Python agents

agentlabs: A Python library for implementing agents on Weavel

AgentLabs SDK for Python

An event-based runtime and messaging framework for AI agents.

Language-first AI Agent Framework - 以自然语言为核心构建 AI 智能体的框架

Devtool to document and inspect LLM agent systems.

Governance SDK for AI agents — audit trails, policy engine, approval gates.

Law-first governance kit for AI coding agents: installable scaffold + memory MCP server that lets agents read project rules before they write code.

Agent Layer

...

Python SDK for AgentLeague — the autonomous AI agent competition platform

A recursive learning framework that gives any AI agent a self-improvement loop with memory

Deterministic run ledger for AI agents

LangGraph-compatible adapter package for AgentLedger

MCP tool and context adapter package for AgentLedger

OpenTelemetry/OTLP trace export adapter package for AgentLedger

Postgres StateStore adapter package for AgentLedger

Python SDK for AgentLedger - AI agent observability and budget management

Runtime reliability layer for Agent Harness stacks

Vendor-agnostic agent framework abstraction layer - Terraform for AI Agents

AgentLego is a versatile tool library for enhancing LLM-based agents.

Python agent for coding and research

lightweight abstractions for building agent scaffolds

Audit logging for Claude AI agents — transparent, tamper-evident, OSS

AgentLens Python SDK — fleet governance for multi-framework agent stacks

MCP server for AgentLens — zero-code observability for MCP-native AI agents

LLM observability, quality scoring, hallucination detection, cost tracking, agent run debugging, and drop-in LangChain + LlamaIndex callbacks — in 2 lines of code.

Debug AI agents visually — self-hosted, open-source observability SDK

Profile AI agents by intercepting LLM API traffic through a local MITM proxy

Pre-Installation AI Agent Tool Risk Analyzer

Python SDK for AgentLens — observability for AI agents

AgentLens observability server for AI agents

The interactive debugger for LLM agents. Pause, inspect, and fork any agent mid-run.

Track and debug AI agents step-by-step

Local-first AI agent debugger with fork & replay

Python SDK for AgentLens — observability and audit trail for AI agents

See what your agents think. Open-source AI Agent observability platform.

This tool can help you scan the network

agent for fun

Framework for development and execution of agents for control and simulation of energy systems.

Framework for development and execution of agents for control and simulation of energy systems.

Agent Lightning — agentic RL infrastructure

General Agent Framework by LinXueyuan

The official Python library for the client API

Phone numbers, SMS, email, and voice for AI agents.

MCP server for Agentline — give your AI agent a phone number, email, SMS, and voice calls.

Lightweight A2A + MCP single-process agent framework

SSH-based communication layer for distributed agents

MCP server for AI agent control of test and measurement equipment via PyVISA

Real-time quality guardrails for AI coding agents

Lint, score, and optimize AI agent configuration files (CLAUDE.md, AGENTS.md, Cursor rules)

Estimate costs and lint agent workflow YAML files

Light Library for Building LLM Agent System

A small, focused library for building Claude-powered agents in Python.

Authorization framework for AI agent tool calls. Your AI agent needs a login screen. AgentLock is that login screen.

AgentLock Python SDK for AI agent integration

Persistent decision memory for any project. Karpathy's LLM Wiki, productized.

Trace AI agent execution — LLM calls, tool calls, costs and latency

Python SDK for agentlog - a local-first decision log daemon for agentic workflows

Simple, colorful debug logs and logfiles.

Python SDK for AgentLogs — open-source observability for AI agents

CrewAI tools for the AgentLookup public AI agent registry

LangChain tools for the AgentLookup public AI agent registry

Production-ready agentic workflow orchestrator with native observability, resilience, and cost control.

A simple, lightweight loop for your agent.

A mem0-compatible memory SDK powered by Alibaba Cloud AgentLoop (CMS)

Virtual filesystem for Alibaba Cloud CMS AgentLoop Memory API - Agent-friendly design

AgentLoop SDK — middleware that turns human corrections into searchable memory for your agent.

Drop-in Anthropic SDK wrapper for AgentLoop — adds memory retrieval and turn logging to messages.create calls. Supports streaming.

LangChain integration for AgentLoop — auto-logs turns to the review queue and provides a memory injection Runnable for retrieval.

Drop-in OpenAI SDK wrapper for AgentLoop — adds memory retrieval and turn logging to chat.completions.create calls. Supports streaming.

SDK for the Alibaba CLoud AgentLoop platform. https://agentloop.console.aliyun.com/

The intelligence layer for AI agents. Self-learning loops that make your agents smarter over time.

AI application development framework for stable structured outputs, observable actions, and durable workflows.

Declarative AI Agent Framework

Observation and developer tooling companion package for Agently

Official SDK for developing extensions for the Agently framework

Agently Stage - Efficient Convenient Asynchronous and Multithreaded Programming

Agently TriggerFlow - Arrange GenAI Application Workflow Based On Event-Driven Triggers

A standalone workflow spun off from [Agently](https://github.com/Maplemx/Agently), featuring minimal third-party dependencies (e.g., json5).

Lightweight AI agent library. Turn Python functions/classes into AI tools instantly.

Shared tools for Agentlys

AgentM SDK

Client SDK for Agent-M Params service

Stdio compatibility bridge for the hosted AgentMail MCP server

Python SDK for AgentMail — open-source email server for AI agents

Client SDK for AgentMail — P2P encrypted messaging for AI agents

Official AgentMail Python SDK — API-first email inbox for AI agents

AgentMail Toolkit

AgentMake AI: an agent developement kit (ADK) for developing agentic AI applications that support 16 AI backends and work with 7 agentic components, such as tools and agents. (Developer: Eliran Wong)

AgentMake AI MCP Servers - Easy setup of MCP servers running AgentMake AI agentic components.

WebUI for AgentMake AI; AgentMake AI: a software developement kit for developing agentic AI applications that support 16 AI backends and work with 7 agentic components, such as tools and agents. (Developer: Eliran Wong)

A tool for building and managing AI agents

AgentMap: Build and deploy LangGraph agentic workflows from CSV files for fun and profit!

Cryptographic provenance for AI-generated code

Claude Agent SDK adapter for AgentMark - integrate AgentMark prompts with Claude Agent SDK

Claude Agent SDK adapter for AgentMark - integrate AgentMark prompts with Claude Agent SDK

Python prompt-core package for AgentMark - high-level runtime for working with AgentMark prompts