Projects tagged with “guardrails”
Browse Jev GitHub projects tagged with guardrails. Filter, sort and explore their source repositories.
- 9bamlThe programming language for agents
BoundaryML/baml · Rust
9,512519boundarymlguardrailsllmprogramming-languagestructured-datarust - 123jevalsAgent evals and guardrails as Jev decisions: one request per trace, a fraction of a cent, fast enough for the agent loop. Runs locally with Kev or Laya.
openlayer-ai/jevals · Python
12013ai-agentsevaluationguardrailsllmllm-evaluationragas - Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.
PyModel/jev-judge-mcp · Python
495agent-toolsai-agentsai-guardrailsclassificationclaude-codefact-checkingguardrails - 209OrdoTurn judgments into decisions. Open-source decision engine in Rust for teams whose thresholds change often, live in many places, or move money. Jev reads the text, Ordo decides what happens next and shows which decisions change before you ship.
Ordo-Engine/Ordo · Rust
429ai-agentsbusiness-rulesdecision-enginedecision-modeldecision-tableguardrailsrule-engine - Jev (TypeSafe System One) backed auto mode for the Pi coding agent: semantically auto-approves bash, write, and edit tool calls and fails closed when a decision cannot be made.
jomatsu/pi-jev-auto-mode · TypeScript
344typescriptauto-modecoding-agentsguardrails - 294jev-cliCommand-line tool for TypeSafe's Jev AI model
Nasrallah-AL/jev-cli · TypeScript
233clifact-checkingguardrailsllm-toolsnodejsprompt-injection - Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.
agent-chaperone/agent-chaperone · TypeScript
158agent-securityai-agent-securityai-agentsai-securityclaude-codeguardrails - 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 - 395pi-heedRuntime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSafe Jev.
Nyarlathoteppppp/pi-heed · TypeScript
131ai-agentscoding-agentsguardrailspi-coding-agentpi-packagetypescript - 408dsh-jevJev (System One decision model) plugin suite for DeepSeek Harness (dsh)
zhangxaochen/dsh-jev · TypeScript
122agent-toolingcordisdeepseek-harnessdshguardrails - 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 - DeepSeek Harness plugin: per-tool-call Auto-permission review powered by TypeSafe Jev, with account usage and API-key management inline on its settings page
sperictao/dsh-auto-review-jev · TypeScript
30auto-reviewcode-reviewdeepseek-harnessdshguardrailspermissionplugin - 841jevegisGuardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT.
0xArx/jevegis · TypeScript
30typescriptcontent-moderationguardrailsllm-security - 845jevrailJev powered pre-execution guard for terminal coding agents
SamanPandey-in/jevrail · TypeScript
30agent-plugingolang-packageguardrailstypescript - Binary approval gate for Codex and Claude Code — every intercepted tool call is reviewed by TypeSafe JEV and composed through a versioned local policy, with scoped authorization.
alexj11324/open-jev-approvals · Go
30ai-agentsapprovalclaude-codecodexgoguardrailshooks - Decision circuits: typed questions to a System One model, calibrated probabilities back, gates in code. Zero-dependency Python SDK with LangChain, OpenAI Agents, and Claude Agent SDK integrations.
Barneyjm/decision-circuits · Python
21ai-agentscalibrationdecision-circuitsguardrailslangchainllmpython - jevkit: fast typed decisions for agents. CLI and MCP tools (route, triage, guard, grep, rank, compact, judge) on TypeSafe Jev. Zero dependencies.
walidboulanouar/jev-agent-kit · JavaScript
20agent-toolsai-agentsclaude-codecliguardrailsllm-routermcp - 1016jevguard-mcpOfficial Model Context Protocol (MCP) server for JevGuard and TypeSafe AI
seb4ez/jevguard-mcp · Python
20ai-agentsantigravityclaude-desktopcursor-ideguardrailsmcpmcp-server - TypeSafe Jev-powered intent gate for OpenCode: confirm intent before the agent dives into underspecified requests.
hoshinodis/opencode-intent-gate · TypeScript
20ai-agentsguardrailsllmopencodeopencode-plugintypescript - 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 - 1318jev-labO Jev (TypeSafe AI) como guardrail em tempo real e como pré-avaliador de agentes conversacionais de negócio. Next.js + LangChain via Vercel AI Gateway, com estudo de calibração em português.
JoaoClemer/jev-lab · TypeScript
10ai-agentsguardrailslangchainllm-as-judgellm-evaluationnextjs - Catch an AI agent stuck in a loop — Jev grades each step progress/repeating/stuck/escalate. Single-file, no build. Use free: jevtypesafeai.com/tools/agent-loop-detector
codaaiteam/jev-loop-detector · HTML
10agent-toolsai-agentsdecision-apiguardrailsllm-toolssingle-file - 1436JevLangA policy engine for LLM decisions: declare routes, gates and actions once in TypeScript or Python, and every decision comes validated, explainable, replayable and audited.
TimMikeladze/JevLang · JavaScript
10ai-agentsauditdecision-engineguardrailsjevlangllm - 1488nocapNo evidence, no answer. 🧢 System One evidence gate for RAG & AI agents: Jev / Laya / any LLM judges before your LLM speaks. MCP server, Python SDK, CI route tests.
xi029/nocap · Python
10ai-agentsclaude-codedecision-modeldeepseekevaluationguardrailshallucination - 1508pi-jev-eyeUltra-lean supervisor for Pi coding agent using local regex filters, verification state tracking, and TypeSafe Jev semantic gate
bismawy/pi-jev-eye · TypeScript
10ai-agentsguardrailspi-packagetypescript - 100 Java agent recipes, typed decision guardrails, Jev adapter, tested fixtures and architecture guides by Sandeep Belgavi
Sandeep-BA/agent-decision-lab · Java
00ai-agentsdecision-makingguardrailsjava - 1623ak-jevNode.js bindings for TypeSafe's Jev — the System One model. Typed decisions, probabilities and confidence, with no text generation and no parsing.
ak--47/ak-jev · JavaScript
00classificationguardrailsllmnodejsreranking - Fail-closed Antigravity PreToolUse guardrail using deterministic rules and TypeSafe Jev to screen tool calls, block risky commands, and escalate ambiguous actions to manual approval.
zjply4000/antigravity-approval · Python
00agent-securityai-agentsantigravityguardrailsllm-securitpretoolusepython - 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 - 1635arbitypeTyped decision tools for AI agents, powered by TypeSafe Jev
Renwang-Huang/arbitype · Python
01ai-agentsclassificationclaudecursordecision-makingguardrailsllm-evaluation - Use Jev instead of an LLM for RAG decisions: relevance grading, query routing, hallucination checks and LLM-as-a-judge evals. Faster, cheaper, measured first.
davidzna/better-cheaper-llm · Python
00cost-optimizationgroundednessguardrailshallucination-detectionllmllm-as-a-judgellm-evaluation - Beveridge: System One decision models with open weights. Typed yes/no, choice and score decisions with calibrated probabilities, on your own machines. pip install bev-decisions
sathiskumarjothi0-oss/bev-decisions-pypi · Python
00beveridgecalibrated-probabilitiesclassificationdecision-modelguardrailsopen-weightstyped-decisions - 把决策模型(typesafe/jev-1.13,经 OpenRouter 的 decisions 端点调用)封装成业务决策工具:注册表驱动,带置信度门控与硬约束。非官方项目。
Wany-i/jev-decision-layer · Python
00agent-toolsdecision-makingguardrailsllmmcppython - 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 - 2166jev-gatesSix calibrated gates for Claude Code, judged by TypeSafe Jev: rules, scope, intent, done, claims, and commit honesty. Each one escalates, none ever approves.
rashedInt32/jev-gates · JavaScript
00ai-agentsclaude-codeclaude-code-plugindeveloper-toolsguardrailshooksllm-tools - 2178jev-guardStatic code scanner (SAST linter) that finds insecure usage of Jev / TypeSafe guardrails in Python. Not a guardrail itself — build-time analysis, offline, no API key.
ppradyoth/jev-guard · Python
00ai-securitycode-scanningguardrailslangchainlinterllm-securityprompt-injection - 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 - 2546jevguardDeterministic decision runtime, zero-token caching, and certainty calibrator for TypeSafe AI (Jev).
seb4ez/jevguard · Python
01ai-agentscachingcalibrationdeterministicguardrailspippypi - 2551jevidenceLet Jev judge. Let your code decide. Python issue-routing sandbox with labeled replay, an offline demo, and Kev support.
peakevergreen/jevidence · Python
00classifierguardrailshuman-in-the-loopissue-triagellmpythonreplay
1–43 of 43