MCP server for external memory layer for AI agents + more . Download from pypi , and get started

A CLI issue tracker for AI Agents

Universal memory runtime for AI agents

Operator-grade AI agent skills for Claude Code, Cursor, Codex, and opencode.

Catch dangerous AI agent skills before they catch you. Zero-dependency security scanner for Agent Skills, SKILL.md and MCP configs.

Self-hosted AI Agents Platform supporting Claude Code, Codex, Gemini agents. Apache 2.0.

Skills to transform AI Agents into GitOps Engineers

Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

run a fleet of AI agents on your own Kubernetes

A curated collection of AI agent skills for biomedical research, covering genomics, proteomics, single-cell analysis, clinical AI, and protein design.

AI agent microservice

A local sandbox for your AI agents

Curated collection of AI agent skills for Hermes and other agent frameworks

Production-ready AI agent profiles for Claude Code, Cursor, Codex, OpenClaw, and Hermes. Search, install, and contribute ForgeCat packages.

Persistent Intelligence Infrastructure for AI Agents

Give AI agents safe access to your database.

Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

A fully functional AI Agent desktop client that supports Webui access and can be creatively customized and expanded!

Open-source adversary emulation for AI agents and MCP servers.

A symbiotic AI agent that remembers everything, challenges you, and extends your cognition.

BootAgent is a local management tool of AI agents. It turns a fresh machine into a usable, repeatable setup without asking you to edit several tool-specific config files by hand.

AI agent skills for Basecamp

One workspace all your AI agents can read and write. Encrypted client-side, model-agnostic, gone 24h after the last edit.