Search

One command gives any AI agent your entire codebase. Auto-detects your stack, generates context files for Claude Code, Cursor, Copilot, and Codex.

Local web console for managing multiple CLI AI Agent instances in parallel

Signals CLI - Command line interface for the Signals lead intelligence API. Discover leads, manage subscriptions, and automate workflows from the terminal or AI agents.

Multi-branch AI Agent framework — one command to scaffold your AI workspace

See what your AI agents actually do. Runtime visibility, audit trails, and guardrails for LangChain, CrewAI, AutoGen, and custom agents.

Multi-agent collaboration skill — orchestrate AI agent teams via ACP with structured protocols, role-specialized councils, and plan-first workflows. Works with any ACP-compatible agent: Claude Code, Codex, OpenCode, Gemini, Cursor, Copilot, OpenClaw, and

Voice-powered terminal agent. Fully offline. Speak commands, get answers.

Universal AI Agent SDK for TypeScript — multi-model support with built-in tools, powered by any LLM.

Multi-Agent Accelerator for Data Science (MAADS): Transactional Machine Learning

autonomous agent behavioral scanner on solana — detects fake ai agents

Agent payment intelligence — predict costs, optimize execution, fix failures. Powered by VialOS Runtime.

Lossless Context Management — persistent memory for LLM agent sessions

CLI launcher for Atlas HQ — task management for AI agent teams

Browser automation CLI for AI agents — navigate, discover elements, click, fill forms, take screenshots, extract data via CDP

Build: Auto-Bidding Agent Framework

Immutable Authority Infrastructure for Autonomous AI Agents

This is a reserved placeholder package to mitigate dependency confusion risks.

AgentFoundry: A modular autonomous AI agent framework

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.

A brain-inspired memory engine — contextual storage and associative retrieval