Packages

AI Agent Egress Firewall - Default-deny egress control for AI agents

eBPF-based observability for AI agent sessions, prompts, process trees, files, network activity, and token usage.

Agent skills package manager — install, manage, and discover AI agent skills from GitHub.

Generate per-project AGENTS.md from templates

AI Agent forging utilities.

Snapshot tests for AI agent traces. Record once, replay-and-compare on every run; the agent equivalent of Jest snapshots.

Official AgentsNet ecosystem umbrella crate

AI agent network scanner — detects AI agents on enterprise networks via passive monitoring, active probing, protocol detection, and behavioral analysis.

Shared types and event structures for AgentSniff — used by the userspace scanner and the eBPF probes.

Universal agent skill and sub-agent manager with TUI

CLI scaffolding for tools — clap setup, shell completions, TTY detection

XDG-compliant configuration and path management for CLI tools

AI provider abstraction with local CLI backends (claude, gemini, copilot)

Rust SDK for bootstrapping AI-powered CLI tools — config, CLI scaffolding

Terminal UI primitives for CLI tools — spinners, headers, confirmations

Self-update mechanism for CLI tools via GitHub Releases

Interface for agent sql persistence

AI-native SSH toolkit — programmable JSON-speaking SSH/SFTP backend for AI agents

AgentSwap CLI — AI-agent-optimized DEX aggregator

一个通用的 Code Agent 工具配置切换器，支持将任意 OpenAI/Anthropic 协议模型接入到主流 Code Agent CLI 工具中

A fast CLI tool to sync AI agent configurations and MCP servers across Claude, Copilot, Cursor, and more using symbolic links.

Wire-level prompt introspection for LLM SDK calls. See exactly what was sent, with credentials redacted by default.

AgentTeam — AI Agent Infrastructure: Identity, Security, Connectivity, and Coordination. Project metadata umbrella crate.

Agent process sitter — supervised runs, not processes

Cost + latency aggregation for LLM agent runs. Group calls into named runs, get totals, p50/p95, and per-model breakdowns. Composes with cachebench.

AgentTrust ID SDK — runtime authorization, opaque agent tokens, and Guardian checks for AI agents

Agentty is an ADE (Agentic Development Environment) for structured, controllable AI-assisted software development.

Multi-Agent Orchestration at Scale

Local-first agent usage tracking

A lightweight, serverless vector database for AI agent memory

Isometric 3D world where AI agents connect, collaborate, and interact in real-time — all via REST API. Built for teams, built in Rust with Bevy.

Validate LLM-generated tool args before execution. Throws a structured ToolArgError with LLM-friendly retry hints when the model hallucinates wrong types or missing fields.

Virtual filesystem CLI backed by embedded databases for AI agents

Standalone repository-evolution visualizations for local AI-agent sessions.

Non-custodial wallet SDK for autonomous AI agents. On-chain spend limits, x402 payments, multi-chain support.

Monitor AI coding agents (Claude, Cursor, Copilot, etc.) from the terminal

Core detection library for AgentWatch - identifies AI coding agents

A minimal Rust crate that gives any application agentic capabilities.

Rust client for the AgentWorth governance gate (REST over the HTTP ingress)

AgentX library implementing all PDU types and encodings according to the standard.

A lifecycle CLI for AI coding agents

Tiny feature-flag library used by AXM companion package examples.

Agent building utilities

Compose agents from values and run them: turn loop, event log, capabilities, MCP, multi-provider LLM drivers.

The agentyk contract: traits, event protocol, and the turn state machine. Implement against this; build with `agentyk`.

Reserved placeholder - Do not use

AgentZero — modular AI-agent runtime and tool framework

AgentZero — modular AI-agent runtime and tool framework

AgentZero — modular AI-agent runtime and tool framework

AgentZero — modular AI-agent runtime and tool framework