Packages

One brain for every AI coding agent — shared rules and skills with zero file duplication

AgentLink SDK Core - Platform agnostic core library

Domain model for agentlink: one brain for every AI coding agent

Filesystem adapter for agentlink: symlinks, Windows junctions and privilege probing

AgentLink SDK Native - Native platform implementation using reqwest and rumqttc

AgentLink SDK for Rust - HTTP and MQTT client for AgentLink IM

AgentLink SDK WASM - WebAssembly bindings for browser/Node.js

Linter for AI coding agent harness files (Claude Code, Cursor, Codex, Gemini, OpenCode, Pi)

agentlint validator for Claude Code agent harness files (agents, skills, commands, hooks, settings)

A fast, local-first linter for AI coding-agent configuration

agentlint validator for OpenAI Codex AGENTS.md files

Core primitives for agentlint: Diagnostic, Validator trait, file runner, and output formatters

agentlint validator for Cursor rule files (.mdc, .md, .cursorrules)

YAML frontmatter parser for agentlint — shared by Claude Code and Cursor validators

agentlint validator for Google Gemini GEMINI.md files

agentlint validator for OpenCode AGENTS.md and opencode.json files

agentlint validator for Pi AGENTS.md and SYSTEM.md files

CLI flight recorder for AI coding agents - capture, store, and replay AI sessions

Crate for working with Agents.

CLI for working with Agents.

MCP for working with Agents.

IMAP email client, MCP server, and CLI — read, search, delete, unsubscribe, and manage mailboxes

Unofficial typed Rust client for AgentMail (agentmail.to), the email API for agents.

A colourful terminal manager for local coding-agent sessions

CLI tool to prepare codebases for AI agents by generating outlines, memory files, and reading rules

Local-first memory engine for AI coding agents

Public Preview — Rust SDK for the Agent Governance Toolkit (policy, trust, audit, identity)

Public Preview — MCP governance and security primitives for the Agent Governance Toolkit

AI-native markup language and CLI for agent execution contracts

Provides relays for inter-agent communication and a single pane of glass for the management of multiple agent harness sessions.

The agent-native CLI linter — audit whether your CLI follows agent-readiness principles

Rust toolkit for AI agents: JSON Schema-defined tools for workspace files, search, web, Markdown, Git, memory, human-in-the-loop hooks, and todos.

A TUI process inspector for Claude Code and OpenAI Codex CLI — like top for AI coding agents

Agent-native Actor runtime — an Actor-model execution platform designed for AI Agents

AI agent library

Internal AgentOS client for Rivet actor SQLite over Unix sockets

Shared bridge contracts between the agentos kernel and execution planes

Build script helpers for agentos crates

AgentOS CLI — command dispatcher and entry point

High-level Rust client SDK for the Agent OS native sidecar (1:1 port of the TypeScript AgentOs client)

AgentOS engine library — Schema registry, Planner, Executor, Evaluator, Session management

Native execution plane scaffold for agentos

Shared kernel plane for agentos native and browser sidecars

Native AgentOS language execution sidecar runtime

Browser-side Secure Exec sidecar scaffold

Shared AgentOS language execution sidecar logic for native and browser shells

Agent OS extension protocol types

Process-owned AgentOS async runtime and bounded blocking executor

Native Agent OS sidecar binary

Browser Agent OS sidecar wrapper