Agent-aware React components for AI/LLM applications
Framework for agent-native application development — where AI agents and UI share SQL state, actions, and context
Agent-native CLI for AI mobile testing and app automation across iOS, Android, tvOS, Android TV, macOS, and Linux.
Dispatch — workspace control plane for agent-native apps. Vault, integrations, destinations, scheduled jobs, and cross-app delegation, shipped as a single drop-in package.
OpenSource Agent-Native forth-generation admin panel
The first Agent-Native (AX) frontend framework.
Sandboxed Linux compute, agent-native and human-friendly.
Agent-native BI toolkit
ANI Agent-Native IM channel plugin
Visual feedback and annotation tool for agent-native web applications
Agent-native CLI for Luma media creation workflows
Agent-native knowledge graph. Notes, tags, links over MCP.
Agent-native second brain skill installer
OpenViking CLI — agent-native context database
Scheduling primitives for agent-native apps — event types, availability, bookings, team scheduling, workflows, and routing forms.
Agent-Native Fullstack Framework - 에이전트가 코딩해도 아키텍처가 무너지지 않는 개발 OS
Agent-native CLI and runtime for building and deploying Lakebed capsules.
Pi skill package for agent-native-hardening.
Agent-native TypeScript framework for building MCP servers. Declarative definitions with auth, multi-backend storage, OpenTelemetry, and first-class support for Bun/Node/Cloudflare Workers.
Mandu MCP Server - Agent-native interface for Mandu framework operations
MCP server for Secondlayer's agent-native subgraph platform.
Agent-native CLI and runtime for building small full-stack TypeScript apps. Hosted Lakebed-style anonymous deploys included.
Lune CLI: agent-native research data and tools
Agent-native CLI for discovering, verifying, installing, and publishing reusable AI skills, prompts, MCP configs, scripts, and workflows.
The agent-native CLI linter — audit whether your CLI follows agent-readiness principles
Claw VCS: intent-native, agent-native version control.
A tiny, no-bloat foundation crate for building agentic CLIs in Rust.
CLI for Arcane - agent-native 2D game engine (dev server, testing, project scaffolding)
Arcane game engine — agent-native 2D engine with embedded TypeScript runtime
Core library for Arcane - agent-native 2D game engine (TypeScript runtime, renderer, platform layer)
Agent-native CLI for prediction market intelligence — sentiment analysis, divergence detection, and cross-platform arbitrage
Agent-native source annotation for semantic program control.
An Agent-native context database library for Rust
Fast macOS disk analyzer and cleanup CLI in Rust — ncdu / dust / GrandPerspective alternative with snapshot diff, agent-native JSON, and Trash-restorable cleanup.
Agent-native version control: typed op log + attestation graph.
Backpac Agent-Native CLI for autonomous settlement workflows
ActiveMatrix is a comprehensive Rails-native Matrix SDK that enables developers to build sophisticated multi-agent bot systems and real-time communication features. This gem provides deep Rails integration with ActiveRecord models, state machines for bot lifecycle management, multi-tiered memory systems, intelligent event routing, connection pooling, and built-in inter-agent communication. Perfect for building chatbots, automation systems, monitoring agents, and collaborative AI systems within Rails applications. Features include command handling, room management, media support, end-to-end encryption capabilities, and extensive protocol support (CS, AS, IS, SS).
Senren UI is a Rails-native UI component library inspired by the developer experience of shadcn/ui. It ships generators, a registry, and a centralized AI-agent skill system. Components are copied into the host app (source-copy architecture) so developers and AI agents can read and edit them directly.
This gem is useful for parsing mobile application's user agent. Not mobile browser based webapps, but native application. It parses iOS AFNetworking library user agent and Java/Android RetroFit library user agent.
Ruby-native LLM agent framework with provider adapters (Anthropic, OpenAI, Google), tool calling, streaming, and session persistence.
Agentf is a Ruby-native multi-agent workflow engine with an ORCHESTRATOR, role-specialized agents, provider adapters (OpenCode/Copilot), and Redis-backed semantic, episodic, and graph-style memory. It includes a unified CLI, MCP server tools, and install/update workflows for generated agent/command manifests.
Agent-native CLI for reading WrestlingIQ data via /api/v1 personal access tokens.
Ruby-native AI coding agent with pluggable LLM adapters, persistent memory, and file editing tools. Features automatic retry logic, SQLite-backed conversation history, and user approval workflows for file modifications.
Kernai is an AI agent kernel based on a universal XML block protocol, enabling simple, dynamic, observable and fully controlled orchestration without external runtime dependencies. Ships with reference provider adapters for Anthropic, OpenAI and Ollama, native multimodal support, a workflow DAG scheduler, pluggable recorder sinks and an optional MCP (Model Context Protocol) bridge.
Octo is a Ruby AI agent with three equal first-class interfaces: terminal CLI, web UI, and IM bridges (Feishu/WeCom/WeChat/Discord/Telegram). It speaks Anthropic Messages, OpenAI (Chat Completions + Responses), and AWS Bedrock natively, and provides autonomous tool use plus a Claude-Code-compatible skill format.
## Overview Privileged Access Manager (PAM) is a Google Cloud native, managed solution to secure, manage and audit privileged access while ensuring operational velocity and developer productivity. PAM enables just-in-time, time-bound, approval-based access elevations, and auditing of privileged access elevations and activity. PAM lets you define the rules of who can request access, what they can request access to, and if they should be granted access with or without approvals based on the sensitivity of the access and emergency of the situation. ## Concepts ### Entitlement An entitlement is an eligibility or license that allows specified users (requesters) to request and obtain access to specified resources subject to a set of conditions such as duration, etc. entitlements can be granted to both human and non-human principals. ### Grant A grant is an instance of active usage against the entitlement. A user can place a request for a grant against an entitlement. The request may be forwarded to an approver for their decision. Once approved, the grant is activated, ultimately giving the user access (roles/permissions) on a resource per the criteria specified in entitlement. ### How does PAM work PAM creates and uses a service agent (Google-managed service account) to perform the required IAM policy changes for granting access at a specific resource/access scope. The service agent requires getIAMPolicy and setIAMPolicy permissions at the appropriate (or higher) access scope - Organization/Folder/Project to make policy changes on the resources listed in PAM entitlements. When enabling PAM for a resource scope, the user/ principal performing that action should have the appropriate permissions at that resource scope (resourcemanager.{projects|folders|organizations}.setIamPolicy, resourcemanager.{projects|folders|organizations}.getIamPolicy, and resourcemanager.{projects|folders|organizations}.get) to list and grant the service agent/account the required access to perform IAM policy changes. Note that google-cloud-privileged_access_manager-v1 is a version-specific client library. For most uses, we recommend installing the main client library google-cloud-privileged_access_manager instead. See the readme for more details.
## Overview Privileged Access Manager (PAM) is a Google Cloud native, managed solution to secure, manage and audit privileged access while ensuring operational velocity and developer productivity. PAM enables just-in-time, time-bound, approval-based access elevations, and auditing of privileged access elevations and activity. PAM lets you define the rules of who can request access, what they can request access to, and if they should be granted access with or without approvals based on the sensitivity of the access and emergency of the situation. ## Concepts ### Entitlement An entitlement is an eligibility or license that allows specified users (requesters) to request and obtain access to specified resources subject to a set of conditions such as duration, etc. entitlements can be granted to both human and non-human principals. ### Grant A grant is an instance of active usage against the entitlement. A user can place a request for a grant against an entitlement. The request may be forwarded to an approver for their decision. Once approved, the grant is activated, ultimately giving the user access (roles/permissions) on a resource per the criteria specified in entitlement. ### How does PAM work PAM creates and uses a service agent (Google-managed service account) to perform the required IAM policy changes for granting access at a specific resource/access scope. The service agent requires getIAMPolicy and setIAMPolicy permissions at the appropriate (or higher) access scope - Organization/Folder/Project to make policy changes on the resources listed in PAM entitlements. When enabling PAM for a resource scope, the user/ principal performing that action should have the appropriate permissions at that resource scope (resourcemanager.{projects|folders|organizations}.setIamPolicy, resourcemanager.{projects|folders|organizations}.getIamPolicy, and resourcemanager.{projects|folders|organizations}.get) to list and grant the service agent/account the required access to perform IAM policy changes.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.