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 218 of 252

openai-agents-valta

OpenAI Agents SDK tool for hard spending limits on AI agents via Valta

pyagent-blueprint

Declarative YAML specs for multi-agent LLM systems — validate, compile, test, diff, render

pyagent-context

Three-tier memory with trust-aware context ledger for multi-agent LLM systems

pyagent-providers

Multi-provider abstraction with capability negotiation, health checks, and fallback chains

pyagent-studio

Kubernetes Dashboard for Agent Systems — CLI + web control plane for multi-agent LLM blueprints

ragkit-adhitya

Production RAG pipelines without the abstraction tax

ros-agent

Quickly run and manage ROS 1/2 robots. Built-in MCP for Claude, Cursor, or any AI client, plus vision, sim, and hot-reload behaviors. Merkle proofs make every run tamper-evident and replayable.

tau-agent

Tau

terminal_agents

Add your description here

tlc-agent

The native TLC agent in your terminal — bring your own brain; TLC is the body.

agent-action-capsule

Reference emit + verify library for the Agent Action Capsule SCITT profile (draft-mih-scitt-agent-action-capsule). Includes the rungs 1+2+6 CORE: emit, record, anchor client, self-attest.

agent-action-capsule-verifier

Verifier for Agent Action Capsules — a SCITT application profile for verifiable agent actions (name claim; implementation to follow).

agent-boilerplate

High-ticket business builder — AI agent pipeline CLI

agent-chat-reader

Read and search Codex CLI and Claude Code chat history from the terminal.

agent-incident-reporter-mcp

Signed, hash-chained, tamper-evident AI incident records (MCP server). EU AI Act Art 73 ready. By MEOK AI Labs / CSOAI.

agent-runtime-kit

One typed runtime API for Claude, Codex, and Antigravity agent SDKs.

agent-skill-eval

Framework for evaluating agent skills across OpenCode, Claude Code, and Codex

agent-trace-eval

Golden trace regression evaluation for tool-using AI agents

agentburn

Where does your AI agent burn money? Local token/cost profiler for always-on agents (Hermes Agent first). Zero dependencies.

agentcairn

Local-first agent memory: an Obsidian markdown vault as source of truth, with a rebuildable DuckDB index.

agentguard-governance

Governance layer for autonomous AI agents — pre-flight checks, runtime monitoring, and post-session reporting.

agentic-ai-kit

Build emotion-aware AI agents, adaptive episodic memory, SQL AI, RAG, tools, and Gemini-powered agent systems.

agentic_terminal_ginachen

An MCP which adds terminal capabilities to an agent.

agentmoat

Security observability layer for LangGraph and Anthropic SDK AI agents

agentpay-python

AgentPay Python SDK — Lightning Network payments for AI agents

agentprobe-injection

Harness for measuring LLM agent resistance to indirect prompt injection and comparing defense effectiveness.

agentwatch-python

Zero-latency AgentWatch wrapper for the official OpenAI Python client.

anthropic-omega

Anthropic Claude SDK with OmegaEngine governance - AI safety and compliance

anytype-llm-wiki

An Anytype-native LLM wiki combining Karpathy's pattern with Anytype's typed knowledge graph (Objects, Types, Relations).

arcen-agent

The self-improving AI agent — creates skills from experience, improves them during use, and runs anywhere

auto-browser-langchain

LangChain / LangGraph / CrewAI integration for auto-browser

autogen-omega

OmegaEngine governance integration for autogen-omega

avs-blueprint-agents

Microservice blueprint for creating agents

buywhere-llamaindex

LlamaIndex FunctionTool wrappers for the BuyWhere product catalog API

cambium-agent

Local-first, ultra-lean agentic workflow orchestration engine.

claude-i

Like `claude -p`, but driven through an interactive Claude Code session.

claude-session-manager-gtk

Native GTK4 GUI to manage and resume Claude Code sessions

cohere-omega

OmegaEngine governance integration for cohere-omega

courier-agent-email

Temporary email inboxes for AI agents. Receive OTP codes, magic links, and verification emails. No signup. Zero dependencies.

create-rustchain-agent

60-second onboarding for a RustChain-participating agent: wallet + agent.py + MCP wiring + First-Light bounty.

crewai-omega

OmegaEngine governance integration for crewai-omega

crewai-rine

Native CrewAI tools for the Rine network — send, receive, discover, and run E2E-encrypted agent-to-agent conversations and groups from a CrewAI crew

deepagent-vscode

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

dial-langchain

Official Dial LangChain tools — phone numbers, SMS, WhatsApp, and voice calls for AI agents

figuard-langchain

FiGuard pre-flight spend authorization for LangChain agents

fj-llm

Lightweight, config-driven client for multiple LLM providers

guarded-rag

Guarded RAG: grounded answers, refuse-when-unsupported, PII redaction, and an eval harness with metrics. Stdlib core, bring-your-own model.

hivemind-a2a-agent-plugin

A2A agent protocol plugin for HiveMind-core

idprova-agents

Verifiable, scope-gated tool execution for AI agent frameworks (IDProva)

ifed-agent
image-rag
jina-v4-vllm-plugin

vLLM out-of-tree model: Jina Embeddings v4 multi-vector (token_embed) on Qwen2.5-VL

langchain-e2b

E2B sandbox integration for Deep Agents

langchain-mnestic

LangChain VectorStore for mnestic — embedded graph + vector + full-text store with one-call hybrid retrieval.

langgraph-tenancy

Tenant isolation and per-tenant usage metering for LangGraph checkpointers and stores

lime-agents-sdk

Official Python agent SDK for LIME: AI agent identity, cryptographic passport JWTs, one-call site login, and MCP OAuth for external MCP servers. Async-first, automatic PoW, typed MCP client.

llama-index-readers-azure-tax-forms

LlamaIndex reader for IRS tax form extraction via Azure Document Intelligence — supports Form 1040, W-2, Schedule C/E/K-1, 1065, 1120, 1120-S

llama-index-tools-tempguru

LlamaIndex tools for TempGuru event staffing: city coverage, W-2 rate ranges, booking lead times, and state labor compliance for 345+ US/CA cities, plus opt-in quote submission. No API key required.

llama-index-vector-stores-mnestic

LlamaIndex vector store for mnestic — embedded graph + vector + full-text store with one-call hybrid retrieval.

llmbridge-sdk

A lightweight Python SDK for using local and OpenAI-compatible LLMs.

llmcapa

Lookup capabilities (context window, modalities, features) of various LLM models offline.

llmrix-hestia

LLMRIX AI Agent SDK

mailagent-agent

Python SDK for MailAgent agent verify API

matrx-rag

Multi-tenant RAG: hybrid retrieval, chunking, embeddings, ingestion, PDF + image + repo pipelines, agent-extraction indexing, priority-aware ranking.

mcp-agent-gate

An MCP server that lets an AI agent gate its own work: deterministic checks, refute-first review, and tamper-evident honest receipts. Fleet Mode, as a tool.

mcp-cb-arbitrage

可转债套利决策引擎 MCP Server — 机会扫描 + 深度分析 + 强赎应对

odoo-addon-storage-file-swap-backend-queue

Delegate storage file backend swap to queue jobs

runspace-agent

Sandboxed execution environment for AI agents operating on filesystem directories

spawnllm

Delete your subprocess wrappers around claude, codex, and gemini.

spool-agent

Spool SDK for Python — trace LLM agent runs into the local Spool store

start-agent

A Python Agent framework for multi-model access, tool calling, RAG, context engineering, evaluation, and Agentic RL.

tag-agent

Orchestrate AI agents from your terminal — multi-source credential import, swarm topology, background queue, live dashboard

trovis-agents

Connect your agents to Trovis — two lines of code for full observability

villm-tok-fast

ViLLM Fast Tokenizer — Rust backend with embedded SentencePiece for Vietnamese-English code-switching

vllm-cpu-nightly

A high-throughput and memory-efficient inference and serving engine for LLMs

SimAgentPlg

A lightweight stateful agent framework with ReAct reasoning, tool dispatch, and MCP integration

agent-passport-standard

Agent Passport Standard (APS) — Python SDK

agent-run-ledger

Local-first verdict layer for AI coding-agent runs: graded repair receipts and a loop-gating exit code. No outbound network code; optional dashboard binds 127.0.0.1 only.

agent-session-manager-gtk

Native GTK4 GUI to manage and resume AI coding agent sessions (Claude Code, Cursor)

agentcrawl-ai

Self-hosted web scraping and Markdown extraction for AI agents.

agente-testes

CLI de testes E2E com IA: linguagem natural vira Playwright executável.

agentok

Agentok — placeholder package.

agentos-sdk-python

Async Python SDK for AgentOS APIs.

agentpay-vn

VietQR payment infrastructure for AI agents — AgentPay VN MCP server & Python SDK

agentrec

Replay recorded LLM API traffic against a candidate model: cross-provider migration & regression reports (OpenAI/Anthropic/Gemini/Mistral) with scoring, cost and latency, built on httpx record/replay

agentsweep

Find and redact secrets in AI coding agent histories (Claude Code, and more).

aigp-agent-core

AIGP Agent Governance Core — shared lifecycle for all framework adapters

aigp-langchain

AIGP governance adapter for LangChain/LangGraph

ainative-openai

Drop-in replacement for the OpenAI Python SDK — routes to AINative's free Llama, Qwen, DeepSeek & Kimi API.

argusllm-sentinel

Lightweight LLM API security layer — deterministic, no AI, no DB.

armature-agents

Agent execution harness — wraps LLMs in structured, inspectable workflow specs

autonomous-qa-agent

Autonomous QA Agent — scan, test, and fix any codebase automatically

aws-bedrock-invoke

Small Python library for invoking Claude 4.x models on AWS Bedrock with manual retries, prompt caching helpers, and JSON parsing.

bridge-mcp-agent

Bridge MCP Agent

cjm-graph-storage-adapter-interface

Typed graph-storage task adapter interface: the repository-style contract (CRUD, typed query execution, introspection) between graph-storage tool capabilities and the substrate.

claude-handoff-manager

MCP server that automates Claude Code conversation handoffs — no more manual copy-paste when you hit the message cap.

claudebot

Always-on Telegram bot that drives the real Claude Code binary on your subscription — no API key, no Agent SDK.

crewai-ainative

Configure crewai to use AINative's free LLMs + ZeroMemory — no OpenAI key needed.

deny-sh-langchain

Wrap a deny.sh vault entry as a LangChain v1 tool. The credential resolves inside the tool boundary; only a narrowed DTO reaches the model. Fail-closed leak sweep.

deny-sh-openai-agents

Wrap a deny.sh vault entry as an OpenAI Agents SDK tool. The credential resolves inside the tool boundary; only a narrowed DTO reaches the model. Fail-closed leak sweep.

Browse other source pages