Python agents

An AWS Labs Model Context Protocol (MCP) server for AWS Security Agent — automated security scanning, penetration testing, and remediation

LLM-based gray-zone verifier for axor-core anomaly detection

Python bindings for bedrock-crustaceans/nethernet - Minecraft Bedrock WebRTC transport

This is a reserved placeholder package to mitigate dependency confusion risks.

Advanced LLM architecture augmentation library - surgical model expansion with minimal compute

Counterfactual replay and causal attribution over LLM-agent trajectories: find which step actually caused a bad outcome by intervening on it.

Drop-in replacement for claude-agent-sdk that adds a proxied telemetry pipeline (PII redaction + guardrails) with OpenTelemetry and AgentOS sinks.

Run Python code in a MicroPython/WASM sandbox

RENAMED: this package is now 'langstage-hermes' (LangStage family). Installing this pulls the new package.

DEER - Deterministic Executable Engine for Runtime-agents

Opinionated semantic API for Divoom ambient displays — ambient.thinking(), ambient.shipped(), etc.

MCP server exposing the divoom-agent semantic API as tools for LLMs (Claude, etc.)

Du-RAG: Durable RAG — persistent memory for AI agents

Personal AI agent with daily-driver CLI, modal TUI, and graph-based memory

Catalog Web Import Agent for Enthusiast

Invoice Scanning Agent for Enthusiast

Shared tools for Enthusiast agents

A plugin for Enthusiast that provides an Anthropic connector.

Run Fleet-exported agents as standalone deepagents projects

Free LLM gateway: 22 LLM providers, 178 enabled chat routes, 431 cataloged chat models; keyless start when available.

Reusable Harbor custom agent that runs Pi SDK sessions and writes trajectory artifacts.

Official Python SDK for building, deploying, and managing HIPAA-compliant AI agents on the Hikigai healthcare platform. Supports Google ADK agent types (LLM, Sequential, Parallel, Loop), MCP connector integration, BYOK model configuration, and one-line Cloud Run deployment.

AI-powered code reviewer and autonomous developer agent

NL2GQL Agent — 安全图谱自然语言查询服务

Jumping Rivers: Prompt Craft

Self-hosted observability dashboard for agentic flows — every LLM turn, tool call, and failure captured

A comprehensive toolkit for LLM context management with intelligent metadata selection and contextual question resolution

Zero-dependency LLM hallucination detection middleware with billing & dashboard — real-time fact-checking proxy for LLMs

Use free LLMs in Simon Willison's llm CLI via freellmpool — pool 16 free providers, works with zero API keys.

A multi-dimensional behavioral framework for evaluating LLM reasoning quality beyond accuracy

An all-you-can-eat buffet of free-tier LLM APIs behind one OpenAI-compatible endpoint, with automatic failover and quota tracking.

Reference Python agent for the LLMOps.Pro sovereign-AI substrate. Consumes the five MCP servers (nwc-mcp, nostr-ops-mcp, marketplace-mcp, albyhub-admin-mcp, paywall-mcp) and demonstrates the agent-pays-paid-MCP loop end-to-end. Ollama-first, API-pluggable. Built on pydantic-ai — no LangChain. MIT.

CrewAI observability, local-first: one line of setup traces crew kickoffs, agents, tasks, tools and LLM calls to a Lookspan dashboard on your own machine.

LangChain and LangGraph observability, local-first: a callback handler that traces chains, graph nodes, LLM calls and tools to a Lookspan dashboard on your own machine.

Framework-agnostic RAG evaluation library — fully local, no LLM API required

A reusable mathematical derivation and verification framework with 12 engines, supporting ODEs, PDEs, analysis, optimization, and formal proofs.

MCP server for AI Agent interview simulation with RAG knowledge base

YAML-defined agent orchestration framework powered by PydanticAI

AI Infrastructure OS — same engine, four facades (CLI, REST, web, MCP). Reduce 80-95% of AI spend by routing tasks to the right model.

Alpha agent trust middleware: audit trails, safety guardrails, HITL, and tool validation

Python SDK for controlling the native agent-browser engine in-process

MCP server that probes, scores, and certifies RAG pipeline compliance — EU AI Act, GDPR/DPDP, HIPAA, SEBI/RBI

Experimental Gemini FunctionDeclaration adapter for Stigmem.

Experimental OpenAI-compatible tool-use adapter for Stigmem.

A model-driven approach to building AI agents in just a few lines of code

Teradata SDK for OpenAPI-based dynamic client generation

Stream-optimized, x402-gated grounding retrievers for LangChain and CrewAI

Turn any video into LLM-ready frames. Smart sampling, scene detection, OCR, and SDK-ready output for modern multimodal language models.

Lightweight monitoring dashboard for vLLM inference servers

AAEP integration for agents built directly on the Anthropic Python SDK

AI Design Slop Index audit engine, schema, CLI, and agent adapters.

Generate short, useful AGENTS.md files without repeating what the repo already says.

Local agent manager/worker conveyor control plane for Codex sessions.

Intercept and log AI coding agent <-> API traffic for prompt-architecture analysis.

AgentAdmit SDK: user-mediated AI agent authorization for any app

Chaos Engineering & Failure Diagnosis for AI Agents

A safety layer that lets developers use AI coding agents at work without triggering security alerts

FastAPI middleware for verifying agent requests using the Agentis identity platform

Multi-agent framework with persistent expert sessions and context isolation — MCP server for Claude Code

Production-readiness platform for AI agents — inspect, improve, and stress-test before you ship.

AI Agent Security Scanner — detect tool-calling vulnerabilities in LLM agents

LLM abstraction layer for the AIDu ecosystem.

Alibaba Cloud SearchAgent (20260515) SDK Library for Python

CLI + TUI for viewing Claude Code usage statistics from local session files

Claude Code hook that reads assistant messages aloud via a local TTS engine

MCP server and Claude-powered CLI for Mega.nz, Box, and OneDrive — one tool to manage all your cloud storage

Docker-backed sandbox backend for DeepAgents

LangChain tools for easycome social media data APIs

LangChain integrations for Exabase memory

Shell LLM client control plane for semcod/coru automation.

GUI Control Plugin with NLP & Intent Contracts

A programmatic git ratchet system for automated agent guarding.

Python client for the Guerrilla Mail disposable email JSON API

Python SDK for H Company's Agents API: autonomous agents powered by Holo.

Production hardening pack for Hermes Agent — per-topic model routing, fallback chains, rate limiting, and cost tracking via gateway hooks

Token efficient IDs for AI agents. UUID alternative for the agentic era

Jumping Rivers: Shiny Meets LLMs

Instrument LLM clients and emit usage events to Lago.

LangChain integration for the Diffbot Knowledge Graph and Extract APIs

Monty-backed code-interpreter middleware for LangChain agents

LangChain connector for Noxy human-in-the-loop — interrupt/resume with relay outcome polling via noxy-sdk.

LangChain tools for ZeroGPU: A compute-efficient inference provider for apps and agents — purpose-built small and nano language models on an edge network that run the repeatable tasks frontier models shouldn’t, ~10x faster and 50%+ cheaper. Auto-scaling, with zero GPU infrastructure. Plug in and you’re live.

LangGraph connector for Noxy human-in-the-loop.

Retrieval-Augmented Generation (RAG) pipeline for the Lexigram Framework

One-import LLM Observability SDK — traces, metrics and cost tracking via OpenTelemetry

Self-hostable LLM observability SDK — trace, cost, and hallucination monitoring in one line.

LangChain tools for Mapsi geospatial APIs — geocoding, routing, isochrone, places

MongoDB Atlas-backed persistent agent memory for mcp-agent (LastMile AI): a drop-in Memory backend with Atlas Vector Search recall.

Mega.nz MCP server and Claude-powered CLI for cloud storage management

Meris — model-agnostic coding agent with a per-project agent harness (.meris/)

Official Python SDK for Najumi Storage with Global Migration support

Python bindings for newt-agent — agentic coder runtime (newt-core, newt-tools, newt-coder, newt-eval, newt-inference, newt-acp-worker, newt-mcp-server submodules)

Noosphere Prime SIGMA Tools for LangChain — sovereign risk intelligence for AI agents

LangGraph source connector for OpenWright — capture agent decisions, tools, and human-in-the-loop approvals as evidence.

Add crawling capability to pydantic ai agent

易于理解、可融入最佳实践、且真正可用的 ReAct 单 agent Python 框架（核心循环 ~30 行）

ANSI console control utility

Search as Code (SaC) — agentic search orchestration using LLMs

Frictionless Salesforce Agent Skill for Codex, Claude Code, and GitHub Copilot.