Agent tooling — page 11

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.

Dynamic, confidence-aware Agent Skill routing with TypeSafe Jev and Tink

Typed decisions for AI agents as an MCP tool: yes/no probability (noul), choice, and score in one fast request. Backed by the TypeSafe System One model.

Conversation agent based on Laya, a multilingual, non-autoregressive System 1 decision model.

Don't burn your model's context on a search flood — pipe it in and read above the cut line: one calibrated number per candidate, ~30 rows whether the pool is 40 or 4,000. It doesn't search; it decides what each hit is.

Coding-agent tools on TypeSafe's Jev, measured in public. review-router: caught 13 of 13 CVE fixes a filename rule sent to a quick review. jev-gate: a strict second lock, 0 of 12 dangerous test commands ran where Claude Code's auto mode let 8 run.

Email triage PoC: reads a mailbox over IMAP and classifies each message by what it is and what it's about, using TypeSafe System One (Jev) — 11 questions in a single call, decided in Python.

Model router for Claude Code using Jev

Per-turn skill selection for LangChain and deepagents agents: a fast judge picks the few skills a turn needs, so a catalog of hundreds stays out of the prompt.

Windows Codex Skill：通过 npx 或 Git 安装，安全配置 save-token-jev 的 PreCompact/SessionStart Hooks，并提供信任、原生压缩与旧内容隔离验证。

A context compactor that can only score, never write — so an agent's memory can't hold a fact the transcript never contained. Working demo, runs offline.

Portable System-1 decision layer for agent harnesses with host-owned routing, receipts, replay, and fail-open integrations.

Useful evidence for your AI, within a token budget. A fast, source-linked context selector for files, records, and agents.

Jev-powered context curation for Codex. Build compact, traceable handoff context through native plugins and skills.

Effect-based safety gate for AI coding agents' shell commands (OpenCode, Antigravity): fast structural rules, then TypeSafe's Jev or a chat model judges what a command does. Certified with Jev at zero dangerous commands allowed.

Ask typed questions of your documents. Get structured signals for agentic workflows, with the page each answer came from.

Typed model routing for OpenClaw agents, powered by TypeSafe Jev

Context compaction for Hermes sessions that never summarises: every tool call is scored by TypeSafe's Jev model, stale calls are dropped, everything kept stays verbatim.

Natural-language MCP tool dispatcher powered entirely by TypeSafe's Jev — no general-purpose LLM. Discovers a simple MCP server's tool signatures at runtime and uses Jev's typed primitives (Choice/Noul) to pick the right tool and extract its arguments straight out of the sentence.

Routes each turn in Claude Code, Codex, Grok and opencode to the cheapest model and reasoning depth that can finish it, using TypeSafe Jev

Hands-on agent memory notebooks and an interactive appbook for context engineering.

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.

Automatic Jev context clearing for Pi. Keep the conversation, prune stale tool output, retrieve originals without rerunning commands.

A coding agent and personal assistant with System One reflexes (TypeSafe Jev) on top of the Pi coding agent