Search

Tool approvals over the run log — the request, the human's answer and every settled gate decision are run-log entries, so desktop, cloud pi and agentic hosts ask and are answered on one surface

Persistent context, semantic recall, and the vector-store contract, for Python.

Payload CMS plugin for AI agent virtual office visualization — PixiJS canvas, multi-floor, multi-agent, WebSocket-ready

A disk-backed engineer loop for AI agents: context on disk, layered gates, no hallucination.

See what your TypeScript AI agent actually did. Wrap a tool in one line; every call is recorded locally (tool name, argument names, never values) and `audit` prints the report. Nothing is blocked.

A local SVG logo editor for fine-tuning designs by hand or with AI agents.

Mediated conversations between humans, LLM assistants and tools

ZeroAI - 终端 AI 编程助手（多专家协作·语音对话·文档生成·安全审计）

pyTracer adapter for the OpenAI Agents SDK - auto-instrument agents via a tracing processor.

pyTracer adapter for LangGraph / LangChain - auto-instrument agents via a callback handler.

GLM-5.3-Flash - AI model available on ModelScope inference platform

Palabra Realtime STT/TTS models for the OpenAI Agents SDK VoicePipeline

AI model: Jackwang111/M2RL-RL_Agent

Windows computer-use MCP server (26 tools) with a human-in-the-loop approval gate: physical-input-only dialogs, signed guard switches, deny/launch lists, hash-chained audit log. 70+ unit tests, green CI.

Stand up your own cross-model AI engineering team — the way Neo.mjs runs its own. Named AI maintainers with persistent identity, shared memory and review across labs, coordinating as a team of teams on your codebases. Multi-window, in the browser or an Electron shell.

Agentic SDLC Governance

Zero-config, black-box sweep and benchmark engine for LLM and agent systems.

Forall (∀) is a coding agent from Astrio that helps developers build correct software by generating spec-driven code alongside machine-checkable proofs.

T2AG 是考你而不是替你答的 AI 学习框架：错题、证明与每一次裁决都存在归你所有的纯文本里，任何 agent 可读可带走；环上的裁决者是你。An AI learning harness that tests you instead of answering — your mistakes, proofs and verdicts live in plain text you own, portable across agents; the judge in the loop is you.

High-speed CLI toolkit and AI agent skill for the Visayas State University E-Learning Environment (VSUEE Moodle).