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 655 of 658
Sarvam Agents API
Multi-account switcher for Claude Code
Haystack components for SayMaker: generate images and video (Veo 3.1, Kling 3.0, Seedance 2.0, Nano Banana 2) in a pipeline
MCP server (Python) for SCDO per-agent x402 wallets: Base USDC payments, signed heartbeats and booked income.
SCDO x402 per-agent wallet tools for Python, LangChain and Virtuals GAME SDK: Base USDC payments, signed heartbeats and booked income.
Rivet VPN agent from SCIA IoT.
ARA-native AI-reviewed open publishing on top of Clew. Part of SciTeX.
Agent Behavioral Testing Platform — tests what agents DO, not just what they SAY
Name reserved by zer07 Labs for Seam. Not installable from PyPI; see the project URL.
Name reserved by zer07 Labs for Seam. Not installable from PyPI; see the project URL.
Name reserved by zer07 Labs for Seam. Not installable from PyPI; see the project URL.
Name reserved by zer07 Labs for Seam. Not installable from PyPI; see the project URL.
A small example package
Your gofer. A second you, in a second.
A coding and document agent on Claude (Azure / Microsoft Foundry): tools, safety rules, memory and context management, usable from the terminal or as a library
AI agents for seismology (placeholder; under development).
Turn creator videos into vault notes and human-approved setup actions
Gasless x402 micropayment plugin and Oracle suite for Microsoft Semantic Kernel
Haystack component that asks send21 to prepare a non-custodial payment request (pay link). Not an official deepset integration.
Sengptr (Sengpt Revive), a maintained terminal client for ChatGPT
Seqoria Agentic Assistant Framework - MCP-native tool orchestration for AI applications
ServChart agent: reports a host's Docker containers, networks and Compose stacks to a ServChart hub.
Expose a local LLM runtime as a reliable HTTP/WebSocket service.
Self-contained conversational ops agent console for FastAPI apps
An agent-controllable browser over the Servo engine's built-in WebDriver.
Apples-to-apples LLM cost & performance benchmark — cost per successful task, reproducible.
Gesture-friendly terminal agent. Gives a phone a real interactive shell on your machine over Tailscale.
Learns the fixed-choice decisions your LLM makes and answers the ones it is certified on in microseconds, from a small table on your CPU. Zero-code proxy for the OpenAI Decisions API, System One and chat models.
An AI assistant for your zsh command line
Session-scoped agent tools for Python Shiny apps on ShinyHub
Core LangGraph agent, RAG, and tools for ShopAgent-OS - import into your own Python backend.
A small example package
A small example package
A small example package
Cringe meta-ironic old meme generator
Self-hostable disposable sandboxes for AI agents, with snapshot, rollback, and fork.
Local RAG search and MCP server for AI agents like Claude Code: hybrid BM25 + semantic search with reranking over Markdown and Obsidian notes, PDF, Office files and emails. Backlinks, metadata filters, browser UI. Runs on your own GPU or CPU: no cloud, no API keys.
Unified client for multiple LLM providers
An easy to use package that encrypts and serializes data including cross-file capabilities.
State-of-the-art framework for building AI agents with OpenAI Agents SDK
Local SkillMesh launcher; requires Node.js 22 or later
Native LLM Agent Terminal Copilot with Shell State Sync
Conservative repository scaffolding for coding agents
AER-1 verifiable execution receipts for smolagents agents: one checkable receipt per tool call.
Run the code of smolagents' CodeAgent in a local Hyperlight micro-VM
Run smolagents Python code in Lizard Sandboxes.
A reusable AI Agent base framework built on LangChain + DashScope + ChromaDB
SolidX AgentHub agent loop and runtime
Spark [Ember] — local-first coding agent with a Codex-style loop
The chat harness runtime SCIMAP Pro, Plexora and other BioCognia products share
Spec-driven pipelines and hierarchical agents (PydanticAI, DSPy, CrewAI, LangChain) over a LiteLLM proxy
Coworker domain pack for agent-fabric: repo_index, context_select, context_pack, code_review, patch_propose
Lakehouse domain pack for agent-fabric: source_inspect, medallion_plan, airflow_dag_render, dag_check
Statistics domain pack for agent-fabric: summary, linear_model, anova, time_series, pca, clustering
Text domain pack for agent-fabric (text_stats, keywords, document_digest); proves the core is domain-agnostic
Give a Haystack pipeline or agent lead lists, company lists and grants from the live web. Every row comes with its source, priced per match in code.
Client for spelunking.ai — a safe haven for AI agents in the wild. Standard library only.
Sphinx current-page Ask AI extension with a local ChatGPT plan server
Cryptographic clone-detection engine for NXP NTAG 424 DNA (SUN/SDM)
Autonomous dual-team (Purple Team) security framework powered by configurable LLM APIs.
Stagehand driver for Anthropic's browser toolset: give Claude a browser through the Anthropic SDK.
Stagehand driver for OpenAI's browser toolset: give GPT a browser through the OpenAI SDK.
Build your own AI agent, powerful but controlled: your tools and your rules, checked on your own machine.
Reserva de nome. O pacote real e privado, da Starbem — este nao tem funcionalidade.
AutoGen tools for Steward's pay-per-call x402 data APIs (USDC on Base, no API keys)
Deterministic cryptocurrency strategy backtesting
Hard budget caps for subagents — token/$ limits enforced by hooks, not just displayed
Team/CI budget control for subagent token spend: shared budget pools, per-agent quotas, overspend checks, and a kill switch.
Renamed escouade-mail. This package re-exports escouade-mail; install escouade-mail instead.
Estimate how much of your Claude Code bill is subagent preamble resends
Embed the super coding agent in a Python program
An open-source, agentic survey engine — define surveys as data; AI authors, administers, and analyzes them. Runs anywhere.
Placeholder: reserves the name for an upcoming open-source agent-swarm library. Not usable yet.
Swarm Python SDK for agent and operator integrations.
Hierarchical multi-agent orchestration: a tree of LLM agents, each node backed by a different provider
Infrastructure for building complex software, end to end.
Evidence-based operations for AI agent fleets: sealed audit trails, SLA-alarmed triage and AI-Act-ready privacy.
A GPU-vectorized multi-agent benchmark for self-assembling modular robots.
Federated multi-agent research framework for authorized specialist consultation
Coordinate coding-agent CLIs (Claude Code, Codex, Antigravity, DeepSeek via Reasonix) across machines over Telegram and a git-backed message bus
Deep Agents teams of domain specialists, exposed over MCP and a terminal CLI.
Git archaeology team for swarmr: which commit broke the test, and proof.
Kubernetes incident investigation team for swarmr.
Agent team that authors Kubernetes mock exams for kubiq and proves every question on a live cluster before opening a PR
Python SDK for SwarmV: edge vector memory with built-in access control for AI agents.
MCP server for SwarmV: persistent vector memory for AI agents, limited to what the user may access.
Universal Multi-Agent Observability, Entropy Circuit-Breaker, and Time-Machine Debugging Platform
Pre-transaction trust firewall for AI agents: should-i-pay decisions, sybil forensics, liveness SLA (SweetAI x402 / ERC-8004)
Terminal and web AI agent that answers requests by driving an LLM in a tool-call loop inside a sandboxed container pod.
The SDK for agents on the Synadia Agent Fabric — tracing and the agent tools' ScratchPad extension, on the hooks of the Synadia Agent Protocol SDK
Bridge MCP local do sync-agents: liga a IA de quem conecta ao canal de alinhamento, escopado pelo repositório git
SZL Evidence Plane plugin for LiteLLM: hash-chained, DSSE-signed receipts for every LLM request via LiteLLM's callback system.
Distill an LLM agent's closed-set decisions into cheap tabular classifiers: TabSchema, TabSynth, TabHead.
Initialize a repository with the TacT developer and agent collaboration kit.
Agentic segments for talkpipe, built on Strands Agents: deterministic pipelines with bounded tool-using steps
Deterministic, team-aware AI workbench configuration auditor
Records what an AI agent spent, from inside the agent's own process, for Agent Pulse.
Placeholder. The Tellmark SDK is available to Tellmark customers from tellmark.si.
The Tellproof evidence agent: a signed, content-free record of how your AI system runs, with a local dashboard.