Search Packages

rememb

Persistent memory for AI agents — local, portable, zero config. Works with Cursor, Windsurf, Claude via MCP.

afkbotio

Local AI agent runtime and CLI with memory, MCP, browser control, automations, and subagents.

memoryos

AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill memory for cross-task skill reuse and evolution.

cuti

Utillity Module for Claude Code. Dev Container, Clawdbot, queuing commands, prompt history, prompt alias, everything in one place

milady

Dynamic loader for Milady — personal AI assistant built on elizaOS

clawmonitor

help you monitor OpenClaw Agents/Sessions.

unbrowse-hermes

Hermes Agent plugin that makes Unbrowse the preferred tool for website tasks.

claw-swarm

A smaller, lighter-weight version of OpenClaw, natively multi-agent, compiles to Rust, and built on the Swarms framework and Swarms ecosystem. One API, unified messaging across Telegram, Discord, and WhatsApp with optional Claude-powered reasoning.

openbotx

An open-source platform for orchestrating AI agents — secure, simple, and built for everyone. Multi-agent, real-time task board, web control panel, skills system, browser automation, multi-provider, scheduler, and more. One command to start. Everything from the browser. No coding required.

hermes-installer

The agent that grows with you

openakita-plugin-sdk

SDK for building OpenAkita plugins — protocols, base classes, and testing helpers

read-no-evil-mcp

A secure email gateway MCP server that protects AI agents from prompt injection attacks hidden in emails.

orchard-kit

Self-governance architecture for AI agents: membrane security, epistemic hygiene, cognitive architecture, and multi-agent trust.

database-pydantic-ai

Database toolset for PydanticAI — schema exploration, SQL queries, and data analysis with read-only mode, query validation, and row limits.

secureshell

A drop-in shell execution wrapper for LLM agents that prevents hallucinated/destructive commands.

vibeguard

🛡️ Open-source runtime security for LLM applications. Detect and block prompt injection, PII leaks, and sensitive data exposure before responses are generated.