TypeSafe Jev / System One 模型的免费 GitHub 项目目录按用途查找官方 SDK、智能体工具、开源替代实现与 Jev 最新资讯

数据更新

智能体与自动化

查找使用 Jev 在工作流中进行类型化决策的智能体与自动化项目。

  • 1454jevx
    jevx: TypeSafe Jev ecosystem repository.

    muthuishere/jevx · Go

    11
    go
  • Скилл для агентов Letta: суждения по критериям через TypeSafe System One (Jev)

    carlsonchik/judging-with-typesafe · Python

    11
    python
  • 1462karnak
    Jev picks Claude Code's reasoning effort before every step. Low for routine, high when recovering.

    kjmagnan1s/karnak · TypeScript

    11
    ai-agentsclaude-codeclaude-code-pluginreasoning-efforttypescript
  • Jev-powered reply trigger for KiraAI 3.x with persona-aware decisions and message history context

    xxynet/kira-ai-plugin-jev · Python

    10
    python
  • kz-harness: TypeSafe Jev ecosystem repository.

    kz-95/kz-harness · JavaScript

    10
    javascript
  • laya-jev: TypeSafe Jev ecosystem repository.

    KonghaYao/laya-jev · TypeScript

    11
    typescript
  • laya-router: TypeSafe Jev ecosystem repository.

    vuongvm812/laya-router · JavaScript

    10
    javascript
  • Picks a model for each subagent, judged by Jev on TypeSafe or OpenRouter. Plugins for Claude Code, Oh My Pi, OpenClaw and Hermes Agent.

    Akurganow/model-router · TypeScript

    10
    claude-codeclaude-code-pluginhermes-agentmodel-routingoh-my-piopenclawopenrouter
  • Weekday AI news briefs in Slack with n8n, You.com, and TypeSafe Jev. Workflow, evaluation, and write-up.

    youdotcom-oss/n8n-ai-brief-workflow · Python

    10
    ai-newsn8nn8n-workflowslackyoudotcompython
  • 1488nocap
    No 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

    10
    ai-agentsclaude-codedecision-modeldeepseekevaluationguardrailshallucination
  • OMP / pi-coding-agent extensions that delegate acceptance gating and subagent routing to the Typesafe Jev decision API

    luw2007/omp-jev-extensions · TypeScript

    10
    typescript
  • Verbatim context compaction for OpenClaw: a context engine powered by TypeSafe's Jev. Drops stale tool calls and results, never summarizes.

    SqaaSSL/openclaw-jev-compaction · TypeScript

    10
    compactioncontext-enginellm-agentsopenclawopenclaw-plugintypescript
  • A local OpenFront agent using TypeSafe Jev for bounded gameplay decisions.

    mogottsch/openfront-agent · JavaScript

    10
    javascript
  • Stop AI agents from executing MCP tools unchecked — policy, approval, JEV decisions, and one-use execution permits.

    qinpei-dev/permit-mcp · Python

    10
    ai-agent-securityai-agent-skillsai-agent-toolsai-agentsmcpmcp-servermodelcontextprotocol
  • 1503pi-jev
    a Jev classification layer for the Pi coding agent

    riposta/pi-jev · TypeScript

    11
    typescript
  • Jev-powered context compaction for Pi. Keep critical instructions and tool history, prune the noise, and fall back gracefully.

    Wang-auspicious/pi-jev-compaction · TypeScript

    10
    ai-agentscontext-compactionpipi-packagetypescript
  • System-One control plane for Pi Coding Agent powered by TypeSafe Jev.

    goodruizhan/pi-jev-control · TypeScript

    10
    typescript
  • TypeSafe / Jev community project: Z761293629/pi-jev-helm.

    Z761293629/pi-jev-helm · TypeScript

    10
  • Agent managed wiki for a project's conceptual space, utilizing Jev to ensure legitmate, relevant, and robust information at scale.

    xAndreiLi/pi-jev-wiki · TypeScript

    11
    typescript
  • Autonomous Pokemon Showdown battle agent powered by Jev AI (System One Model by TypeSafe AI), with a validated poke-env harness, safe fallback decisions, and a live dashboard for transparent battle state, legal moves, probabilities, telemetry, and Jev decision history.

    NatBrian/pokemon-showdown-jev-agent · JavaScript

    10
    ai-agentsai-observabilityautonomous-agentbattle-aidecision-enginefastapigame-ai
  • 1532siege
    SIEGE: 200 people vs one agent. A typed action gate (TypeSafe System One) that learns from every breach, evaluated by W&B Weave, hardened by a defender loop. Built at CoreWeave Hacks: Agent Loops 2026.

    vnmoorthy/siege · TypeScript

    10
    typescriptagent-loopsai-agentscoreweave
  • smart-router-chatbot: TypeSafe Jev ecosystem repository.

    SairajGavhane/smart-router-chatbot · Python

    10
    python
  • Every tool call your agent makes, checked before it runs. A Claude Code plugin that uses TypeSafe AI's Jev to verify each pending tool call against the session plan, then allows it, asks you, or blocks it. Proof of concept

    getexcited/stepwarden · TypeScript

    10
    ai-agents
  • 1551tacano
    tacano: TypeSafe Jev ecosystem repository.

    Nicolas6879/tacano · Python

    10
    python
  • Frontier prices only for frontier work: each task goes to the cheapest model that does it well, a request is split only when that pays, and every result is checked. Decisions by Jev.

    cintocasals/taskpenny · Python

    10
    ai-agentsbenchmarkclaudecost-optimizationgeminillmllm-routing
  • thinkdial — per-task reasoning effort for Claude Code, decided by TypeSafe's Jev: main loop, Claude subagents and Codex delegations. Effort-only by design: model switches break the prompt cache.

    DmitryBMsk/thinkdial · TypeScript

    10
    claude-codeclaude-code-modllm-routingprompt-cachingtypescript
  • Alert triage as a UNIX filter: JSONL security alerts in, typed decisions out. Runs on TypeSafe Jev or a local model; policy routing stays in code.

    m0rphtail/triagedy · Rust

    11
    alert-triageclillmrustsecuritysoc
  • Unofficial community MCP plugin for Codex and Claude Code using TypeSafe Jev for bounded routing, ranking, extraction, verification, and escalation

    E-FL/typesafe-as-a-judge · JavaScript

    10
    ai-agentsclaude-codecodexdeveloper-toolsmcpmodel-context-protocol
  • 4genthub-client: TypeSafe Jev ecosystem repository.

    phamhung075/4genthub-client · Go

    00
    go
  • 58_JEV_AI: TypeSafe Jev ecosystem repository.

    kassaiattila/58_JEV_AI · Python

    00
    python
  • Interactive agent-routing demo. The API key and Sites project id stay in local env files.

    Neha/agent-battle-royale · TypeScript

    00
    typescript
  • 100 Java agent recipes, typed decision guardrails, Jev adapter, tested fixtures and architecture guides by Sandeep Belgavi

    Sandeep-BA/agent-decision-lab · Java

    00
    ai-agentsdecision-makingguardrailsjava
  • Point AI coding agents at the right docs in large codebases: local BM25 and a Jev search propose, a Jev check confirms.

    beqaux/agent-doc-search · JavaScript

    00
    adrai-agentsbm25claude-codecoding-agentsragretrieval
  • AI agent tool-call guardrail for Xano: Jev (TypeSafe AI) judges each call; Xano allows, blocks, or holds it for human review.

    xano-community/agent-guardrail-jev · XS

    00
    xano-templatexs
  • An experimental protocol for evidence-aware agent handoffs, bounded worker continuation, and TypeSafe/Jev-assisted review, with reproducible evaluation.

    zsoXi/agent-handoff-gate · Python

    00
    pythonagent-orchestrationai-agentsevidence
  • A ~400ms System-One safety reflex for AI coding agents: auto-approves routine tool calls, escalates risky ones, blocks exfiltration & prompt injection. Powered by TypeSafe's Jev.

    rutvikchandla3/agent-reflex · TypeScript

    00
    typescript
  • Fast computer-use agent for macOS: Gemini plans once, Jev acts at every step via the Accessibility API

    omerfeyzioglu/agentp-macos · Python

    00
    accessibilityai-agentscomputer-usellmmacosvoice-assistantpython
  • 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
  • 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

第 301–350 条,共 563 条