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。
- 631jev-orcMy JEV Orchestrator to supply my needs
hiyoku/jev-orc · TypeScript
50typescript - JEV Smart Router — a Databricks App that uses TypeSafe JEV to pick which model answers each message, then runs inference on the chosen Databricks Foundation Model API endpoint.
rmosleydb/jev-smart-router · Python
52python - Windows port of typesafe-computer-use with Jev decisions, local OCR/UIA, and MCP host integration
kofanlabs/typesafe-computer-use-windows · Python
53automationcomputer-usemcpocrwindowspython - 677docsignalsAsk typed questions of your documents. Get structured signals for agentic workflows, with the page each answer came from.
PSPDFKit-labs/docsignals · TypeScript
40typescript - 681ha-gutcheckHome Assistant integration that makes small judgment calls about your install
funkadelic/ha-gutcheck · Python
40hacshacs-integrationhome-assistanthomeassistantpython - 683hermes-jevHermes Agent plugin: route each turn to the one skill that fits, via TypeSafe Jev on the Vercel AI Gateway. Fail-open, opt-in, stdlib only.
DoGMaTiiC/hermes-jev · Python
46skills - jev-android-super: TypeSafe Jev ecosystem repository.
SomeshSampat2/jev-android-super · Kotlin
40kotlin - 692jev-clawTyped model routing for OpenClaw agents, powered by TypeSafe Jev
trietphan/jev-claw · JavaScript
40ai-agentsllm-routingmodel-routingopenclawopenclaw-pluginjavascript - Jev Decisions Plugin for Hermes (and other AI Agents): tool risk reviews, human approval recommendations, evidence checks, a local decision journal, local decision supervision, and learned corrections.
bojansandhaus/jev-decisions-hermes · Python
40action-verificationagent-toolsai-agent-safetyai-agentsapproval-workflowsautomationclef - Jev picks what, code owns how - a System One Factorio agent driven by TypeSafe's Jev on FLE
AI-Ascension/jev-factorio-agent · Python
40python - 697jev-gateNot every coding task needs your best model. Experimental Jev-powered model routing for Claude Code — V3 prototype runs today, V4 routes at the task boundary.
MongLong0214/jev-gate · TypeScript
40agentic-aiai-agentsai-coding-assistantai-engineeringanthropicclaudeclaude-code - Per-turn router for agent harnesses: one 350ms Jev call picks the model tier, effort, tools and skill, behind a hard deadline with a regex fallback. Claude Agent SDK adapter included.
JoacoMarc/jev-harness-router · TypeScript
41ai-agentsclaudeclaude-agent-sdkcost-optimizationharnessllm-routing - Predict another skill's next closed decision with TypeSafe Jev — without running that skill.
DanielKillenberger/jev-predict-skill · HTML
40html - Keep skill catalogs outside the main LLM context. Jev selects relevant skills through one read-only MCP tool.
himomohi/jev-skill-router · Python
41agent-skillsclaude-codecodexcontext-engineeringllmmcppython - 711jev-starterTyped, policy-driven decision workflows on top of TypeSafe AI Jev: confidence routing, fallbacks, evaluation, and RAG patterns for TypeScript apps.
hamakyo/jev-starter · TypeScript
41confidence-routingdecision-enginedecision-workflowsfallbackhuman-in-the-loopllm - 721jevskillTeach your coding agent to stop burning context. Jev (System One) via OpenRouter or TypeSafe: 325ms, 0.000013 USD per decision. A/B tested 99.3% fewer input tokens with accuracy up. Ships a reversible reduce and a ledger that learns when Jev pays off.
lazniak/jevskill · Python
41agentic-aiai-agentsclassificationclaude-codecodexcoding-agents - Long-term memory for AI agents on Jev. Keep raw records, judge them with a fast System 1 model and answer from under 4k tokens of context.
Grivn/mnemon-memory-agent · TypeScript
40agent-memoryai-agentscontext-engineeringdeepseek-harnessdsh-plugindual-processllm-agents - paseo-spacedock: TypeSafe Jev ecosystem repository.
audreyt/paseo-spacedock · TypeScript
40typescript - 737reflexPre-execution risk gate for AI coding agents (Claude Code, Codex, opencode, pi, Hermes). Blocks or asks on risky shell commands, guards against prompt injection in what agents read, escalates to System 2 and a human queue. Optional TypeSafe Jev.
ursuciprian/reflex · JavaScript
40agent-securityai-coding-agentsautonomous-agentsclaude-codeclaude-code-hookscodexcodex-cli - Agent Skills for Codex Desktop and Claude Code, plus a Codex CLI harness. Jev-assisted context selection. / Codex Desktop・Claude Code向けAgent SkillsとCodex CLI用ハーネス。Jevでコンテキストを選別。
Oranquelui/astra-jev-harness · Python
30agent-skillscodexcodex-desktopcodex-skillspython - Agent Skill and Python workflow for Clay lead scoring, B2B prospect qualification, and people-search ranking with TypeSafe JEV.
promptgtm-shared/clay-jev-people-ranker · Python
32agent-skillsai-agentsai-lead-scoringb2b-salesclaude-codeclayclay-cli - TypeSafe Jev hooks for Claude Code, Codex and pi: per-turn skill suggestion and subagent model routing
onlyjq04/jev-agent-hooks · JavaScript
31javascript - Grok skill: Jev as a judgment sensor in a builder-agent loop (priors × probabilities → next act)
rainbowpuffpuff/jev-builder-loop · Python
30python - A framework-independent participation gate for AI agents in group chats, powered by typed Jev decisions.
pandore/jev-chat-gate · JavaScript
30ai-agentschatbotjavascript - Context compaction for Hermes sessions: every tool call scored by TypeSafe Jev; stale calls dropped, kept context stays verbatim.
picaye/jev-compaction · JavaScript
30ai-agentscompaction - open-sourced jev-flash-router: an MCP server for TypeSafe's new Jev model. AI coding agents waste hundreds of reasoning tokens just deciding which file to edit, which route to pick, or whether a diff breaks tests. Jev evaluates state and outputs calibrated probabilities. Works
Ravinder82/jev-flash-router · TypeScript
31mcpai-agentsrouter - 814jev-mermaidjev-mermaid: TypeSafe Jev ecosystem repository.
JordanDalton/jev-mermaid · JavaScript
31javascript - 816jev-nethackTypeSafe's Jev model plays NetHack 5.0: code lists the legal moves, Jev picks one, no LLM in the loop
statico/jev-nethack · Python
31ai-agentsgame-aihardfoughtnethackpythonroguelike - 827jev-routejev-route: TypeSafe Jev ecosystem repository.
mcftira/jev-route · Python
31python - 829jev-royalTypeSafe / Jev community project: Amrit-Nigam/jev-royal.
Amrit-Nigam/jev-royal · TypeScript
31 - 846jevselectorOpenCode v2 plugin that uses Jev (TypeSafe AI) to dynamically select relevant skills and tools per turn, reducing context window usage.
universam1/jevselector · TypeScript
31ai-agentscontext-optimizationmcpopencodeopencode-plugintypescript - 855mem-jevDeterministic procedural memory for agents
Sauhard74/mem-jev · Go
32 - 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 - 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 - Verbatim context pruning for the pi coding agent, scored by TypeSafe Jev: stale tool calls and results are dropped or truncated, everything kept stays verbatim.
QuentinDanblon/pi-fast-jev-compaction · TypeScript
31ai-agentscompaction - Pi extension that removes the inlined skill list and asks TypeSafe Jev which skill to load
iamdin/pi-jev-skill-suggestion · TypeScript
30typescript - Per-prompt model routing for the Pi coding agent: classify each prompt with Jev, pick a model tier, and switch before the turn runs.
rizafahmi/pi-jev-task-router · TypeScript
30typescript - 869reflexLab project: route Alertmanager alerts to urgent or informational Discord channels using TypeSafe's Jev model, with label-based fallback
Starttoaster/reflex · Go
30alertmanagerdiscordgolabprometheus - An autonomous risk-monitoring MCP server. Define a risk profile — a topic, the geographic locations to watch, and the policy triggers that matter — and the server runs an agentic sweep: live web search scoped by a judgment model (Jev), source scoring, and a Markdown briefing you can read from any MCP client.
youdotcom-oss/risk-analysis-server · TypeScript
31ai-sdkmcp-serveropenrouterweb-searchyoudotcomtypescript
第 151–200 条,共 563 条