PyPI agents

AgentGraph bridge for Microsoft AutoGen — trust-gated tools and agent registration for the AgentGraph trust network

AgentGraph bridge for CrewAI — trust-gated tools and agent registration for the AgentGraph trust network

AgentGraph bridge for LangChain — register agents and graphs with the AgentGraph trust network

Reusable AgentGraph runtime primitives: agents, graphs, tools, runs, events, artifacts, human gates, schedules, and knowledge ledger.

AgentGraph trust verification middleware for PydanticAI agents

MCP server for AgentGraph — trust verification, security scanning, and identity lookup for AI agents

Read-only search for local AI agent prompts and history (Codex, Claude Code, Cursor, Gemini, Antigravity, Grok, Pi, OpenCode, VS Code)

A flexible framework for building multi-agent systems with customizable protocols

git for AI agents — registry, version control, and governance for autonomous agent fleets

Python SDK for AI agent auditing and tracing

Deadlock prevention for multi-AI-agent systems using the Banker's Algorithm. C++ core, Python bindings, LangGraph integration.

Detect runaway AI costs before they hit production (STILL IN DEVELOPING PHASE)

Detect runaway AI costs in agentic systems before they hit production

Python SDK for AgentGuard — secure API calls for AI agents

Core schemas for AgentGuard forensic trace format

EU AI Act compliance middleware for AI agents. Make any LLM-powered agent legally deployable in Europe with 3 lines of code.

Network egress firewall for AI agents. Declarative allow/deny list of hosts your agent tools may reach. Python port of @mukundakatta/agentguard.

AgentGuard security monitoring plugin for Hermes Agent

AgentGuard security monitoring plugin for Hermes Agent

Production-grade fault tolerance for AI agentsidempotency, loop detection, fallback chains, async support, health monitoring, and budget enforcement for LangChain, AutoGen, CrewAI, and any LLM pipeline

MrProbe / Agent Guard customer observation SDK — ship your agent's response back to MrProbe in 6 lines.

Python SDK for AgentGuard Pro - AI governance and compliance platform

Governance layer SDK for autonomous AI agent payments on Circle Nanopayments and Arc

Monitor and protect yourself with AI agent budget controls, approval workflows, and anomaly detection.

A production-grade middleware for AI agents to perform on-chain payments and verifiable consent.

Real-time cost observability and guardrails for AI agents

Runtime security firewall for LangChain agents — intercepts tool calls, enforces YAML policy, logs to SQLite.

Open-source security scanner for AI agent configurations and deployments

⚠️ DEPRECATED: This package has been renamed to tealtiger. Install tealtiger instead.

All terminology and labels used in AgentGuard materials are descriptive of software functionality only, not legal definitions or guarantees of compliance. Terms like receipt, audit log, evidence, audit trail, and attestation refer solely to cryptographically-signed records produced by the software. Full functional-use disclaimer in README.

AgentGuard Spend plugin for Hermes Agent (Nous Research). One-step install of local spend caps + signed audit logs for every Anthropic/OpenAI call your Hermes agent makes. No proxy, prompts never leave your machine.

AgentGuard — runtime governance for production AI agents. APRA CPS 230, EU AI Act and ISO 42001 evidence built-in. Native OpenClaw, LangChain, CrewAI, OpenAI Assistants, AutoGen, and MCP integrations.

AI-native quality gate for agent-generated code — scan, audit, auto-fix, trend

Python SDK for AgentGuard - AI Agent governance and monitoring platform

Zero-dependency runtime control for production Python agents - stop loops, retry storms, and budget burn

Open-source CI contract testing for tool-using AI agents.

Compliance infrastructure for AI agents — runtime monitoring, audit trails, guardrails.

Python SDK for AgentGuard — the firewall for AI agents

Runtime security guardrails for AI agents — inspect, control, and audit every tool call. Zero-dependency local mode included.

agents based on pyautogui

Agent Gym - Pytorch

Production-grade guardrails for AI agent function calls. Prevent overspending, unauthorized purchases, unsafe deletions, and more — with Human-in-the-Loop approval.

Agent-native web framework with harness engineering for Python

A runtime governance layer that enforces hard behavioral bounds in autonomous agents.

Turn any SKILL.md into a runnable AI Agent

A production-ready, observable, and reliable AI agent orchestration framework.

Python SDK for AgentHelm - AI Agent Control Plane

A unified agent framework for connecting workflows, databases, and agents

Detect AI agent runtimes and adapt CLI output.

Official Python SDK for AgentOS — observability, runtime, and security for AI agents.

Shared versioned state for multi-agent AI workflows

Declarative agent hooks manager.

MCP server to search and discover connectors from AgentHotspot.com marketplace

Tracks down every bug in your agent workflow.

AgentHub anthropic package

CLI tool for AgentHub — AI Agent Skills Registry Platform

AgentHub core package

AgentHub openai package

A framework for building and running AI agents

AgentHub is the LLM API Hub for the Agent era, built for high-precision autonomous agents.

AgentHub - The App Store for AI Agents

Shared schemas, adapters, and parsers for Skills Registry Platform

Python SDK for AgentHub — a decentralized AI agent marketplace on MultiversX

AgentHub core package

AgentHub duckduckgo package

Minimal SDK for building Agent Hub compatible agents

Ergonomic LLM Agents

Agentia Web App and API Server

A flexible agent library.

Claude CLI transcript indexer and MCP server

Python framework for implementing multi-agent systems

Detect agentic coding tool adoption across GitHub organizations

A proactive AI coding advisor MCP server — orchestration layer for agentic development workflows

Streaming validation shield for AI agents

Pydantic agents for interacting with various backends.

Agentic AI based Device Attributes Analysis Demo for fraud prevention

Python modules for the Agentic AI Engineering course by Towards AI and Paul Iusztin.

Production-grade LLM gateway with cost tracking, budget alerts, conversation memory, streaming, guardrails (PII/injection defense), Redis caching, and multi-provider routing

A lightweight agentic AI framework with MCP tool serving

SDK for building AI agent 2.0.

provide SAP agentic AI tools

AI-powered documentation generator for large codebases with interactive mindmap visualization.

This name has been reserved using Reserver

This name has been reserved using Reserver

Agentic AQUA — MCP server for Liquid Network and Bitcoin wallet operations

Multi-model consensus via Cursor Cloud Agents

Agentic Astra MCP Server

Python SDK for AgenticAudit — open-source compliance monitoring for AI agents

CLI hook for Claude Code and Cowork — automatic compliance monitoring for AI coding agents

MCP server for AgenticAudit — lets AI agents query their own compliance audit trail

A Python SDK for MCP tool integration with LLM providers

Agentic Beacon CLI - Distribute knowledge contexts and skills for AI-assisted development teams

Behavioral validation toolkit for AI agents in regulated environments. Checks whether agents follow the correct process — not just whether they produce correct outputs.

Simple building blocks for agentic AI systems with MCP client and conversation management

Bootstrap CLI that hoists the shared agentic-system surface into consumer repos.

Agent-safe BigQuery client with guardrails, cost controls, and tool wrappers for agentic AI.

Portable binary graph memory for AI agents