PyPI agents

Open-source budget controller for AI agents spending USDC on Base

Command-line client for the AgentVault ecosystem.

Native AgentVault plugin for the Hermes agent runtime — E2E encrypted owner-↔-agent and A2A messaging via MLS

Unified memory layer that consolidates history from all your AI coding agents — searchable by humans (Obsidian) and by AI (MCP).

AgentVault's patched UniFFI Python bindings for mls-rs (RFC 9420 MLS)

Server SDK for building AgentVault A2A compliant agents.

Embedded, serverless vector database for mutable AI agent memory — pure Rust, with native TTL, in-place upserts, and incremental HNSW search

AgentVectorDB (AVDB): The Cognitive Core for Your AI Agents. A lightweight, embeddable vector database for Agentic AI systems, built on LanceDB.

MCP server for AgentVee (testnet / pre-1.0) — file uploads, marketplace listings, and paid downloads for AI agents. Currently targeting the develop environment for integration testing before 1.0 release.

Python SDK for routed AI-agent action decisions, approvals, receipt records, and bounded evidence

AgentVend SDK - verify HMAC, validate keys, report usage, progress, completion

AgentVend SDK - verify HMAC, validate keys, report usage, progress, completion

✅ Sell verified agents. Buyers trust verified packages. Unsigned agents get ignored. Add verification in seconds.

Deterministic testing for AI agents. Assert agent actions, not vibes.

A versatile framework that streamlines the process of creating custom multi-agent environments for large language models (LLMs).

A lightweight but powerful library for building (AI) multimodal agents with memory, tools, and knowledge.

A set of API clients to easily integrate to Featch AI services.

Validate LLM-generated tool args before execution. Wraps tool functions with arg validation, raises ToolArgError with LLM-friendly retry hint. Python port of @mukundakatta/agentvet.

Workspace runtime and execution boundary for AI agents

Framework-agnostic reasoning trace visualization tool for AI agents.

The official Python SDK for the AgentVisa API.

~/.ssh/agent for AI agents

Real-time 3D visualization for multi-agent AI systems

Edge-based voice assistant using Gemma LLM with STT and TTS capabilities

Runtime guardrails enforcement for AI agents — reads agent.guard.yml and enforces limits at runtime

A dotfile-driven firewall that protects the OS from destructive LLM agent tool calls

Agent Wallet SDK.

Non-custodial wallet SDK for autonomous AI agents. On-chain spend limits, x402 payments, multi-chain support.

Non-custodial wallet tools for CrewAI agents — EVM + Solana, spend limits, x402 micropayments, CCTP bridge

Financial governance infrastructure for AI agents — spend controls, rules engine, kill switch, and audit trail.

MCP Server for AgentWallet Protocol — AI agents get wallets, escrow, and payments as native tools

Secure every agent action — from install to runtime. Source-available security platform for AI agents.

Security and access control for AI Agents

A framework that can be used to easily build agents that has memory and knowledgebase

The Reliability, Safety, and Observability Layer for AI Agents

Connect your local Moltbot gateway to AgentWatch cloud

Production monitoring SDK for AI agents

Real-time health and security monitoring for AI coding agents

Zero-config OpenAI usage tracking for AgentWatch — prompts never leave your server

SDK for AgentWatch — observability for multi-agent AI systems

DevTools overlay for browser-based AI agents — see what your agent is doing in real time.

Observability SDK for AI Agent Execution — catches hallucinations, silent failures, and missing executions

CLI tool for initializing and managing AI agent projects based on LangGraph

Multi-agent AI collaboration framework (Claude, Kimi, Gemini, Codex, and more)

Observability and mesh layer for multi-agent AI systems — track what your agents decided, why they decided it, and how they're connected.

An intuitive agent development framework

A package for developing Open Agents

Python SDK for AgentWeb.live — the global business directory for AI agents

Python SDK for connecting agents to the AgentWeb platform

Python package for semantic relevant web search results.

Turn any MCP server into a curated, composable, A2A-ready agent.

Behavioral health layer for AI agents. Agents that work with humans, not around them.

AgentWerkstatt, a minimalistic agentic framework

Add your description here

A telephone benchmarking system. Measuring information degradation in multi-agent LLM communication chains.

Multi-session voice web interface for AI coding agents

Real-time message bus and inspector for multi-agent LLM systems

Transparent proxy witness for AI agent ↔ MCP server communications

Verifiable evidence for AI-assisted engineering

Official MCP server for Agentwork — delegate tasks to AI agents

Local-first harness for learning, evaluating, comparing, and optimizing repo-native agents.

AgentWorks SDK - Instrument and observe multi-agent AI systems

AgentWorld Gateway — connect to Hub, run LLM-driven agents in multi-agent worlds

Wrap agents, ship APIs - Turn agent CLIs into libraries and OpenAI-compatible servers

Python SDK for the AgentWrit broker -- ephemeral scoped credentials for AI agents via Ed25519 challenge-response

AgentWyre — AI ecosystem intelligence for your agent. Hype-checked signals from hundreds of sources. 8 languages.

Official Python SDK for the AgentX multi-agent platform

A production-grade Python framework for building LLM agents. Multi-provider chat, permission-gated tools, RAG (in-mem + Chroma/Qdrant/pgvector), semantic memory, Supervisor + Handoffs multi-agent orchestration with streaming, evals harness, prompt caching, Batch API, prompt-optimizer, MCP integration.

AgentX - Native compiled Python agent framework

Official Python SDK for the AgentX multi-agent platform

Official Python SDK for AgentX (https://www.agentx.so/)

The reliability layer for AI agents in production

Runtime firewall for AI agents - blocks catastrophic tool calls and self-heals the run.

A collection of tools for Large Language Model Agents

An agent that uses XAI to achieve goals by executing tools

Modular agent communication framework with multi-transport support

A framework for creating AI agents.

Deterministic MCP-first browser automation runtime for coding agents

统一的细胞类型分析工具包，集成四个专业Agent提供完整的细胞类型注释流程

Local AI-agent usage analytics and persona archetypes

Agent-first Python CLI library — Typer-compatible, built on argparse + pydantic

empty metapackage

Agent observability, tracing, and evaluation toolkit for agentic AI systems

Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks

An open-source python package with multiple python tools.

StepFn Aggregation Agent

A streamlined interface for LangChain based AI agent creation with multi-modal support

AI Action Firewall — seven-stage Decision Intelligence Core for safe agentic AI

基于 FastAPI 和 LangGraph 的智能代理管理平台

Aglet RAG memory technique — LanceDB-backed vector recall with pluggable embedders.

Aglet ModelProvider that routes to 100+ LLMs via the LiteLLM SDK.

Aglet ModelProvider that talks to any OpenAI-compatible chat-completions endpoint.

Aglet tool technique that wraps another agent.yaml as a callable Tool — the multi-agent primitive.

Parametrizable Agno-based agent runtime — FastAPI factory with pluggable agent sources, multi-tenant headers, and LISTEN/NOTIFY hot reload.

Cloud agnostic storage service

Compatibility shim for the renamed agora-agents package.