Source
PyPI agents
25,155 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.
25,155 agents · ranked by popularity · refine in the directory →
Source platform: PyPI →
PyPI agents — page 211 of 252
Visual stepper UI for agentrr record-and-replay
A database-native Agent Harness for runtime data workflows, powered by Bub
Project-lifecycle CLI for AgentSeek (scaffold, run, build, deploy, skills, api)
Essential CLI tools for AI agent developers
AIMEAT Liaison Agent for CrewAI -- drop-in crew member that handles all communication with an AIMEAT node (Hello Integration handshake, capability reporting, memory writes, knowledge publishing, task lifecycle, offers + workflow-compatibility) so the rest of the crew can focus on domain work.
AMFS integration for AutoGen
Use AMFS as CrewAI Memory storage backend
AMFS integration for LangChain
AMFS integration for LangGraph
AuthSec integration for AutoGen — secure AI delegation token retrieval
AuthSec integration for CrewAI — secure AI delegation token retrieval
AuthSec integration for LlamaIndex — secure AI delegation token retrieval
RAG pipeline for Claude Code — indexes your codebase and exposes it as an MCP server
A lightweight AI agent firewall, audit, and compliance SDK.
CLI, Agent Skill, and MCP server for AI agents to manage Dida365 (TickTick) tasks and projects
Name reservation — see https://github.com/Gilamonster-Foundation/agent-mesh
OpenAI runtime adapter package for eXo-brain.
CLI tool for generating production-ready FastAPI RAG backend templates
胖貓專屬嘴臭LLM推理API
Privacy-preserving audit framework for multi-agent AI systems. Detects cross-agent data leaks, inference attacks, and compliance violations — without accessing raw content.
File-centric multi-graph manager
Reusable Agent Harness infrastructure library — 权限控制、Hook 系统、记忆系统、知识库 RAG、文件审计、多 Agent 编排
LangChain integration for Engram — cognitive memory infrastructure for AI agents
Official LangChain / LangGraph integration for Thrindex — persistent semantic memory for AI agents.
An integration of LiteLLM AI gateway into the Haystack framework, routing to 100+ LLM providers.
LlamaIndex vector store, reader, retriever, and KV/Doc/Index/Chat storage backends for CockroachDB
本地 LLM Runtime 与 GGUF 模型管理工具
Installer for LLM-native Obsidian Markdown knowledge vaults.
Build a high-quality llms.txt for any website. Model-agnostic, SSRF-safe, no hallucinated URLs.
占位包：Magic-agents Agent管理平台）
Recursive multi-agent swarm for long-horizon work
Lightning-paywalled FastAPI service — niche: OTel-Compatible Per-Task Cost Splitter for Multi-Agent Systems
Agentic RAG MCP Server — 13 retrieval/read tools plus workflow help for AI-driven multi-round retrieval over any text
LangGraph adapter for NCP: invoke NCP graphs as LangGraph nodes via ncp-mcp-server subprocess.
Cryptographic peer-to-peer agent coordination (Python bindings for agent-mesh)
Agent-coordination layer for optio task types: the optio.log keyword protocol, its session driver, and the LLM-facing keyword documentation (SSOT).
Run Anthropic Claude Code as an optio task; local subprocess or remote via SSH; ttyd-served TUI iframe.
Multi-agent orchestration with a local LLM Leader directing cloud/local Workers.
Rule Coherence Graph — detect conflicts in AI agent rule corpora.
Placeholder — under active development.
Smart RAG — the retrieval layer for local AI agents. Replaces Tavily + Firecrawl + Perplexity with a single open-source package.
Framework Python para deployar agentes de IA no WhatsApp em menos de 24h
AST+vector context router for AI coding agents — cut token costs 5-15x
Agent Brain MCP - Model Context Protocol server exposing Agent Brain as MCP tools, resources, and prompts
Enterprise golden-path framework for scaffolding MCP-first agent servers in Python.
AI Agent Cost Governance — policy engine, budget enforcement, per-tool cost tracking, multi-tenant workspaces
CLI tools, SRE observability, and sandbox isolation for the Agent Governance Toolkit
Core runtime, kernel, and trust layer for the Agent Governance Toolkit
Offline personal assistant MCP server — memory, tasks, contacts, and conventions stored locally in your Obsidian vault. Works with Claude Code, OpenCode, and any MCP-compatible agent.
Turn Langfuse/LangSmith agent traces into human-readable Agent Activity Reports (Markdown + HTML).
Python SDK for Agent Identity, Agent Profile, Agent Delegation, and Agent Discourse protocols
LLM Prompt Injection Detection API — 5-layer detection (Vigil + DistilBERT + mDeBERTa + Rules + Groq)
Agent Strike — Offensive LLM Security Testing. Coming soon by Sandeep.
Authorization, delegation, provenance, and verifiable-audit engine for AI agents
ToolStore v2 — MCP Client + Skills Manager + MCP Server. The universal tool platform for AI agents.
Know what your agents cost. Cost intelligence for AI coding agents.
Turn your LangGraph agent into a small fine-tuned model that runs with no orchestrator - near-frontier quality at a fraction of the inference cost.
Audit & Compliance SDK for AI Agents
Library-first authentication and authorization SDK for AI agents
An MCP which adds terminal capabilities to an agent.
An MCP which adds terminal capabilities to an agent.
Langfuse evidence and trace export adapter package for AgentLedger
WebSocket + REST relay for Agentrix. Routes IDE <-> mobile <-> core.
MCP server for SUMO traffic simulation: orchestrate networks, trips, simulations, and analysis from LLM agents.
Source-available MCP route for approval and local evidence on routed MCP tool calls
An open specification for versioning agent runtimes and keeping datasets valid.
Planetary Agents MCP server — converse with historical-figure personas, council-feed threads, and culinary debates from alchm.kitchen.
Gemini API proxy for routing requests to Google or OpenAI-compatible backends
A simple, unified interface for RAG across multiple vector store backends (txtai, Chroma, Qdrant, LightRAG)
BrainPalace - Typed-memory & retrieval engine for AI agents (BM25 + vector + GraphRAG); code & docs today, more domains coming
Chaos engineering for AI agents — Chaos Monkey, but for your agents and tools.
Audit chain for Claude Code workflows — consensus verification, persistent memory, and XRPL provenance for every agent action.
Evaluation utilities for deepagents (placeholder release).
企业级全栈代码助手智能体 - 多智能体协作架构
LangChain Tools for ANP2 — where AI agents talk, share knowledge, build trust, and (when useful) trade (publish, query, post tasks, earn credit)
LangChain integration for Daftari — wrap a Daftari MCP vault as LangChain tools.
Multi-model orchestration for LangChain chat models: primary/secondary failover (resilience) and tier-split gather/compose (cost/latency), tool-calling preserved across both.
LangChain integration for Nomad headless browser engine — 700× cheaper than Chrome
LangChain tools for 2s.io — pay-per-call AI agent APIs on Base via x402.
LangChain embeddings for Forge, Voxell's hosted text-embedding API (turbo, pro, ultra tiers). Voxell's Ingot-8B-R3 ranks #1 for English on the public MTEB leaderboard.
Time-travel debugging for LangGraph agents — record, replay, fork, and catch regressions from a single SQLite file.
A terminal coding tutor that scaffolds a project and tests, then makes you write the core logic.
Agent system for Lexigram Framework - AI agents with tools, strategies, and execution
LlamaIndex embeddings for Forge — Voxell's text-embedding API (turbo/pro/ultra; ultra = Qwen3-Embedding-8B, ~75+ avg MTEB, #4 English).
LlamaIndex tools for 2s.io — pay-per-call AI agent APIs on Base via x402.
CLI tool that evaluates LLM outputs from production logs against a dual-dimension rubric.
Zero-config LLM API inspector — intercepts calls, shows token breakdown and cost estimates in a local dashboard
Official Python SDK for the llmrix AI Agent Platform API
Local-first general-purpose RAG with an MCP server, CLI, and web console
LangChain tool for generating My Magic Pencil live visual lessons
Cross-session persistent memory for AI Agents. 4500x faster retrieval, zero LLM dependency.
Portable, stdlib-only guardrail for autonomous coding agents — safe continuations instead of reckless actions.
PayAgentic Python SDK — Agent payments for AI agents
Self-hosted document ingestion and hybrid (vector + keyword) retrieval server backed by Postgres/pgvector and Google embeddings.
PHANTASM: Invert LLM hallucination, confabulation, and uncertainty into productive features.
Sync Pi coding agent models.json with models served by a vLLM/llama.cpp server
Visual Retrieval-Augmented Generation — render, embed, index, search
Durable execution of Pydantic AI agents on Postgres via Absurd.
Production-ready Telegram and Slack channels for Pydantic AI agents.