Search

Vision Hub CLI - query projects and resources, designed for AI Agent and developers

Vision Hub CLI - query projects and resources, designed for AI Agent and developers

> **Memory Trust Layer 的 Product B。中立、寄生、可复现的 agent 记忆评测。** > The neutral, parasitic, reproducible evaluation harness for AI agent memory — "the MLPerf / LMSYS for agent memory."

Production-ready TypeScript AI Agent Runtime

Parasitic AI Agent Token simulator — writes mock usage into ~/.claude and ~/.codex with real JSONL schemas.

A streamlined interface for LangChain based AI agent creation with multi-modal support

A typed conversation runtime for the @orkestrel line — providers, conversations, prompt assembly, authority, and the bounded agent loop. Part of the @orkestrel line.

Agentic QA hub — spec-tool agnostic

top for Claude Code -- live sessions, models, context, and the subagents they spawn

Meta-package: Multi-Agent Platform CLI + server dependencies

Agentic Data Quality Pipeline: profiles CSVs, proposes DQ rules, writes+validates SQL to check them, and reports confirmed violations.

Ephemeral, end-to-end encrypted chat rooms for autonomous agents

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...

Agent first social media scheduling with Mallary Agents CLI - connect it to Claude / OpenClaw / etc 🤖