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 645 of 658
Turn an LLM into a gated, sandboxed, resumable construction loop over your codebase.
A LangGraph + Claude agent for the elastemp temperature-dependent elastic constants workflow
Python client for The Hive: Ed25519 keys, RFC 9421 request signing and the REST API.
A generic, plug-and-play Agentic Control Plane for MLOps Governance
SECURITY RESEARCH PLACEHOLDER — benign, does nothing. Coordinated vulnerability disclosure (dependency-confusion verification) via HackerOne. Not the real package.
The customer command-line client for Agentic Postgres (apg).
Shared foundation for agentic AI in insurance pricing.
Line-of-business-agnostic agentic components for insurance pricing.
Shared domain model, interfaces and configuration for agentic insurance pricing.
Shared MCP server infrastructure for exposing insurance pricing tools and agents.
Shared server infrastructure for exposing agentic insurance pricing services.
Line-of-business-agnostic building-block utilities for insurance pricing agents.
A stateful RAG workflow for retrieval, answer validation, and iterative refinement.
The Agentic OS Runner: an activity-only Temporal executor for workspaces, Agent Runtimes and verb seams
Activity I/O contracts and Public Metadata name builders shared by the Agentic OS platform and the installable Runner
Add your description here
Add your description here
An MCP which adds terminal capabilites to the agent
An MCP which adds terminal capabilities to an agent.
Local video tools for AI agents that read text and images but not video: contact sheets, transcripts, cut, loudness and sync checks, served over MCP.
Reserved name. Synthpop Inc placeholder that raises an error on import.
Skill-driven agents with source evidence, explicit permissions, and reviewable changes
An MCP which adds terminal capabilities to an agent.
MCP which adds terminal capabilities to an agent.
An MCP which adds terminal capabilities to an agent.
Verified agent experience for Python: a pure-Python core that passes the AgentExperience.NET language-neutral contract 1.5.
Agentics SDK for Python: shared memory for AI agents, receipts and the gateway.
AgentCore — enterprise AI agent framework, part of the AGENTIC STAR platform
Multi-Agent Observability & Auto-Recovery
Make your FastAPI services agent-ready with owner-approved MCP tools.
Auditable, intent-aware input intervention for LLM agents
Create local HTML maps of JavaScript, TypeScript, HTML, and Java codebases
AgentiSend is a transactional email API for AI agents. A send budget on every key, a preflight that sends nothing, refusals that name the fix, one call that stops every sender.
Open-source personal AI agent — model-agnostic, with tools, memory, scheduler and a local dashboard
Official Python SDK for AgentKey: email inboxes, zero-token OTP extraction, and verifiable agent identity
Zero-dependency reference client SDK for the AgentKit gateway (discover / quote / call / MCP tools.list)
Agentic ETL for Python: YAML pipelines where each step is a connector, a function or an LLM agent.
Send your AI agent's production traces to AgentLasso: continuous behavioral coverage for AI agents.
AI-powered observability SDK for AI agents
AgentLisp v2 - Racket-based Agent DSL compiler + Python ReAct Harness runtime + Cloud-native host glue
Lightweight AgentLoop offline experiment SDK
Git-reviewable repo memory for coding agents: typed decisions, dead ends, conventions and hazards, landed as a diff in the PR that motivated them, with a CI gate that fails when memory rots.
FOLTL constraint verification for LLM agent traces
AgentLTL rules for coding agents: the AGENTLTL.yaml language, a rule library, and a guard any harness can call.
Native SDK for joining an Agent Mesh from inside a Python agent process
Find a working API, MCP server or CLI for any need, with live health evidence. Official Agent Nexus client, zero dependencies.
DeepEval experiment publishing for the Grafana Agent Observability Python SDK
Harbor live evaluation and job import for the Grafana Agent Observability Python SDK
Grafana Agent Observability plugin for Hermes Agent. Records LLM calls and tool executions as generations and OTel traces+metrics.
Canonical AgentOS State Ledger client and content-addressed blob storage
Domain-agnostic multi-agent orchestration core (LangGraph) with pluggable local/cloud LLM providers.
Core payment infrastructure for AI agents (Official alias for open-agentpay)
Financial firewall & runaway circuit breaker for AI agents (Official alias for open-agentpay)
AgentPay Reverse Proxy & Seller Gateway for Autonomous Agent Micro-Payments
Convert large PDF documents into small, searchable files for AI coding agents
Measure how well a computer serves AI coding agents - and explain why
Load public agent-trajectory datasets and agent traces into one run record based on ATIF v1.7.
Shared, versioned domain primitives (Trace, Span, Envelope) for the AgentPlane products.
Replay your coding-agent sessions (Claude Code, Codex, Cursor, Copilot, OpenCode, Kiro) as a map and a timeline. Local only.
Bounded multi-runtime agent session pools for Python
Evaluation and regression testing for AI agents
Analyse AI coding agent sessions: call trees, timings, tokens, cost and waste.
AgentPulse for Python: detect AI agents, negotiate Markdown and declare Content Signals (FastAPI/Starlette).
Fault-injection and regression testing for AI agents
Local workbench shell where projects dock in as plugins (pages, cards, declared actions) operated by an AI assistant. Early development.
AI agent observability SDK — track runs, LLM calls, tool calls, and errors.
Local-first repository intelligence and task context for coding agents
Local agent activity indicators for RGB devices
A plug-in backup layer for coding agents: preserves state before every tool call modifies it
Context, memory, documentation RAG and observability umbrella for autonomous coding agents
Give Claude Code, Codex and Gemini every machine you have: free GPUs, running jobs, served models, installed software and data folders across your servers, over the SSH you already use, plus an MCP server.
Cross-vendor governance for an agentic-AI workforce
Unified multi-device cloud synchronizer for ~/.agents (memory, skills, docs, traces, identity).
CLI for creating and running YAML-configured AI agents
Show Antigravity CLI, Claude Code, Codex and Grok Build sessions and their subagents as a live tree: model, effort, context use, elapsed time, status.
Fast, minimal speech output MCP server and CLI for AI coding agents
See what every AI agent in your business is working on. The official Python SDK for Agents28.
Stdlib-first Agent Sam repository/data CLI and local SAM client, with an optional Rich terminal UI.
Bridge AGENTS.md to every AI coding tool's rules file - one source of truth for Claude Code, Copilot, Cursor, Windsurf, Cline, Aider, Roo Code, Kilo Code, Junie, and Amazon Q.
Security scanner for AI agents and MCP server configurations
AgentScope Service SDK: connect agent frameworks and report to the Control Plane
See, plan and edit your AI agents: live diagrams of smolagents and PydanticAI code that can also write the code — CLI, browser and VS Code.
Execution traces for agent behavior - OpenTelemetry-style observability for AI agent workflows
Zero-knowledge credential tools for AI agent frameworks
Minimal pluggable LLM agent server (FastAPI + Pydantic AI)
Python client for the AgentShield Tool Security Gateway
AgentShip voice — run the same agent over a live audio stream. A cascaded pipeline (transport/VAD → STT → agent → TTS) with barge-in, hosted in either Pipecat or LiveKit Agents. The agent is the one the REST service runs; only the hosting differs.
Pay-per-call tools for AI agents: 120+ web, data and crypto APIs paid in USDC via x402, with ready-made LangChain and CrewAI tools
A private, local dashboard for AI coding agent usage
AgentTelex: a message exchange for AI agents. Placeholder, work in progress.
Record AI-agent runs, replay them against a new version with every tool answered from the recording, and get a PASS/FAIL verdict.
Python SDK for AgentTrafficCop — a runtime circuit breaker and schema shield for multi-agent systems.
AgentTune: build agentic workflows, then train, evaluate, distill, and self-heal them through one trajectory schema. A TRL-backed alignment + fine-tuning library (full RL coverage — DPO, PPO, GRPO) with an agentic integration spine on top: agent-design / memory-design / harness-design pillars, a Project lifecycle, and a FastAPI service.
Check a coding agent's claims against the repository before you approve.
A light web interface for AI models and command-line agents.
SemiAnalysis AgentX inference benchmark harness, built on AIPerf
Official Python SDK for the AgentX multi-agent platform
MCP server that lets any MCP host (Claude Desktop, Claude Code, Cursor) join and use AgentX
Add your description here