PyPI agents

Multi-agent message broker for AI agent coordination via MCP

Agent workflow graph visualization plugin for LangGraph and other frameworks

Deterministic spatial multi-agent environment with an LLM-agent framework, verifiable rewards, and a connect-out benchmark platform

SDK for Agentzon, the everything store for AI agents on Solana. Discover, register, list and execute agent skills, settled in $AGENTZON.

Sidecar bridge that puts any local agent (OpenClaw, Hermes, …) on Agora — wraps pippa-agora-sdk (unmodified) behind a tiny localhost HTTP API + pluggable connectors.

AI Agent 框架——多模型 ReAct 引擎 + MCP 集成 + Coze 工作流 + WebUI + 可视化编辑器

AG-UI ↔ Claude Agent SDK protocol adapter

独立于具体 Agent 的持久化记忆层 (MCP Server),可被 Claude Code / Qoder / Cursor 复用

A Python CLI tool built with ConfigArgParse

Local-first, offline-by-default security posture scanner for MCP / local-agent setups.

MCP server for ai·rete·rag — deterministic rule-based decisions with RAG-powered explanations

Production-grade AI agent orchestration system — Boss, Manager, Coder, Critics, and Worker pipeline

AI2Human Coinbase AgentKit integration — CDP agents dispatch human-execution tasks with proof verification.

AI37 agent host (Python): A2A + AG-UI + MCP + file-aware store backends поверх a2a-sdk и ai37-agent-sdk. Порт @ai37/agent-host.

AI37 agent SDK (Python): JWKS auth + billing + A2A forward for ecosystem agents

Code-first agent memory SDK for AideMemo (aidememo)

Parses and packages AIND VR Foraging behavioral sessions into tabular (parquet) and NWB outputs.

AirGPTX Python package with the bundled AirSim client APIs.

Store time series data as HDF5 files and access them through an API.

Python implementation of Claude Code - an agentic coding assistant in your terminal

An MCP which adds terminal capabilities to an agent

Collaborative agent patterns for the Akgentic framework

LLM integration layer for Akgentic agent systems

Alibaba Cloud AgentTeams (20260605) SDK Library for Python

Alibaba Cloud OssAgent (20260622) SDK Library for Python

Protobufs generated by Alis Build

Protobufs generated by Alis Build

Event-sourced memory and orchestration server for multi-agent AI systems

Multi-agent stock & crypto screening with leakage-aware (point-in-time) LLM evaluation and an honest, mechanical backtest.

Haystack components for AlphaAI: AI-scored financial news and SEC Form 4 insider events as Documents.

Open AI API compatiable LLM server for Amlogic Device

Local-first, privacy-preserving genealogy CLI with modular LLM providers.

Ant Chain AGENTCREW SDK Library for Python

Ant Chain RESOLVEAGENT SDK Library for Python

Local privacy and proxy consistency audit skill

General-purpose agent runtime with multi-agent orchestration, MCP tool integration, and WebAssembly support

Generate agent tools (and an MCP server) from your API — then verify each tool against the live API, repair what breaks, and grade whether a real agent can finish real tasks.

DEPRECATED — renamed to mcp-agent-health. See README for migration.

Provider package apache-airflow-providers-anthropic for Apache Airflow

Feather durable execution platform — Python SDK

Feather durable execution platform — Python SDK

Python SDK for AI agent payments on Arc using USDC nanopayments (x402 / EIP-3009)

Keep code adherent to a described architecture; teach coding agents to reason about it.

Ares — AI-native host security investigator for Linux: continuous eBPF telemetry with minute-by-minute AI investigation.

Argon adapters for AI agent frameworks: sandboxed, versioned MongoDB for LangGraph and Mem0

Official Argorix Agent Guardrails SDK for Python agents and tool execution

Argus RedTeam local security scan agent — code never leaves your infrastructure

Argus RedTeam local security scan agent — code never leaves your infrastructure

AI Agent-first aria2 RPC wrapper with MCP support. Kills the pre-allocation false-positive problem forever.

Cross-platform AI agent — chat, web answers, password vault, and skill routing

Astra — a terminal AI assistant that understands natural language and drives your dev tools.

The ergonomic, standalone Python SDK for agentic payments: embed payments in your product (or give your AI agent a payment tool) under a signed, capped, payee-scoped contract over HTTP. Three nouns — agent, contract, payment.

LangChain integration for Attestari — the auditable memory layer for AI agents.

An enterprise-grade autonomous ReAct agent framework with token streaming and hierarchical orchestration.

Local-first runtime evidence SDK with a self-serve AURORA quickstart

LLM agent library with tool use, dynamic tool generation, and software evolution capabilities

Agent: text / field layout -> dashboard in selected BI on top of DWH DM layer

MaaFW agent command plan and environment preparation plugin for AUTO-MAS

aws_sdk_bedrock client

aws_sdk_bedrock_agent client

aws_sdk_bedrock_agent_runtime client

aws_sdk_bedrock_agentcore client

aws_sdk_bedrock_agentcore_control client

aws_sdk_bedrock_data_automation client

**AzerAI Agent Creator Plugin** - Yeni AI Agentləri Yarat Plugin

Activity protocol host for Azure AI Hosted Agents

This package will be released in the near future. Stay tuned!

Baidu Cloud agentidentityApi SDK Library for Python

Resilience and cost-control plane for multi-agent AI systems: circuit breakers, backpressure, cost-aware fallbacks, and chaos testing

Query-aware context trimming for LLM requests. Your context could use a trim.

Checker and validator for the Barrage language — makes code readable by anyone

Local Apple Silicon LLM Coding Agent Runtime & BaseRT Task Orchestrator with HDAR Receipts

LangChain tool: scan Base contracts via BaseSentinel (HTTP 402 + USDC tx-hash proof).

Local-first operating system for AI-agent teams: resource governance, gated workflows, and multi-project orchestration on top of Agent Memory OS.

Reserved package name for Bateleur (bateleur.aero). Distributed via private registry.

Embed text with AWS Bedrock and read/write AWS S3 Vectors

Mobile-first PWA remote control for Claude Code sessions on your Mac

Bharat-Tiny-LLM v2 - 33.8% Hindi token compression via Brahmi injection. 1.5B LLM runs offline on edge devices.

Context apoptosis for LangChain: µs-scale, class-aware history pruning (B.I.O.M.A. kernel) as a drop-in Runnable.

Contract-bounded autonomy for LLM agents: five small primitives that make an agent safe to leave alone.

Fast, validated and differentiable Bragg powder diffraction

Bragg Edge modeling

Python SDK for Bragi — parse PDFs into typed semantic document graphs

BridgeNode LLM client — AI inference with x402 payment on Solana USDC. No API keys, no registration.

Reserved namespace placeholder. The real brink-litellm-plugin is not yet public — see README.

Cloud-native LLM Agent Development and Testing Toolkit

MCP server for Cairn reminders — lets an AI agent create, list, complete and delete reminders on a Cairn backend over a signed agent API

Cambrian Agent SDK — build Cambrian agents in Python with zero boilerplate

The Cardinal agent-telemetry contract: OTLP emission, initiative resolution, spend-limits delivery, device-code consent.

LLM Pipeline Query Optimizer — automatic model routing, cost optimization, and quality-aware escalation.

A small OpenAI Python SDK based personal AI agent with local skill support.

File-backed mail, MCP tools, push delivery, and authenticated browser messaging for Codex agents

Typed async Python SDK for the ChainlessChain cc agent NDJSON protocol

Experimental subject-scoped ChatGPT OAuth and subscription transport

ChatGPT PlayWright API

ChatML for LLM

Local analytics for Claude Code project exports

An open-source, self-evolving AI agent whose reasoning core is an LLM-Fusion engine (panel -> judge -> synthesizer).

A Python utility package containing reusable helper classes.