Language
Python agents
65,757 Python AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
65,757 agents · ranked by popularity · refine in the directory →
Python agents — page 636 of 658
Persistent operating context and dynamic control for coding agents.
Bootstrap any repository with a lean, best-practice agentic development setup for Claude Code.
An MCP which adds terminal capabilities to an agent
AgenticVulHunter secure code review tool
Entity-oriented multi-agent runtime — your domain model, as a network of agents.
Just-In-Time Compiler for AI Agent Trajectories. Compiles multi-step LLM workflows into ultra-fast deterministic Python code with zero token cost.
TollWarden payment security for Coinbase AgentKit: a scan-before-you-pay action provider for x402 payments, with prompt-injection provenance and signed verdicts. Non-custodial.
⚛️ AgentKthx - A minimal, modular, python stdlib, agentic framework for tool calling AI agents
Python client for the Agent Loadout API: inboxes, messages, realtime events, screening, webhooks and credentials for AI agents.
AgentMeasure — check-up report for coding agent runs + conformance pack for telemetry fixture verification. Zero external dependencies.
Placeholder package reserving the agentos-execution-kernel name on PyPI. Real implementation tracked in docs/.
Placeholder package reserving the agentos-execution-kernel-client name on PyPI. Real implementation tracked in docs/.
The operating memory and learning runtime for AI agents — turn every execution into reusable intelligence.
A decentralized protocol for autonomous AI agent identity and negotiation
Replay recorded agent tasks against an OpenAI-compatible endpoint.
Optional Rust streaming client for agentperf-local.
MCP server that lets a model explore AKShare's 1000+ China market data functions on its own — search, inspect, call
Define project policy once, render it into every agent harness, route work across providers, and get auditable results.
Find every AI agent in your organization and know how risky each one is.
A multi-tiered defensive pipeline for stopping prompt injection, jailbreaks, and domain hijacking.
AgentQuay Python SDK — 让 AI Agent 通过 MCP 发现并调用你的桌面应用方法
An open-source red-teaming framework for security assessment of AI agents.
Backend-neutral governance telemetry for AI-agent runtimes
CalDAV calendar feeler for agents (CLI + MCP). Stdlib HTTP, no caldav/icalendar libs.
Record, archive, analyze and explore every coding-agent session (Claude Code, Codex, Copilot, Bob): a local knowledge vault built with Claude Code itself.
Ultralight CLI for local text-to-speech, powered by Kokoro by default
Generate a solid AGENTS.md / CLAUDE.md for any repo by detecting its stack, commands, and structure
CLI tool for managing AI agents, skills and harness
Read-only scanner for exposed AI/agent services: detects unauthenticated endpoints on standard ports and enumerates their API surface.
A seatbelt for AI agents: budget caps, rate limits, time limits, loop detection, endpoint filters and x402 payment limits for any Python agent.
Agentic Security Framework & Real-Time Threat Visualization Engine
Task-scoped authorization for AI agents: compile user intent into a least-authority policy and enforce it at every tool call. Hermes Agent plugin.
Deterministic Security, Guardrails, and Governance OS for Autonomous AI Agents in Python.
Name reservation for the AgentSpace Python SDK (import agentspace), a live office for AI agent teams. The real SDK ships as 0.1.0.
Auto-test and validate agent-generated APIs. CLI + MCP server for the agent era.
Local AI coding-agent status, alerts and focus for Stream Deck Mini, MK.2 and XL
A stress-test benchmark that provokes MAST failure modes in LLM agent frameworks, and shows how much of the failure comes from the framework's own prompt scaffolding.
Persistent task workflows inside your existing Claude Code or Codex session (placeholder, coming soon)
Zero-dependency Agent Traffic Lab client for one-call agent task execution with automatic Outcome
Pre-inference routing for tool-rich LLMs and multi-agent systems with MCP, A2A, LangGraph, AutoGen, policy-aware routing, recovery, and reproducible evaluation.
Deprecated. This package described two different, now-retired products (a general web-agent tool, then a chip-design board) and neither matches anything currently live. There is no successor to point to; it is retired outright.
Python client for the AI Agent Allowlist API: per-URL allow/deny verdicts and verified page-type URLs (login, signup, checkout, upload...) across 40M+ domains for web-browsing AI agents.
Spending limits for AI agents: meter every call, cap the spend, and stop it before the provider is contacted.
Deterministic AIMarket capability providers for the HESTIA hearth: signed decisions, canonical JSON, commit-reveal refereeing
Rate-limited, batching, failover-capable async client layer for LLM APIs
A small, provider-agnostic gateway for OpenAI/Anthropic-style language and vision models.
AIYou distribution of LiteLLM with HTTPX2 and OpenAI Python SDK 3+ support
A powerful framework for building realtime voice AI agents
Agent Framework plugin for services from OpenAI
Algen's provider-neutral runtime for governed AI agents
A reproducible algorithm optimization agent for C++ and Python
Independently versioned Worker collaboration for the AgentCore SDK
Python runtime SDK for Alibaba Cloud AgentCore high-code agents
An agent framework that keeps configuration (Agent) and history (State) apart, with a plain Python function as the loop
LangChain toolkit for Andreax's pay-per-call x402 AI tools (USDC on Base, EIP-3009 autopay).
LangChain tools for the AnswerLine answer and search monitoring API.
Anthropic infrastructure FinOps SDK — part of the Hyperscaler Radar suite.
One API over the coding agents installed on a machine: Claude Code, Codex, Cursor, and more.
Anzar — Local-first AI Software Engineer Agent
Records what a LangChain agent's tool calls changed on disk, for Apache SkyWalking AI Sessionizer
Apple's on-device (Foundation Models) and Private Cloud Compute LLMs from Python. No API key, no account, macOS 26+ on Apple Silicon.
Provider isolation for aqven: every model provider SDK import behind one factory.
Portuguese-first, CPU-only retrieval: tinyzchunk chunking, static embeddings, BM25, rank fusion and CXM25 reranking. numpy only, out-of-core, with metadata filtering and CRUD.
Aria agent SDK - mirrors the OpenAI Agents SDK (Agent / Runner.run / Runner.run_streamed / function_tool / Session) on top of the aria-agent-cloud beta Agents API.
An AI assistant on Athanore: a chat that manages agent workflows
Lightweight OpenAI-compatible terminal REPL
Adapters externos REST, gRPC e orientados a eventos para o Atlas
Configuração declarativa e composition root do Atlas
Contratos centrais independentes de provedor para o Atlas Agent Framework
Avaliação provider-neutral para o Atlas Agent Framework
Meta-package opcional do ecossistema Atlas Agent Framework
Integração opcional do Atlas Agent Framework com MCP
Providers oficiais opcionais para o Atlas Agent Framework
MCP-first Jira and Confluence tools for coding agents, where every write is a dry run first.
AUDiaGentic: Agentic workflow orchestration and execution platform
Renamed to tracyn-mcp -- pip install tracyn-mcp instead. See https://tracyn.online
Aumate QA — framework-agnostic auto-healing agent for any language, any test framework
Automated CSV Data Analysis & ML Diagnostics Agent for Jupyter Notebooks
Agent framework with verifiable self-made tools (the forge pipeline).
M2MCent x402 V2 plugin for Microsoft AutoGen (EIP-3009 Gasless Settlement on Base L2).
Multi-agent DevOps CLI: scaffolds Docker/CI/k8s, runs GitHub Actions, monitors and self-heals — with human approval gates.
⚡ AutoSRE: Autonomous Incident Response Agent powered by Corrective RAG (CRAG) & Multi-Index Hybrid Search
Sub-layer fragment placement for GPUs too small to hold one full transformer layer -- capacity-proportional splitting, column/row-parallel execution, verified against an unsplit reference.
Package name reserved — implementation coming soon
Package name reserved — implementation coming soon
This package will be released in the near future. Stay tuned!
This package will be released in the near future. Stay tuned!
This package will be released in the near future. Stay tuned!
Microsoft Agent Framework integration for Azure Functions.
Framework-neutral Agent integration for Azure Functions.
Epistemic Uncertainty Estimation & Guardrails for Agentic LLMs and RAG Systems
One-shot migration of inference from supported providers to Amazon Bedrock for Python repositories
The reliability layer for AI agents with write access: policy-first, code-gated, read-back-verified multi-app execution
Let Claude and other AI agents call your phone and hear your spoken reply.
Use Jev instead of an LLM for RAG decisions: relevance grading, query routing, hallucination checks and LLM-as-a-judge evals. Faster, cheaper, measured first.
Anthropic provider for BindAI
Groq provider for BindAI
Ollama provider for BindAI
Blast-fragmentation prediction from a bench pattern: the published ladder from Kuz-Ram to stacking ensembles, scored on real measured blasts under three split protocols, with the statistic named (variance explained, not squared correlation).