Packages
Browse packages indexed by the registry.
Core traits, data models, and prompt primitives for building deep agents.
Manage AGENTS.md and Docs markdown indexes for agent-oriented repositories.
Env vars for AI agents — use secrets without ever seeing them
Rust provider registry and lightweight clients extracted from Neo's LLM provider module
Autonomous Rust coding harness for long-running software engineering tasks with a supervisor loop, tool execution, and session management
A tool for managing parallel AI agent tasks with Claude and Codex
Procedural macros for Rust Deep Agents SDK
Generate a solid AGENTS.md / CLAUDE.md for any repo by detecting its stack, commands, and structure
Database-backed persistence implementations for the Rust deep agents SDK (Redis, PostgreSQL)
Reserved for the DeepSeekAgents project's desktop pet companion. This 0.0.0 release reserves the name; real releases start at 0.1.x.
Proc macros for typed agents and type-safe tool calls
Async runtime orchestration for Rust deep agents.
High-performance Rust SDK for composing reusable AI agents with custom tools, sub-agents, and prompts
Fast fuzzy finder TUI for coding agent session history
A minimal, stable, easy-to-understand skill installer and manager for AI agents
Test helpers and provider fixtures for agents
Reusable tools and utilities for Rust deep agents.
Shared Rust implementations of agent tools
AgentSchema Rust Runtime - declarative AI agent definitions
Scope firewall and audit layer for AI coding agents
AgentScope Rust - A framework for building LLM-based agents Only for learning
A programming language for AI agents
Procedural macros for the agentsdk library
Autogenerated OpenAI types for agentsdk.
A FileSystem plugin for agentsdk.
An MCP (Model Context Protocol) plugin for agentsdk.
AgentSec — Agent ecosystem security suite (inventory scan / web sanitize / paste detection)
AgentSec core library — scan / web / paste logic, pure Rust
AgentSec platform probe for Anthropic Claude Code config layout
AgentSec platform probe for Claude Desktop (macOS) config layout
AgentSec platform probe for Cursor (cursor.com) config layout
Transparent OpenAI-compatible security gateway for LLM agents: DLP, secret-leak, jailbreak and prompt-injection detection at the egress.
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.
Composable analysis, materialization, and storage extensions for AgentSight.
Compatibility facade for the AgentSight capture and analysis pipeline.
Native cross-platform capture substrate for AgentSight.
Bounded in-process WebAssembly Component runtime for AgentSight extensions.
Shared AgentSight Node protocol for native, CLI, and browser WASM clients.
Agent skills package manager — install, manage, and discover AI agent skills from GitHub.
AI Agent forging utilities.
Snapshot tests for AI agent traces. Record once, replay-and-compare on every run; the agent equivalent of Jest snapshots.
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.
CLI scaffolding for tools — clap setup, shell completions, TTY detection
XDG-compliant configuration and path management for CLI tools