タグ：guardrails

guardrails タグの付いた Jev GitHub プロジェクトを検索・並べ替えし、元のリポジトリを確認できます。

115jevals
Agent 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
1029
ai-agentsevaluationguardrailsllmllm-evaluationragas
192pi-jev-auto-mode
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
311
typescriptauto-modecoding-agentsguardrails
224agent-chaperone
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
224
agent-securityai-agent-securityai-agentsai-securityclaude-codeguardrails
227jev-cli
Command-line tool for TypeSafe's Jev AI model
Nasrallah-AL/jev-cli · TypeScript
223
clifact-checkingguardrailsllm-toolsnodejsprompt-injection
348dsh-jev
Jev (System One decision model) plugin suite for DeepSeek Harness (dsh)
zhangxaochen/dsh-jev · TypeScript
92
agent-toolingcordisdeepseek-harnessdshguardrails
550jevshield
Sub-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
40
agent-securityai-agentsai-safetyguardrailslangchainllm-securitymiddleware
642jevrail
Jev powered pre-execution guard for terminal coding agents
SamanPandey-in/jevrail · TypeScript
30
agent-plugingolang-packageguardrailstypescript
653open-jev-approvals
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
30
ai-agentsapprovalclaude-codecodexgoguardrailshooks
727jev-agent-kit
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
20
agent-toolsai-agentsclaude-codecliguardrailsllm-routermcp
787jevegis
Guardrails for LLM apps in one API call. Prompt injection, jailbreaks, leaks, unsafe content. Built on TypeSafe Jev. MIT.
0xArx/jevegis · TypeScript
20
typescriptcontent-moderationguardrailsllm-security
792jevguard-mcp
Official Model Context Protocol (MCP) server for JevGuard and TypeSafe AI
seb4ez/jevguard-mcp · Python
20
ai-agentsantigravityclaude-desktopcursor-ideguardrailsmcpmcp-server
887decision-circuits
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
11
ai-agentscalibrationdecision-circuitsguardrailslangchainllmpython
894dsh-auto-review-jev
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
10
auto-reviewcode-reviewdeepseek-harnessdshguardrailspermissionplugin
991jev-guard
Vets 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
11
ai-agentsai-safetyguardrailsllmtypescript
1010jev-loop-detector
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
10
agent-toolsai-agentsdecision-apiguardrailsllm-toolssingle-file
1134pi-jev-eye
Ultra-lean supervisor for Pi coding agent using local regex filters, verification state tracking, and TypeSafe Jev semantic gate
bismawy/pi-jev-eye · TypeScript
10
ai-agentsguardrailspi-packagetypescript
1224ak-jev
Node.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
00
classificationguardrailsllmnodejsreranking
1227antigravity-approval
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
00
agent-securityai-agentsantigravityguardrailsllm-securitpretoolusepython
1232approval-judge-bridge
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
00
ai-agentsai-safetyapprovalsguardrailshermespython
1234arbitype
Typed decision tools for AI agents, powered by TypeSafe Jev
Renwang-Huang/arbitype · Python
00
ai-agentsclassificationclaudecursordecision-makingguardrailsllm-evaluation
1260better-cheaper-llm
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
00
cost-optimizationgroundednessguardrailshallucination-detectionllmllm-as-a-judgellm-evaluation

31 件中 1–31 件