Home Assistant custom component: Conversation agent with Jev fast-path + Grok fallback
Agent tooling — page 14
Frameworks, routers and utilities that use Jev to choose tools or branches inside a larger agent system.
1,206 active projects in this collection. All collections →
System-architecture skill for TypeSafe AI Jev/System One — find fuzzy semantic judgment and turn it into small Choice/Score/Noul primitives.
Build versioned judgment functions on TypeSafe's Jev once, then call the same published version from your backend over HTTP and from coding agents over MCP. The vendor key stays on your machine.
3
Reward-hack radar for coding agents: structural denies + TypeSafe Jev System One sidecar for Claude Code & Cursor hooks
Shadow-mode validation harness for a pre-execution firewall on AI agent tool calls (TypeSafe/Jev). Real run, findings in report.md.
Automated database migration safety reviewer powered by TypeSafe AI (Jev System One model)
3
Type-safe model router. Jev (System One) banks each request to a typed catalog route.
Topic memory for LLM agents — edited, not accumulated: a topic keeps the starting question, conclusion, impact and dependencies; process is not memory. OKF bundle for dsh, local-first, git-traceable, budgeted LLM-free injection.
Tag $agent inside your Pull Requests and Issues to let Jev decide which model and reasoning to use.
3
g8s (The Gatekeepers): Zero-trust multi-agent orchestrator. Brain/supervisor delegates to muscle/worker via briefs, receipts, heartbeats, and lifecycle cleanup.
Multi-machine, multi-agent orchestration and control platform for DSH: route tasks across devices, workspaces, and Agent runtimes with streaming, approvals, and recovery.
3
Rakitsu is a Go-based runtime for building and debugging multi-agent AI systems — a visual builder to wire agents together, a real debugger to watch and step through what they're actually doing while they run.
DSH 的自动审批权限插件
3
Agent orchestration that guides projects toward demonstrable goals.
Self-updating weekly radar of trending GitHub repos (AI agents, security, dev tools, DevOps) via a Go script + GitHub Action
专门用于管理herdr 的agent，方便手机上沟通开发
Claude Max account usage and auto-switching for bb — proactive on utilization, reactive on real rate-limit failures, with thread auto-continue.
One-command setup for a full VS Code Copilot Chat agent-skills stack on Windows - 254 bundled skills (281 on disk), 18 CLIs, 11 MCP servers, 50 fork mirrors, and a 74-site design-system library, all security-gated.
3
coding agent like claudecode
Self-hosted MCP server for Kalshi prediction markets. Native RSA-PSS auth, token-bucket rate limiting, demo/prod safety controls. Designed to be forked and deployed.
x402 risk-check provider: TypeSafe Jev (System One) typed decisions + ES256-signed attestations for agent payments
2
Trolley Promblem for the Agentic Era
Claude Code plugin + zero-dependency CLI for TypeSafe's Jev: judge items in bulk with calibrated yes/no, pick-one and rubric answers; handle the confident ends in code, review only the uncertain band.
No project description available.