PyPI agents

A reusable memory layer for SAP agentic workflows

Lightweight memory store for AI agents — pure Python, zero dependencies

MCP server for Agent Memory — Telegram memory layer for AI agents

Persistent memory for AI agents — store, retrieve and search knowledge across sessions

A Memory Server for LLM Agents and Applications

Placeholder package — install mcp-memory-service instead.

Long-term memory management for AI agents

Hybrid retrieval memory for AI agents - BM25 + vectors + knowledge graph with RRF fusion

Multi-agent communication, task routing, and workflow orchestration

Migrate conversation history between AI coding agents

Ultra-lightweight personal AI agent — shell, files, web, memory — powered by local or cloud LLMs

A comprehensive monitoring solution for AI agent frameworks including Langchain, CrewAI, and Agno. AgentMont provides enhanced metrics and deep observability for production AI agent applications.

Multi-layer security analysis engine for AI agents

Give your AI Agent a break with a virtual coffee.

AI-powered agent negotiation MCP server for agents. Supports propose deal, evaluate offer, counter offer. By MEOK AI Labs.

Nexus is an autonomous CLI coding agent powered by LangGraph and MCP. It plans complex tasks, persists context via SQLite, and securely orchestrates tools. Features specialized Architect/Code modes, real-time metrics, and human-in-the-loop safety for production workflows.

AI agent configuration manager for Claude Code, OpenCode, and Copilot

Universal MCP notification relay — polls MCP servers and streams change events as log notifications

Cross-platform notifications for long-running agentic CLI tools

Cross-platform notifications for long-running agentic CLI tools

Universal MCP notification relay — polls MCP servers and streams change events as log notifications

Cross-platform notification system for AI agents (Claude Code, Gemini CLI) with ntfy.sh support

A Python SDK for MCP tool integration with LLM providers

Lightweight Python SDK for Agent Observability Tracing — instruments multi-agent AI workflows

Agent observability with cost tracking and compliance audit trails

AutoGPT plugin for Agent Observability - automatic logging, cost tracking, and compliance

CrewAI integration for Agent Observability - multi-agent logging, cost tracking, and compliance

LangChain integration for Agent Observability - structured logging, cost tracking, and compliance for AI agents

Real-time monitoring and debugging platform for multi-agent AI systems

Observability primitives for AI agents (tracing and streaming introspection)

Framework-agnostic observability, audit, and eval for AI agent applications

Python SDK for Agent Office API - AI-powered document editing

Official Python SDK for Agent OnBoard — the identity and trust network for AI agents.

Open-source agent operations SDK — integration discovery, security scanning, autonomy rules, HITL primitives, and capability management for Python agentic systems.

Agent Ops (AO) - high-performance JSONL issue/event store

A library for prompt optimization.

A framework for building composable, observable, and maintainable agent workflows

Orquestrador de Agentes de IA para Desenvolvimento de Software

MCP server for agent orchestrator. Features create agent, list agents, delegate task. From MEOK AI Labs.

基础智能体构建库

Modern Python CLI for AgentOS - Streamlined AI-assisted development environment management

Production observability for Agent OS - OpenTelemetry traces, Prometheus metrics, Grafana dashboards

A library and runtime to build autonomous AI agents.

智能体服务

面向LLM的工作流图嵌套调度框架

Drastically reduce token consumption for unittest and pytest runs

Building the infra for Claude Code-native deep research

Python SDK for the Agent Passport System. Identity, delegation, governance, data source registration, training attribution, per-period attribution settlement, mutual authentication, evidentiary type safety, Wave 1 accountability primitives (action, authority-boundary, custody, contestability, bundle), Cognitive Attestation, Instruction Provenance Receipts. Cross-language parity with agent-passport-system npm v3.3.0 tested against byte-identical canonical JSON fixtures.

Runtime pathology detection for AI agents. Diagnoses loops, stalls, oscillation, drift, and silent abandonment.

Reusable AI agent workflow patterns using LangGraph and LangChain

Production-ready boilerplate for common agentic AI patterns in Python

SDK for AI agents to make payments on merchant websites, make transfters and other kinds of bill payments.

Payment infrastructure SDK for AI agents — crypto, card, and ACH in one SDK

Simple infrastructure to enable payments for AI agents

An SDK for LLM tracing and more.

LLM-agent working memory as a session-scoped fact graph: a @pin decorator extracts facts from tool returns, ready-made graph-read tools let the LLM navigate them.

Unified pipeline orchestrator — fluent builder API for composing agent execution pipelines.

A lightweight production ready agentic framework to build your agents

사용자 맞춤형 AI 에이전트 플랫폼

The Storybook for AI Agents

Local-first playground for experimenting with simple AI agents and sandboxed Python execution.

Builder for Agent Plugins.

Local-first diagnostics for MCP and AI coding-agent plugin setups.

A simple SDK for deploying agent pods using FastAPI and SSE.

Per-agent-pair IAM for A2A. Define policies ('orchestrator may call billing only when amount<1000'), gate every A2A call via evaluate_call. EU AI Act Art 14 + ISO 42001 Annex A.7 evidence with signed policy-decision attestations.

Deterministic, capability-based policy enforcement runtime for AI agents

Policy enforcement and taint tracking for AI agent tool calls.

Compliance & guardrails for AI agents — PII filtering, audit logging, GDPR/AI Act checks, kill switch

Agent Policy Layer - Portable, composable policies for AI agents

Generate and safely update agent-specific instruction files from one engineering policy

Preview and validate AI agent actions before execution.

Shared primitive data models for Agent OS - failure types, severity levels, and base structures

Agent-level adversarial resilience testing. Tests what others don't: tool interactions, memory poisoning, confused deputy, cost bombs.

The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool arguments, A2A payloads for OWASP LLM01 prompt injection BEFORE they reach a downstream agent. Curated from OWASP + academia + production incidents.

API for interacting with Agents that use the Agent Protocol

Agent Communication Protocol Client

One-shot multi-registry release publisher for OSS packages (Python port of @p-vbordei/agent-publish)

Pub/sub messaging infrastructure for AI agent systems.

Autonomous AI consulting agency — a swarm of specialized agents built on pydantic-ai, litellm, and Puter.js

A python wrapper around the Agent REST API.

Visual browser QA console for AI coding agents — live browser, element selection, source mapping, RTL/a11y/perf audits, and test-fix-verify loops.

Evaluation package that allows benchmarking of agentic AIs from various sources and frameworks by producing statistical results which can be compared across different use cases and datasets.

A quantitative trading system development framework for A-share stock market

A private task queue system for agents using Redis + Celery with gRPC interface (Client Package)

Agentic RAG framework - Coming soon. Part of the AIH-Infra ecosystem.

RAG MCP server: ChromaDB + sentence-transformers, exposes ingest/search/list/delete tools.

put your agents on guardrails

Intelligent rate limit handling for AI agents

Fleet-wide shared rate limiter for A2A + multi-MCP deployments. Most MCP servers rate-limit independently — a hostile agent hitting 10 MCPs gets 10x quota. This MCP is the shared counter: every MCP checks here before allowing a call. Sliding window + concurrency grants + signed enforcement attestations. By MEOK AI Labs.

Decentralized agent reputation protocol — signal composition, portable reputation bundles, Merkle verification, and anti-Goodhart architecture

Role-Based Access Control for AI Agents with ML-Powered Anomaly Detection

A lightweight Python protocol for agent-oriented documentation

Intelligent Reader of various types of media

Benchmark how agent-ready a code repository is for LLM coding agents.

Score any URL for AI-agent readiness — llms.txt, JSON-LD, AI-bot robots.txt, canonical, MCP, meta, sitemap.

Shared schema, dataclasses, and version constants for the agent-readiness insights ecosystem.

MCP server exposing agent-readiness scan, detect, and apply tools to coding agents.

A tool to analyze codebases for AI-Agent Friendliness