Projects tagged with “ai-safety”
Browse Jev GitHub projects tagged with ai-safety. Filter, sort and explore their source repositories.
- 221jev-harnessA custom coding harness for TypeSafe AI's Jev: an LLM proposes, Jev answers narrow questions, code decides, every step leaves a receipt.
TypeSafeAI/jev-harness · TypeScript
3912agent-harnessagentic-codingai-agentsai-governanceai-safetycode-reviewcoding-agents - ⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. Fail-closed by construction. dsh 生态第一个 System-1 决策插件
AskTheWay/dsh-jev-interceptor · TypeScript
334agent-harnessagentic-aiai-agentsai-safetydecision-modeldeepseekdeepseek-harness - opencode plugin: a System One decision model judges every bash command before it runs — destructive / credentials / your guardrails.md policy
berget-ai/guardrails-md · TypeScript
143ai-safetyguardrailsopencodeopencode-plugintypescript - Doom or Bloom: map your AI worldview and compare it to others.
transitive-bullshit/doom-or-bloom · TypeScript
90ai-futuresai-risksai-safetyworldviewtypescript - 479jevcCompile agent policy prose into deterministic verdict programs: narrow evidence questions for the model, the verdict computed in code. Install: npm i -g jev-compiler
doronp/jevc · TypeScript
90agent-securityai-agentsai-safetyai-sdkclaude-codecli - 646jevshieldSub-100ms security gate for AI agent tool calls, powered by TypeSafe's Jev (System-1) decision model. Single-request Choice/Noul/Score evaluation, dual-factor blocking matrix, calibrated-confidence routing, fail-closed parsing, zero-config local fallback. LangChain-ready.
lgy1027/jevshield · Python
50agent-securityai-agentsai-safetyguardrailslangchainllm-securitymiddleware - 707jev-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.
caiovicentino/jev-shield · JavaScript
40javascriptai-safetymcpprompt-injection - 859ohmyjevJev, batteries included, for Claude Code, Codex, pi and omp: no permission prompts for safe commands, long output trimmed, the right skill loaded, and destructive commands (rm -rf, force push) or data exfiltration stopped until you say yes.
novacon/ohmyjev · TypeScript
31agent-securityai-agentsai-safetyanthropicbypass-permissionsclaudeclaude-code - Open-source Jev tool-calling authorization gateway for AI agents: deterministic policy, exact-action single-use permits, MCP and HTTP enforcement.
omkarghugarkar007/actiongate-jev · TypeScript
20agent-securityagentic-aiai-agentsai-guardrailsai-safetyauthorizationfastify - A tinystruct-based TypeSafe SDK with JEV model.
tinystruct/tinystruct-typesafe-sdk · Java
20ai-safetyai-toolstinystructtypesafe-actions - A conservative Jev-backed auto-mode safety gate for Antigravity CLI tool calls
thomas-chong/agy-cli-jev-auto-mode · JavaScript
10agyai-safetyantigravitycoding-agentsnodejspretoolusetool-permissions - 1300jev-guardVets an LLM agent's tool calls through TypeSafe AI's Jev before they run — allow, block, or hold, failing safe on uncertainty.
CMaintz/jev-guard · TypeScript
11ai-agentsai-safetyguardrailsllmtypescript - 1447Jevs-GarageA garage full of tiny experiments for building critical systems with System One & Jev 🔧🧠⚡
JGalego/Jevs-Garage · Python
11ai-demosai-safetydecision-intelligencedeveloper-toolsexplainable-aihuman-in-the-loopincident-response - 1535skill-dashSkill Dash uses Jev to judge Claude Code and Codex skills and plugins: usefulness, redundancy, clarity, duplicates, safety. Local dashboard plus the corpus pipeline behind whichskills.dev. MIT.
48Nauts-Operator/skill-dash · Python
10agent-skillsai-safetyclaude-codeclaude-skillscodexdashboardprovenance - OpenAI-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
oppih/approval-judge-bridge · Python
00ai-agentsai-safetyapprovalsguardrailshermespython - 1664awesome-jevThe self-updating, trilingual directory of everything built on Jev (TypeSafe AI System One) — typed decisions, calibrated probabilities. AI-curated on free models.
hdjekuue/awesome-jev · JavaScript
00agent-harnessai-agentsai-safetyawesomeawesome-listcalibrationcontext-compaction - JEV evaluation (FM-JEV-01): replay-only, advisory-only evaluation of Foreman-style supervision with TypeSafe Jev. Measures how much safety comes from the model versus a deterministic evidence gate. No worker authority.
MahdiHedhli/foreman-jev-evaluation · Python
00agent-supervisionai-safetyevaluation-harnessllm-evaluationpython - 2081Jev-DefenseA Jev-powered security guard for AI agents: blocks dangerous tool calls, strips prompt injection, scans skills. Works with Claude Code, Codex, Copilot CLI, Gemini CLI, Cursor, and OpenCode.
prestonkakukdev/Jev-Defense · Python
00ai-agentsai-safetyclaude-codeguardrailsllm-securityprompt-injectionpython - Architecture for running many semantic decisions through one validated path, with a labelled 111-case benchmark comparing TypeSafe Jev against a Claude baseline, and a dashboard for inspecting any single decision. Experimental, not production.
ghubnab99/jev-enterprise-decision-fabric · C#
00agent-toolsai-safetyaspnetcorebenchmarkc#decision-makingdotnet - 2501jev-watchdogEvent-driven trajectory watchdog for coding agents: per-event LLM judgments (Jev, Claude, GPT) accumulated into quarantine decisions
glebmish/jev-watchdog · Python
00ai-agentsai-safetyclaude-codeclaude-code-hooksguardrailsllm-as-a-judgepython - 2507jev-workflowDecision contracts, adversarial testing, tracing, stability, and privacy controls for TypeSafe Jev
gbesse/jev-workflow · TypeScript
00ai-safetydecision-engineobservabilityprivacytypescript - 2637laya-guardrailsGuardrails de input, tool call y output para agentes de IA con un modelo System One tipo Jev (laya-pt-es-typed) autoalojado en una NVIDIA L4: 5 ms por check frente a 140 ms de un LLM-as-a-judge.
javimp2003/laya-guardrails · Python
00ai-safetyfastapiguardrailslayallm-agentsllm-as-a-judgenvidia-l4 - A typed decision layer for Salesforce: TypeSafe Jev (System One) in Apex for Service Cloud case triage and an Agentforce guardrail. Built live for Deep Dives by Sangam.
divingsbysangam/typesafe-jev-salesforce · Apex
00agent-scriptagentforceai-safetyapexllm-guardrailssalesforcesalesforce-dx
1–23 of 23