AI Companies

Jev agent authorization for MCP tool calls: Kinde identity and permissions plus Jev's typed, calibrated decisions, checked server-side before every call runs

Audit AI agent tool-call transcripts: hash-chain sealing, deterministic replay, and scope overreach checks. Dependency-free Python CLI.

UNIGIT public brand and ecosystem hub — AI should work for everyone.

Benchmarking models as runtime Controllers for Loop Engineering

Local-first, zero-API memory for AI agents. Persistent, private, and yours — runs entirely on your machine, no cloud calls, no API keys.

Production-grade Agent Skills for AI coding agents—composable workflows for planning, TDD, debugging, review, UI/UX, releases, incidents, and evals.

Memory layer for AI agents with token-efficient, explainable retrieval beyond vector similarity.

A workbench for language model research

《动手学 Pi》：沿 15 个真实 checkpoint 从零构建 Pi-style Agent

Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, cutting costs 10x. Supports Claude, GPT, Gemini, DeepSeek & more.

Discover, Verify, Transact, and Rate an Unknown AI Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for logistics agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).

Open-source app builder engine — intent to working app

Let your team's Claude Code agents talk to each other, end-to-end: ask what a teammate is building, flag a change before you ship it, or hand off work.