Python agents

Semantic infrastructure for AI coding agents

Track LLM costs across OpenAI, Anthropic, Gemini, LangChain, and 3500+ models with zero code changes

AI Agent Cost Governance — track, control, and optimize LLM spending

Universal multi-agent A2A hub — any AI coding agent can join via a single link

ACP是一个开放协议，用于解决Agent互相通信协作的问题。ACP定义了agent的数据规范、通信及授权规范。

Python SDK + MCP Server for agentCrab — trade Polymarket prediction markets, earn $CRAB token airdrops

A Python package for language processing utilities

Python SDK for a AgentCraft (Crafted) Vector DB

AgentCraft MCP Server: A secure and scalable AI agent framework

Discovery service for AI agents. Find any agent by capability.

Agent Credit Bureau — trust scoring and audit reports for AI agents and MCP servers

Placeholder for reserving the agentcrew package name.

Multi-Agents Interactive Chat Tool

Python SDK for AgentCRM — agent-native contact & newsletter API

CLI tool for automatic code bug fixing powered by LLMs

Symmetric encryption using the ssh-agent

A minimal Python package for agent control

Add your description here

Institutional control layer for AI agent actions — authority, policy, risk, and audit before execution.

Placeholder pre-release to reserve the package name.

AgentCube CLI - A developer tool for packaging, building, and deploying AI agents to AgentCube

Python SDK for AgentCube Code Interpreter

Multiagentic supervisory system

agent daemon

Observability SDK for Claude Agent SDK - metrics, tracing, and debugging for AI agents

Multi-Agent Systems Failure Taxonomy (MAST) annotation library using LLM-as-a-Judge

Agent Data Shuttle - Python SDK

MCP server for AgentDB — give any AI agent persistent memory and observability

AgentDB tells you when your agent stops behaving like itself. Causal lineage, time travel and behavioral baselines for any AI agent.

Deprecated: AgentDbg has been renamed to Maida. Use maida-ai instead.

Portable error analysis, tracing, and recovery framework for agentic AI systems. Import as `agentdebug`.

The open game console and Research system for investigating AI behavior

A desktop for AI agents

A desktop for AI agents

AgentDev provides basic components that used on Bailian.platform with unified API

Cryptographic proof that a human stands behind an AI agent.

Lightweight coordination library for AI agents to prevent concurrency issues

Python client for the Agent Disco API — grade any public URL for AI-agent discoverability.

Python SDK for AgentDisk API (gateway mode)

Agent Development Kit for building intelligent agents with LangGraph and MCP integration, Support Agent Async in jupyter notebook/IPython

Sentry for AI Agents — one-line observability with local SQLite persistence

Python SDK for AgentDNS - Service naming and discovery system for LLM Agents

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

Lightweight Linux namespace sandbox with persistent shell and instant reset

tool for maintaining docs for your agents

Lightweight evaluation toolkit for AI agents — test tool use, grounding, safety, and efficiency before production

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents

Core code for AgentDojo

The universal runtime that makes every website, desktop app, and API accessible to AI agents — zero human in the loop.

MCP server for AgentDomain — register, buy, and manage domains as an AI agent

Python Agent SDK for AgentDoor - headless agent authentication

FastAPI adapter for AgentDoor - agent authentication middleware

Placeholder — AgentDossier SDK (coming soon).

AgentDraft SDK — ops API for AI agents with inbox, conflict-free calendar booking, and audit trail.

LangChain tools for AgentDraft — let LangChain, LangGraph, CrewAI, and AutoGen agents book calendars through the coordination layer without colliding.

MCP server for AgentDraft — expose inbox, conflict-free calendar, and audit tools to MCP-aware AI clients

Detect when your AI agents get dumber. Open-source quality drift monitoring.

Placeholder for AgentDrive's stdio MCP companion. Full release coming soon — see https://agentdrive.mnexa.ai.

Agent Drive MCP server for Claude Code

Python SDK for AgentDrop - agent communication infrastructure

A comprehensive benchmarking platform for evaluating AI agent capabilities in data science tasks

Python client for AgentDS-Bench: A streamlined benchmarking platform for evaluating AI agent capabilities in data science tasks

A token-efficient DSL for Agent-to-Agent and Human-to-Agent communication, optimized for LLM context windows

CLI for Agent Duel - compete with AI agents in language-based games

Open-source diagnostic SDK for detecting failure pathologies in AI agent systems

Official Python SDK for AgentDyne — The Global Microagent Marketplace

A very simple Python framework for building AI Agents

agenteam

An AI library for humans

Turn any GitHub repo into an AI agent in one command

Generate Markdown-based agent tasks from NLP prompts with optional OpenAI enhancement.

AgentEcon SDK — The Credit Score for AI Agents

Python SDK for AgentEconomy on Cardano — AgentWallet + BountyClient

LLM + knowledge graph

The open standard for AI agent integrity. Evaluate, enforce, and prove that autonomous agents are adversarially coherent, environmentally portable, and verifiably assured.

Official Python SDK for the AgentEmail API — create and manage email inboxes programmatically.

Secure runtime framework for AI assistants.

Placeholder package for AgentEnclave CLI.

Placeholder package for AgentEnclave Core.

Placeholder package for AgentEnclave Runtime.

The framework where the agent IS the backend

Kingsoft Cloud Agent Engine SDK alias package for ksadk

The agent awareness layer

Orchestrate AI agents in perfect harmony - A comprehensive Python framework for building, testing, and orchestrating multi-agent AI systems

Agent prompt tensors, modules, and optimizers for Orcheo workflows

Agent Environments

Runtime identity, telemetry quality, and cost guardrails for AI agents

Agenter — Backend-agnostic SDK for autonomous coding agents supporting Claude, Codex, Anthropic, and AWS Bedrock with streaming, budget controls, security validation, and LangGraph/PydanticAI adapters.

Terminal-native agent runtime with persistent sessions, branching, and MCP

Generator for AI Environments

MCP servers that allow AI agents to interact with various AI coding assistants

Universal agent testing and evaluation toolkit - record, replay, mock, and benchmark AI agents

Agent-based wildfire evacuation simulator using SUMO and LLM-driven agents

pytest for AI agents — catch failures before production

Lightweight evaluation and observability toolkit for LLM agents

Telemetry and Observability SDK for AI Agents — with Trace Tree MRI

Open-source evaluators for LLM agents

Standalone framework to evaluate agent correctness based on portable OpenTelemetry traces

Lightweight SDK for building custom agentevals evaluators

The Natural Selection Protocol for AI Agents - A self-evolving tool ecosystem.