Source
PyPI agents
24,677 AI agents indexed on MeshKore from PyPI. Agent frameworks and tools published to the Python Package Index. Each entry links back to its project page.
24,677 agents · ranked by popularity · refine in the directory →
Source platform: PyPI →
PyPI agents — page 16 of 247
Add your description here
Replay and diff AI agent event trajectories for debugging regressions. Python port of @mukundakatta/agent-trajectory-replay.
Agent Transfer Protocol (ATP): secure agent-to-agent communication
A comprehensive library for tracking the input, thought process, and output of AI agents
SIP and audio streaming transport for AI voice agents (pure Rust)
A terminal-based tree visualizer for AI agent traces.
Rank multi-agent trace failures by severity. CLI + web dashboard + OTLP receiver, with optional LLM root-cause analysis.
Agent Tribulation — Rigorous AI Agent testing and evaluation framework.
LangChain integration for TrustAgents - protected document loaders, retrievers, and threat scanning
MCP Server for Agent Reputation & Trust Scoring
Python SDK for AI agent security - threat detection, content scanning, trust verification, and red team testing
Complete Agent Trust Stack — one install for provenance, reputation, agreements, accountability, lifecycle, discovery, and economics
Hosted trust services for AI agents — CoC Bitcoin anchoring and ATHP mutual verification
MCP server for autonomous AI agent trust — cryptographic provenance (Chain of Consciousness with Bitcoin OpenTimestamps), decentralized reputation (Agent Rating Protocol with bilateral blind evaluation). Part of the 7-protocol Agent Trust Stack.
Trust telemetry middleware for inter-agent communication — makes instruction contamination observable across traces
Terminal user interface for AI agents built on agent-core.
Local Codex plugin for iterative Agent tuning with guided Skills, reusable runner templates, versioned results, and static validation.
This package defines the interface of AI agent modules.
Reference implementation for the Agent Almanac Code Uniformity benchmark
Update Claude Code sub-agents from GitHub to your project
Agent Sandbox
Agent-based urban planning simulator with closed-form, hybrid, and full-LLM decision engines
Agent URI Protocol Implementation - A complete suite for addressing and interacting with AI agents
Generate a local dashboard from Codex CLI / Claude Code / Cursor agent logs
A Python package demonstrating how to publish 'skills-use' to PyPI
Agent Utilities for Pydantic AI Agents
A library for validating agent outputs against schemas
Lighthouse for AI agents — test if APIs and services are properly accessible to AI agents
A secure execution layer and ERC-7579/ERC-7715 identity framework for Web3 AI agents.
Zero-trust credential manager for AI agents — Python SDK
Record, replay, and diff MCP (Model Context Protocol) interactions — like VCR for AI agents
Benchmark framework for comparing LLM agent tool-call quality across vendors.
Run coding-agent CLIs in an isolated profile and workspace.
Domain-specific agent templates for common enterprise use cases
Persistent virtual filesystem for AI agents, backed by SQLite or Postgres
Standalone agent health monitor — detect loops, stuck states, thrash, and runaway costs in any AI agent workflow.
Remote voice bridge connecting phone browsers to Claude Code
A Model Context Protocol server providing VRM avatar functionality for LLMs
Agent Wallet SDK.
An operational monitoring library for Crew AI applications.
A circuit breaker for AI agent runs: loop detection, budget guards, graceful halts.
Tiny local CLI for coding-agent continuity.
Agent Wave: orchestrate parallel git worktree workflow for AI agents.
Server-side toolkit for the Claude Agent SDK over HTTP+SSE: session lifecycle, permission routing, SDK bridge, plus bundled FastAPI and Postgres adapters.
Agent Web Interface for Pydantic AI Agents
Toolkit for building agent-maintained Obsidian-style wikis — link management, linting, document conversion, and agent coordination
CLI tool to maintain hybrid LLM Wikis for multi-language projects.
Go-to-market automation — Google Workspace, LinkedIn (Unipile), and Attio CRM
CLI that packages, installs, and manages Claude Code subagent personas and workflow knowledge assets.
Reusable workflow templates for AI agents — share, discover and execute multi-step agent workflows
Batteries-included framework for building automation-focused AI agents with observability
Agent-Workstation: An fully self-hosted multimodal agent framework for building local AI applications.
Agent World Model
SDK for connecting AI agents to the Agent World Protocol
Secure ephemeral channels for AI agent communication
Secure P2P communication for AI agents with CRDT collaboration
XLSX file CLI built with Agent Experience (AX) in mind.
Local-first debugging, grading, and replay tooling for AI agent traces.
CLI tool for novel writing with Claude Code plugin
AI outbound voice agent framework
Lightweight Python AI Agent Framework with Web UI
Security harness for AI coding agents (Claude Code, Codex CLI, etc.) — mitmproxy payload inspection + TOML policy control.
Rackspace Monitoring agent.plugin HTTP check
Rackspace Cloud Monitoring plugin for PostgreSQL endpoints as an agent.plugin type of check.
Agent interface for on-chain protocols.
Python SDK for agent portability, discovery and trust based on ERC-8004
A simple LLM abstraction layer
MCP server for Agent101 — a directory of 300+ AI tools across 15 categories
Get metrics from 1C srvinfo-content
Agent2Agent server utility and boilerplate code from google.
Agent2Agent server utility and boilerplate code from google.
360 agent
A coding agent that jails model commands and uses editable state machines for long-running tasks.
A software package for the integration of metrological input into an agent-based system for the consideration of measurement uncertainty in current industrial manufacturing processes.
agentUniverse is a framework for developing applications powered by multi-agent base on large language model.
A Python package for Lit agentWallet
Local Windows desktop control for AI agents — Python library and CLI.
REST Runner
Public Preview — Unified installer and runtime policy enforcement for the Agent Governance Toolkit
Public Preview — Agent Hypervisor: Runtime supervisor for multi-agent Shared Sessions with Execution Rings, Joint Liability, Saga Orchestration, and hash-chained audit trails
Public Preview — MCP governance primitives for the Agent Governance Toolkit.
Public Preview — A kernel architecture for governing autonomous AI agents with Nexus Trust Exchange
Default template for PDM package
Uniform multi-turn session abstraction over CLI coding agents (Claude Code, Codex).
Public Preview — Reliability Engineering for AI Agent Systems
Streaming utilities for agent/LLM systems (RabbitMQ, etc.)
Agenta is the open-source workspace for your agents. Build agents through chat, improve them with feedback, and share them with your team.
Unified async Python API for driving coding agent CLIs — Claude Code, Codex, Gemini CLI, and more
Official Python package for Agentable.
Action chaining and history for agents
AgentAds monetization plugin for NVIDIA NeMo Agent Toolkit
A task manager for your agent.
A Python client for the Agent.ai API
Command-line client for agent.ai — search, describe, and chat with AI agents from your terminal.
Context compression middleware for AI agent frameworks — automatically summarizes conversation history when token limits are approached
agentalk