjev-guard (rudra72r)Fast, cheap guardrails for LLM apps powered by TypeSafe Jev (with offline try path).GitHub · ★ 1 · rudra72rSafety & guardrailsjevshBash wrapper: TypeSafe Jev scores shell command risk (LOW–CRITICAL) before you confirm run.GitHub · takeshiueSafety & guardrailslaya-guardrailsSelf-hosted Laya System One guardrails—typed checks instead of LLM-as-judge.GitHub · javimp2003Safety & guardrailslaya-packet-analyserReal-time or pcap network security analyser: deterministic packet detectors plus a second opinion from a local Laya (Jev-compatible POST…GitHub · esterhuizenSafety & guardrailsautomater.aiMCP tools the agent can skip are not a gate.Site · AutomaterSafety & guardrailsI think models like Jev are the future of intelligent,…I think models like Jev are the future of intelligent, automated, cyber defense...X post · JhaddixSafety & guardrailsjev-guard (klauswg)Real-time risk triage gateway for exchange deposits/withdrawals: TypeSafe Jev answers risk/pattern/freeze questions; Java code owns hard rules,…GitHub · ★ 36 · klauswgSafety & guardrailsjev-agent-authorizationKinde starter: identity + permissions, then TypeSafe Jev typed gate before every MCP tool call — allow, step-up approve, or stop.GitHub · ★ 5 · kinde-starter-kitsSafety & guardrailsjev-pilotFast System-1 Decision, Arbitration & Safety Engine for Autonomous AI Agents (Powered by TypeSafe Jev).GitHub · ★ 5 · h0j5bz0adh0-stackSafety & guardrailsjev-sap-commerceSAP Commerce (jevintegration) extension: TypeSafe Jev moderates product reviews and suggests categories with dry runs, audit records, and human…GitHub · ★ 5 · EmenowiczSafety & guardrailsA CAPTCHA rebuilt with JevThe browser measures how you fill the form.X post · Jarek CeborskiSafety & guardrailsAn agent-agnostic permission gateJev and hooks, so a dangerous command asks first.X post · ImRobotSafety & guardrailsjev-cloud-cost-guardianGitHub Action FinOps gate: normalize cloud cost evidence, ask TypeSafe Jev for a typed approve / warn / block / manual-review decision, then apply…GitHub · JevForgeSafety & guardrailsjev-x-filterChrome MV3 extension that filters X (Twitter) timeline spam with TypeSafe Jev typed decisions across six toggleable classes; high confidence only…GitHub · harodgggSafety & guardrailsjev-model-tokengateStreaming LLM proxy that holds tokens in a sliding buffer, runs semantic safety criteria (TypeSafe Jev by default) on each window, and releases or…GitHub · ★ 4 · Thanh-Mathieu95Safety & guardrailsgrok-jev-guardTyped preflight/approval layer for Grok Bot: local policy owns hard boundaries; TypeSafe Jev judges ambiguity; the agent executes only inside the…GitHub · ★ 2 · 0xwhrariSafety & guardrailsopencode-jev-guardOpenCode 2 plugin: every local shell (and FarHand remote shell) command is judged by TypeSafe Jev before run—overall verdict plus host-litter /…GitHub · ★ 2 · CogFluxSafety & guardrailsJuardrailsGo guardrails management service for TypeSafe Jev: define Choice/Score/Noul policies in YAML or a UI, batch questions into one provider call, then…GitHub · ★ 1 · abhaybhargavSafety & guardrailsA phishing message detectorTypeSafe Jev checks messages for phishing.X post · choroshinSafety & guardrailsEvery rule checked in 348 msJev reads each Claude Code reply and edit against the rules you wrote.X post · erkamyaman_ngSafety & guardrailsJev blocks a $50,000 transfer95% irreversible risk and 94% sensitivity, so it refused.X post · fluixooSafety & guardrailsJev finds the sensitive files in a shareA security researcher picks out risky files with Jev.X post · _xpn_Safety & guardrailsJev ModerationTypeScript and Python SDKs for text moderation with TypeSafe Jev: a bundled, versioned community policy or your own filters, each rule compiled to a…GitHub · abishakkodiSafety & guardrailsJev_validation_agentPython Jev Guard (jev_guard): double-check LLM answers with TypeSafe Jev Noul/Score/Choice checks (on-topic, contradicts-source, format) before…GitHub · omkarchougule19Safety & guardrailsJevGuard (blacksinisterx)Agent tool-execution security layer: hard-rule prefilter, then TypeSafe Jev allow/review/block (distinct from catalog leepokai/CMaintz/klauswg…GitHub · blacksinisterxSafety & guardrailsOpenCode Security GuardLinux OpenCode shell permission guard: local command check plus TypeSafe Jev read-only score ≥ 0.90 for auto-allow (ask otherwise; deny stays final).GitHub · koppertSafety & guardrailsRegret CheckChrome extension that pauses you before commit-like clicks you might regret: a local server scores the page action with TypeSafe Jev (via OpenRouter)…GitHub · daniloceciliaSafety & guardrailsSpamGuard (tb-spam-guard)Thunderbird MailExtension (Manifest V3, Thunderbird 128+) that scores incoming mail with language-independent header rules (display-name vs…GitHub · Helicon1968Safety & guardrailsTesting Jev for prompt injectionA demo that shows how to test prompt injection against Jev.X post · Frank ChenSafety & guardrailsjev-chat-jarvis-macA macOS overlay that judges message intent and risk, then drafts.GitHub · ★ 388 · jev-chatSafety & guardrailsjev-edgeTyped-judgment admission control at the traffic edge: three-layer prompt-injection and abuse filter for nginx/OpenResty, powered by TypeSafe Jev.GitHub · ★ 35 · kiwi0719Safety & guardrailsjev-idsJev IDS is a network intrusion detection experiment that shows Jev one network flow plus a few labeled examples and gets back whether the flow is an…GitHub · ★ 19 · jev-secSafety & guardrailsjev-guard (muratcakmak)Claude Code plugin with PreToolUse-style hooks that combine local regex rules and batched TypeSafe Jev noul scores to deny rule-breaking edits and…GitHub · ★ 7 · muratcakmakSafety & guardrailsjev-harness (ismaelsoilet)Zero-dependency System One decision harness: 5 semantic gates saving frontier AI agent tokens on trivial errors & doom loops.GitHub · ★ 7 · ismaelsoiletSafety & guardrailsjevcCompile natural-language agent rules (and JSON Schema) into TypeSafe Jev programs: narrow typed questions plus a code-owned reducer/verdict you can…GitHub · ★ 6 · doronpSafety & guardrailstoxic-filterChosen expressions on X get blurred out.GitHub · ★ 5 · eijiarakiSafety & guardrailsclaude-jev-pluginTypeSafe Jev semantic guardrails for Claude Code.GitHub · ★ 2 · dr-dimitruSafety & guardrailsagy-jevgateFail-closed Antigravity (agy) PreToolUse hook for run_command: exact read-only fast-pass, a short static destructive guard, then TypeSafe Jev risk…GitHub · catpotdSafety & guardrailsjev-cmdline-classifierPortable agent skill plus stdlib Python/JS reference that classifies shell commands with TypeSafe Jev Choice into allow / prompt / forbidden for…GitHub · liodaliSafety & guardrailsjev-guard (CMaintz)Framework-agnostic TypeScript guardrail that vets proposed agent tool calls with TypeSafe Jev (score/noul dimensions → allow/block/hold), plus…GitHub · CMaintzSafety & guardrailsjevgate (craxrev)Claude Code plugin: before Bash/Write, TypeSafe Jev reports risk facts; fixed rules allow, ask, or deny—aimed at bypassPermissions mode.GitHub · craxrevSafety & guardrailsmayiPermission gate for Claude Code, Cursor, and Codex: TypeSafe Jev scores each shell/file/MCP tool call before it runs; routine work passes silently…GitHub · AidenHadisiSafety & guardrailstwitter-jev-guardLow-quality, spam and ad posts get a translucent watermark.GitHub · ★ 9 · qs-lllSafety & guardrailsdsh-jev-toolsJudgment, not generation, inside DeepSeek Harness.GitHub · ★ 6 · HorusJiangSafety & guardrailsagi-jev-containmentAGI JEV Detection — local AI agent monitor: chain-level malicious-agent detection (TypeSafe Jev + Sentinel), escalate-only L1–L5 containment, Neo4j…GitHub · ★ 4 · carlosedm10Safety & guardrailstweet-911Real-time AI / solicitation / parrot-bot scores for X posts and replies.GitHub · ★ 3 · elliothuxSafety & guardrailsB站降噪 · JEV (Bilibili noise filter)Original Chrome/Edge extension (Chinese, with English README) that filters Bilibili comments and plain-text danmaku on the page with TypeSafe Jev:…GitHub · ★ 3 · littlewindy123Safety & guardrailsjevshieldPython runtime security gate for agent tool calls: TypeSafe Jev Choice/Noul/Score dual-factor evaluation with fail-closed parsing,…GitHub · ★ 2 · lgy1027Safety & guardrailsjev-firewallReal-time firewall for AI coding agents: a PreToolUse hook checks every Claude Code / Codex tool call with deterministic shell-aware rules, and…GitHub · ★ 1 · Koushik890Safety & guardrailsA confidence badge on every postPosts on screen classified live as scam, slop or neither.X post · tanavtwtSafety & guardrailsslop-graderA CLI that audits text against your own rulesets.X post · VintuxaiSafety & guardrailsUXRayA screen overlay that flags manipulative interface patterns.GitHub · Mohammad ZohaibSafety & guardrailsagent-chaperoneScreen an agent's tool calls with Jev before they run.GitHub · ★ 21 · agent-chaperoneSafety & guardrailsjev-belayClaude Code Stop hook that blocks an unverified done: reads the transcript for evidence, asks Jev once, fails open on everything else.GitHub · ★ 18 · valentynkitSafety & guardrailspi-jev-sentinelPi coding-agent extension: TypeSafe Jev checks for tool calls, tool outputs and replies (prompt injection, approvals, secret scrubbing, task pinning).GitHub · ★ 9 · harshwasanSafety & guardrailsgg-friggin-ezFast, drop-in profanity and toxicity screener for Node.js, powered by TypeSafe AI Jev.GitHub · ★ 7 · ItisShikharSafety & guardrailsconstruct-auto-classifierEffect-based safety gate for AI coding agents' shell commands (OpenCode, Antigravity): fast structural rules, then TypeSafe's Jev or a chat model…GitHub · ★ 3 · godspedeSafety & guardrailsJev-AVAntivirus scanner and real-time defense sentinel: extracts structural features from executables, scripts, and documents (entropy, hashes, strings, PE…GitHub · ★ 2 · newuser7171Safety & guardrailsjev-pii-checkerCLI that scans text and files for PII with TypeSafe Jev presence/sensitivity judgments plus regex and segmentation layers, emitting JSON or tables…GitHub · ★ 2 · coo-quackSafety & guardrailstoolgate (RiskAverseTech)Open tool-call firewall for AI agents: static rules first, then TypeSafe Jev risk judgments, shipping as a Claude Code PreToolUse hook and an MCP…GitHub · ★ 2 · RiskAverseTechSafety & guardrailsactiongate-jevRuntime authorization and guardrails for AI-agent tool calls with deterministic policy and TypeSafe Jev via OpenRouter.GitHub · ★ 2 · omkarghugarkar007Safety & guardrailsstepwardenEvery tool call your agent makes, checked before it runs.GitHub · ★ 2 · getexcitedSafety & guardrailsjev-crawlersBug-hunting crawlers built from five Unix-style primitives.GitHub · ★ 1 · russfrankySafety & guardrailspi-jev-permitPi coding-agent extension that asks TypeSafe Jev whether each bash / write / edit call should run, after local hard-deny, allow/deny rules, and a…GitHub · ★ 1 · kurihadaSafety & guardrailsjev-gatesSix hook gates for Claude Code that catch broken rules, out-of-scope edits, unfinished asks, and false claims, each judged by Jev against a fixed…GitHub · rashedInt32Safety & guardrailsLangChain's Jev tool-call gateTool output stays out of the classifier's input.Guide · Yurii OksamytnyiSafety & guardrailsCitation checksTest a claim against a supplied source passage.Guide · TypeSafe AISafety & guardrailsJev Call ScreenerOpen-source call-screening backend: ask why the caller is calling, classify the transcript with TypeSafe Jev, and forward or reject under a fail-open…GitHub · SuchintKSafety & guardrailsjev_antispam_botA Telegram bot that deletes only the spam Jev is sure about.GitHub · ★ 11 · backmeupplzSafety & guardrailspi-jev-sentinelAdd TypeSafe Jev checks for coding-agent tool calls, tool outputs, and replies—shipping as a Pi extension plus a shared Claude Code / Codex CLI hook.GitHub · ★ 9 · harshwasanSafety & guardrailsmastra-jev-moderationInput moderation for Mastra agents in one file.GitHub · ★ 4 · CodeAlive-AISafety & guardrailsjev-decisionsPlugin that gives the Hermes agent (and other AI agents) Jev-backed review tools: tool-risk reviews, human-approval recommendations, checking answers…GitHub · ★ 3 · bojansandhausSafety & guardrailsclear-headClaude Code Stop hook that checks factual claims in the assistant’s answer against what it actually read this session, using TypeSafe Jev as the…GitHub · ★ 2 · VladyslavHontarSafety & guardrailsBouncerA judgment layer that checks every Claude Code tool call against your policy.GitHub · ★ 1 · ClownwareSafety & guardrailsdsh-auto-review-jev (sperictao)DeepSeek Harness Auto-permission plugin: TypeSafe Jev reviews each tool call, with inline usage and API-key settings.GitHub · ★ 1 · sperictaoSafety & guardrailsResponsible AI HarnessModel-agnostic assessment harness: deterministic hard rules plus an optional TypeSafe Jev judge for prompt injection, secret/PII leakage, unsafe tool…GitHub · ★ 1 · syabdulrSafety & guardrailsfirehose-judgeThe live Bluesky firehose, judged post by post, with a lane for humans.GitHub · Leo MataSafety & guardrailsInterlockA gate on every agent tool call, with Jev as one of its sensors.GitHub · somooreSafety & guardrailsjev-gatesComposable three-valued semantic logic circuits: small TypeSafe Jev (or LocalJev) judgments become explicit TRUE/FALSE/UNKNOWN signals, combined with…GitHub · carlchou0dailyfreshSafety & guardrailsjev-prompt-sentryIngress reverse proxy for Anthropic Messages: one batched TypeSafe Jev call screens jailbreaks, indirect injections, and exfil risk before the…GitHub · ca7aiSafety & guardrailsis-maliciousA codebase scanner that helps you not run malicious code.GitHub · ★ 26 · luantakSafety & guardrailshermes-jev-approvalsPoC: TypeSafe Jev as the reviewer for Hermes Agent smart command approvals.GitHub · ★ 16 · anpicassoSafety & guardrailsjevcalChoose acceptance thresholds from labeled examples.GitHub · ★ 11 · abhixhekSafety & guardrailsspecpi-jev-guardPi coding-agent extension: local deny/fast-pass rules first; uncertain shell/file commands are scored for danger by TypeSafe Jev via OpenRouter…GitHub · ★ 9 · TannerMiddSafety & guardrailspi-heedChecks every side-effecting tool call against what you asked for.GitHub · ★ 8 · NyarlathotepppppSafety & guardrailsclaude-code-jevExperimental Claude Code PreToolUse permission gate that classifies each tool call as allow / block / ask with TypeSafe Jev via OpenRouter’s typed…GitHub · ★ 4 · RahulBalakaviSafety & guardrailsjev-guardI built "jev-guard", an auto-approval layer for Claude Code / Codex / Antigravity agent harnessesGitHub · ★ 3 · sudo rm -rf /*Safety & guardrailsJeevesI added twitch moderation to so you can set actions like ``` !setaction ban users if they harass others !setaction time a user out for 1 week if they…GitHub · ★ 1 · JustSomeDevJSafety & guardrailsjevmodModeration with a probability per category and thresholds you set.GitHub · ohernandezdevSafety & guardrailsMade a real-time slop detector with jev as you scrollMade a real-time slop detector with jev as you scrollX post · RBilgilSafety & guardrailsPi WardenFlag risky actions and unverified completion.GitHub · ★ 143 · DevMortimerSafety & guardrailsJev Moderation BotScreen Discord messages and escalate concerns.GitHub · ★ 48 · brainstormitySafety & guardrailsjev-guardSecurity hook for coding agents: TypeSafe Jev risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in…GitHub · ★ 34 · leepokaiSafety & guardrailszod-jevAdd meaning-based checks to shape validation.GitHub · ★ 9 · jomatsuSafety & guardrailsJev ShieldCheck MCP calls, outputs, and tool descriptions.GitHub · ★ 4 · caiovicentinoSafety & guardrailsJodCombine local schemas with typed model judgments.GitHub · ★ 4 · mateonunezSafety & guardrailspi-typesafe-jevA pi extension that exposes TypeSafe (Jev, System One) judgments as five pi tools, so a model can make narrow semantic judgments while your code and…GitHub · ★ 4 · legacybridge-techSafety & guardrailsjev-audio-beeperLow-latency audio censorship POC using Jev typed decisions and ffmpeg.GitHub · ★ 3 · santos-sanzSafety & guardrailsjevegisGuardrails for LLM apps in one API call.GitHub · ★ 3 · 0xArxSafety & guardrailstoolgateAgent tool/MCP call gate — allow / ask_human / deny via TypeSafe Jev.GitHub · ★ 3 · ndolinschiSafety & guardrailsguard-jevComment-moderation playground: paste a comment, Jev decides what to do with it.GitHub · ★ 2 · NorbertBodzionySafety & guardrailsproject_blackoutBuilt a simulated SIEM to showcase Jev's risk assessment capabilities.GitHub · ★ 2 · DataSherpaSafety & guardrailsAgent Handoff GateReview evidence before an agent hands work off.GitHub · ★ 1 · zsoXiSafety & guardrailsCheck RiskRecommend checks for a proposed code change.GitHub · ★ 1 · moezubairSafety & guardrailsSwitchboardExplore model routing alongside safety checks.GitHub · ★ 1 · aniruddh-krovvidiSafety & guardrailscartshieldCartShield — SMB checkout fraud disposition via TypeSafe Jev.GitHub · ★ 1 · ndolinschiSafety & guardrailsomp-jevens-classifierJev-powered model-judged permission gate for OMP (TypeSafe System One).GitHub · ★ 1 · STRMLSafety & guardrailspkg-gatePre-install security gate for npm lifecycle scripts using TypeSafe System One.GitHub · ★ 1 · hemanthSafety & guardrailsscam-shieldScam text message filter powered by TypeSafe's Jev model.GitHub · ★ 1 · ShupingRSafety & guardrailsspendbrakeAgent budget brake — continue / downgrade_model / stop via TypeSafe Jev.GitHub · ★ 1 · ndolinschiSafety & guardrailstrustgateTrustGate — indie media T&S gate via TypeSafe Jev.GitHub · ★ 1 · ndolinschiSafety & guardrailsJev as an agent safety monitorChecks each agent action first: most attacks caught, almost no false blocks.X post · NickSafety & guardrailsTypeSafe TypewriterSixteen judgments about your text, asked again on every keystroke.Site · Steve KrouseSafety & guardrailsAgentgateway exampleAdd a Jev check at an agent gateway.GitHub · agentgatewaySafety & guardrailsFraud detection with Jev and Kimi K3Jev sorts 100 emails in 1.42 s and sends the unsure ones to Kimi K3.X post · HassanSafety & guardrailsJev DetectorAn AI slop detector built on Jev, scanning about 10,000 words in 2 seconds.X post · Jozef GhermanSafety & guardrailsKassad.NET LLM guardrails: TypeSafe Jev typed checks return Allow/Flag/Review/Block with calibrated confidence (ASP.NET middleware).GitHub · jacob-berendsohnSafety & guardrailssecond-thoughtterminal seatbelt on Jev — judges shell commands before Enter, ~$0.000001/check, blocks past 85% confidenceGitHub · ★ 4 · rodriveigaSafety & guardrailsJev for security engineeringKostas on threat hunting with Jev: define the questions and outputs, then rank, score and classify activity at scale.X post · KostastsaleVSafety & guardrailsVercel fx: Jev as a command safety reviewerGuillermo Rauch: Jev reviews every fx command, faster and more accurate than a chat model.X post · Guillermo RauchSafety & guardrailsLLM guardrailsEvaluate incoming and outgoing messages.Guide · TypeSafe AISafety & guardrailsHeimelHEIMEL solves a simple problem: agents can decide and plan, but something still has to control what actually happens.GitHub · ★ 6 · NjaalSafety & guardrailsbeam-cli (AgentBeam)Local AgentBeam CLI (beam): installs native hooks for detected coding agents, captures agent/MCP activity, applies policy locally, and optionally…GitHub · ★ 11 · whyashthakkerSafety & guardrailsagent-control-planeSharing what I'm building: ZIFFER, a deterministic authorization layer for AI agents.GitHub · ★ 7 · Yacine "ZIFFER"Safety & guardrailsdigital-twinsHey! For the past few months I've been building simulated sandboxes as an approach to buid safer ai agents.GitHub · ★ 20 · hadesSafety & guardrailsrippyRust shell-command safety hook for AI coding tools; a separate opt-in rippy-jev build can ask Jev to approve only commands rippy is unsure about,…GitHub · ★ 6 · mpecanSafety & guardrailsModels are getting smarter.Models are getting smarter.GitHub · ★ 89 · ThibautSafety & guardrailsBlackroseTypeSafe System One decision layer that returns allow/review/block before/after LLM generation.GitHub · ★ 6 · Dino-KupinicSafety & guardrailsexample.com** Jev CLI is out** <a:elmo_fire:1549940287235686410> `jev` puts TypeSafe's Jev model on the command line.Site · NasrSafety & guardrailslesswrong.comHi everyone, I just wrote up a small experiment testing TypeSafe’s Jev as a trusted and cheaper monitor alternate for AI Control.Site · venkatSafety & guardrailspi.devim using jev as a fast judgement layer for the agent; checks each tool call (irreversible?Site · devmortimer24Safety & guardrailsJev as a terminal guardrail.Jev as a terminal guardrail.Site · lampSafety & guardrailsJev Content GuardA Manifest V3 Chrome extension that filters fraud, advertising, AI slop, spam, clickbait, "info-gypsy" schemes, and toxicity from web pages using…Site · serejkaaa512JSafety & guardrailsJev-Mod (undeemed)Jev-powered Discord moderation with configurable TypeSafe rules, hosted dashboard, and Cloudflare/Docker self-host optionsSite · undeemedSafety & guardrailspi-typesafe-bash-guardPi coding-agent extension that classifies every bash tool call and user !GitHub · gowthamgtsSafety & guardrailsSoterAutomated Discord moderation: TypeSafe Jev (OpenRouter Decisions) scores hate speech and spam per message; code deletes clear hits, flags borderline…Site · frolleksTSafety & guardrailsTG-SpamSelf-hosted Telegram anti-spam bot and Go library (maintained since 2023); its optional Jev provider asks one typed spam question (plus an optional…Site · umputunSafety & guardrailsWatermelonStatus-update honesty auditor: paste a weekly program update; TypeSafe Jev judges language while local code parses dates/slippage; the app returns…Site · shashwatc12

Other use cases

Agents & browsers 299Coding & code review 450Routing & model choice 348Context & memory 117Search & RAG 108Data & extraction 98Documents & research 45Support & inbox 81Marketing, sales & social 120Trading & finance 77Games & real time 256Creative & generative UI 69Home, robots & devices 31Everyday apps 176SDKs & integrations 625Benchmarks & research 682Guides & docs 342