aionedge.
Jev project category

Security & Guardrails: open source Jev projects

Guardrails that put a fast judgment in front of risky actions: prompt-injection and jailbreak checks, command-risk reviews, content filters and commit checks. The good ones keep the final block or allow decision in ordinary code.

Projects
23
Jev code linked
12
Common languages
Python, TypeScript, Rust, Go

Where to start

agentgatewayagentgateway/agentgatewayJev scores jailbreaks, harmful content and secret disclosure; thresholds or evaluation errors reject requests.★ 4,986 · Jev code linkedAgentAgentiLoop/AgentAdds a destructive-risk judgment after local shell checks and refuses commands above the configured threshold.★ 629 · Jev code linkedjev-experimentsdabit3/jev-experimentsJudges risks such as exposed credentials or destructive changes; local rules warn or block a commit.★ 369 · Jev code linked

All 23 Security & Guardrails projects

Sorted by GitHub stars, which belong to the whole repository rather than its Jev integration.

  1. litellmBerriAI/litellmAI gateway with a TypeSafe guardrail and Jev classifier for policy judgments and complexity-based request routing.★ 59,424
    Python
  2. dubdubinc/dubThe open source link-attribution platform, which runs a Jev check as part of its malicious-link screening.★ 24,818
    TypeScript
  3. agentgatewayagentgateway/agentgatewayA Jev guardrail example in Agentgateway using a webhook to inspect model requests and responses.★ 4,986
    Rust
  4. AgentAgentiLoop/AgentAn optional Jev command-risk advisor inside a native macOS Agent, with a TypeSafeKit client.★ 629
    Swift
  5. jev-experimentsdabit3/jev-experimentsA collection of Jev developer-tool experiments, including Commit Sentry for semantic checks on staged diff hunks.★ 369
    TypeScript
  6. captaincoreCaptainCore/captaincoreJev commands in the WordPress toolkit CaptainCore answer structured questions and prioritize malware scanner findings for review.★ 71
    Go
  7. jevalsopenlayer-ai/jevalsFramework-agnostic agent evals and guardrails that batch a trace's checks into one request to Jev, Kev, Laya, or a chat-model fallback.★ 63
    Python
  8. jev-tool-permissionsNicolasMontone/jev-tool-permissionsAdds tool-call approval and tool-list pruning to the Vercel AI SDK.★ 5
    TypeScript
  9. EdwardVeridicalTech/EdwardEdward — external control plane for AI coding agents: deterministic guardrails + local semantic scorer + resumable interventions.★ 5
    Python
  10. jev-block-android-adufec/jev-block-android-adAn Android notification and SMS filter that applies local OTP rules before asking Jev whether a message is advertising noise.★ 5
    Kotlin
  11. oc-pluginsOpeOginni/oc-pluginsThe oc-auto-perms plugin in an OpenCode plugin collection uses Jev to check tool intent against natural-language rules.★ 4
    TypeScript
  12. jevgateTech-Byte-Frontier/jevgateCode-review gate for CI and coding agents: asks TypeSafe Jev small typed questions about functions, files, tests and docs, and reports findings with locations and probabilities.★ 4
    Rust
  13. jev-shieldcaiovicentino/jev-shieldSemantic MCP firewall powered by Jev — screens every tool call, tool result, and tool description with calibrated System One verification. 94% block recall, 0 false positives, ~$0.00002/check.★ 3
    JavaScript
  14. typesafe-ai-firewallAnshChoudhary/typesafe-ai-firewallShadow-mode validation harness for a pre-execution firewall on AI agent tool calls (TypeSafe/Jev). Real run, findings in report.md. No repository-level license file was found during review.★ 2
    Python
  15. jev-sec-benchGaurav-Gosain/jev-sec-benchBlind security benchmarks for Jev, TypeSafe's System One model: prompt injection and vulnerable code detection, built on jev-go.★ 2
    Go
  16. jev-cvssRed5d/jev-cvssScripts that use Jev to select CVSS metrics from vulnerability descriptions, then compute v3.0, v3.1 or v4.0 scores in Python.★ 2
    Python
  17. jev-pii-checkercoo-quack/jev-pii-checkerA CLI that sends text to TypeSafe Jev for PII category Nouls and a sensitivity Score, then locates spans with regex and segmentation.★ 2
    TypeScript
  18. jev-screen-mcpjiawei686/jev-screen-mcpSingle-purpose MCP server (one tool, one job): a content-moderation gate powered by TypeSafe Jev (System One decision model).★ 1
    TypeScript
  19. jevegis0xArx/jevegisGuardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT.★ 0
    TypeScript
  20. jev-policy-engineBhavinM/jev-policy-engineJev Policy Engine is the first universal Policy-as-Code SDK built for TypeSafe AI's Jev System One model. It allows RevOps, DevOps, and Security teams to define strict, deterministic AI governance rules in YAML, and execute them at high speed.★ 0
    Python
  21. switchboardaniruddh-krovvidi/switchboardGuardrail + model router for LLM gateways on TypeSafe's Jev (System One model), with an independent accuracy/calibration/latency evaluation. Stdlib Python.★ 0
    Python
  22. pi-jevkurowashi/pi-jevPi extensions using Jev for semantic checks on file edits and placement of new files.★ 0
    TypeScript
  23. approval-judge-bridgeoppih/approval-judge-bridgeOpenAI-compatible judge endpoint for agent approval gates: typed judgements (Jev), any OpenAI-compatible model, or a rule file — fail-closed, calibrated, with a replay battery.★ 0
    Python

Related categories