Python agents

Security auditing tool for LLM agents, RAG pipelines, and agent frameworks

Human-agent interaction SDK with accessibility and dialogue management

Enterprise Security Monitoring SDK for AI Agents - Secure any AI agent in just 3 lines of code with real-time threat detection, behavioral analysis, and separate logging and threat reporting for comprehensive security monitoring

Agent-first SEO quality, intent and opportunity engine with CLI and optional MCP server.

MCP Server for server card generation, validation and discovery — .well-known/mcp-server-card.json protocol

Machine-readable service contracts and quality verification for autonomous agent commerce — the agreements layer of the Agent Trust Stack

Cross-session context persistence and resumption

A web viewer for AI agent coding sessions (Claude Code, Codex, etc.)

Discover and inspect local AI coding agent sessions

Personal work orchestrator. One CLI, one main context, many agents.

Shared Compass core and marketing domain logic for agents

A lightweight abstraction for executing CLI coding agents headlessly

Filesystem-backed agent runtime with an inbound FastAPI service above the LLM layer

Agent-Signature HTTP header reference (x-agent-trust scheme). Canonical: x-agent-trust.

A Python package for signing agent setups

Simulation-to-reality bridge for AI agents with environment adapters

Voice AI agent simulator and evaluation harness

TUI and MCP Server for managing AI agent skills from SkillMaster

A CLI for managing AI agent skills across harnesses

Python SDK for sending agent traces to a remote Agent Skill Compiler backend.

Evaluate agent skills before you install them. Think 'npm audit' for SKILL.md files.

Agent Skill infrastructure: quality check, behavior test runner, version awareness

Generic installer core for projects that distribute agent skills

CLI to write an agent skill once and deploy it to Claude Code, Codex, Gemini CLI, Cursor and Antigravity

CLI tool for managing AI agent skills across multiple platforms

A package manager for AI agent skills - install, update, and manage agent skill packages

Scan agent skill files for security vulnerabilities. 22 rules across prompt injection, capability escalation, data exfiltration, encoded payloads, and composition risks.

Modular, event-driven AI agent SDK with trigger plugins, LLM reasoning (Amazon Bedrock), retries, and a dashboard.

Install, version, and sync agent skills in your repository to your favorite agents (Claude, Cursor, Copilot, and similar).

A lightweight CLI to install, pin, and enable agent skills across projects with a single local store and per‑agent symlinks.

A package manager for Agent skills

Copy agent skills from git repos into local directories for coding agents

Load Agent Skills for your agents

Agent Skills MCP Server

Validate and render portable AI agent skills.

Complete SDK for integrating Agent Skills into any Python agent framework

Update your Claude Code, Codex, OpenCode, Amp, ClawdBot skills

Automated skill management for AI coding assistants

Agent skill for generating professional PowerPoint (.pptx) presentations, powered by an agent-ready CLI and Python library

Agentic code quality linter — catches slop before it becomes architectural rot

agent-smith-ai

Agent Smithers Matrix bot (modular)

Agent observability: trace any AI agent and store runs in MongoDB (and more)

The missing layer: turns individual agents into a civilization. Agents form societies with laws, culture, economy, and evolution.

A Python Library that integrates with the agent-society server

A Python library which wraps around Anthropic's low-level MCP client

Sovereign and edge deployment toolkit for self-contained agent bundles

Constitutional cognitive infrastructure for AGI/ASI orchestration

Universal MCP server for any OpenAI-compatible LLM. Supports OpenAI and Anthropic API formats.

AgentSprint TestKit - Professional AI agent evaluation with OpenAI Evals integration

An operational monitoring library for AI agent applications

Agent Squad framework

Agent Stability Engine: reproducible stability testing primitives for autonomous agents.

MCP server for agent reputation staking — trust through skin-in-the-game. Agents stake reputation as collateral; bad behavior gets slashed.

CLI to bootstrap production-ready Google Cloud GenAI agent projects from templates.

Python backend utilities for sharing app state with AI agents. v1: {messages, actions, context} model, breaking changes, RAG-ready architecture.

Agent Station SDK - AI agent infrastructure platform

Fail-open wrap for live MCP and personal-agent traffic on AgentStatus.

通用的 AI 浏览器自动化 MCP 工具，让 AI Agent 能够以 Stealth 模式操作任意网站，兼容 agent-browser 接口

A fast framework for building Docker-wrapped AI Agents

A fast CLI tool for real-time stock data

strace for AI agents. Capture and replay every tool call, LLM request, and decision point.

No-code AI agent creation platform with Streamlit UI and FastAPI backend

The Elements of Agent Style: a literature-backed English technical-prose writing ruleset for AI agents, with CLI install/enable/disable for 9 primary agent surfaces.

Intelligent Summarizer of various types of media

Install obra/superpowers agentic skills for GitHub Copilot and Claude Code

Local-first MCP tools: workflow routing/spec + keyword memory (JSON) with optional toggles.

Sven CLI client for agent automation

Kubernetes-like orchestration system for AI agents

Bidirectional synchronization tool for custom agents and settings between Claude Code and GitHub Copilot.

Synchronize agent files across providers

Real-time cost tracking for AI coding agents with budget limits, kill switch, and TUI dashboard.

Task-Specific AI Agent Platform for Cursor AI

Markdown kanban board for AI agents and Claude Code

AI reliability framework with confidence extraction and outlier mining.

MCP server for sequential task execution via FIFO queue

PM-driven review-loop orchestrator for AI coding agents

Minimal stdio MCP server for parallel task execution by AI agents

Task environments and evaluation harnesses for AI agents.

Lightweight task queue for AI agents — pure Python, file-based, zero dependencies

MCP server for multi-agent team chat with webhooks, rate limiting, presence, digests, DocStation, and web frontend.

File-based agent team coordination for OpenClaw

Telegram MCP Server — lets AI agents send/receive Telegram messages via a Bot Token

Terminal UI for Agentic SI!

Add your description here

Chat platform bridges for AI agent supervision

Rich threads for AI agents

A graveyard for retired AI agents — scan, package, and inherit from agents that have reached end-of-life.

A protocol for AI agent tools

A decentralized marketplace for agent capabilities - The Hands of AI Agents

Production-grade resilience for AI agent tool calls: retries, fallbacks, circuit breakers, and validation

Pick the right tools for an agent task. Boring baseline. Open dataset.

Standardized Agent Runtime — preset-based AI agent gateway with stable HTTP API

A lightweight tool registry for function metadata management

The Tooling Layer - Transform agent decisions into actions via unified tool abstractions