Openai agents

A decentralized marketplace for agent capabilities - The Hands of AI Agents

LLM API 代理与日志追踪系统 - 透明观察智能体行为

Lightweight Python AI Agent Framework with Web UI

A simple LLM abstraction layer

Local-first, governed AI agent runtime for Python — embed it in your app, or run it as a CLI or ACP server. Permissions, MCP, memory and audit replay built in.

Record/replay testing for LLM agents - VCR.py but for LLM SDKs

AgentApps — A flexible multi-agent orchestration framework with visual Flow Builder

Local-first runtime controls for Python LLM apps and agents: budget circuit breakers, PII/secrets redaction, tool-call policy checks, rate limits, and audit traces — in 2 lines, no hosted proxy.

Compliance, governance & observability layer for AI agents

OpenTelemetry-based SDK for tracking AI agent usage and billing

Chaos proxy for testing LLM agent resilience — inject faults like latency, errors, and bad responses. Supports OpenAI, Anthropic, and MCP.

Bridge OpenAI tools to Claude Code SDK, Codex CLI, and OpenRouter

Cost guardrails for LLM agent runs.

Python SDK for the AgentCC LLM Gateway — OpenAI-compatible, type-safe, with guardrails and observability

A multi-agent AI coding system with built-in RAG — local or cloud, CLI or API.

Chaos testing for agentic AI — fault injection hooks for openai-agents-python

AI Agent Cost Governance — track, control, and optimize LLM spending

Generate Markdown-based agent tasks from NLP prompts with optional OpenAI enhancement.

Terminal-native agent runtime with persistent sessions, branching, and MCP

Production-ready orchestration for OpenAI Agents with Redis-backed coordination, activity tracking, and workflow management

Fit your messages into the LLM context window. Token-aware truncation with multiple strategies, pluggable tokenizers. Python port of @mukundakatta/agentfit.

Minimalist Python framework for building AI agents

Framework Python open-core pour orchestrer des agents IA via un système Kanban event-driven

Official Python SDK for the AgentFM peer-to-peer compute mesh.

OpenAI LLM + embeddings provider for AgentForge — gpt-4o / o-series + text-embedding-3-*

Detect runaway AI costs in agentic systems before they hit production

Monitor and protect yourself with AI agent budget controls, approval workflows, and anomaly detection.

All terminology and labels used in AgentGuard materials are descriptive of software functionality only, not legal definitions or guarantees of compliance. Terms like receipt, audit log, evidence, audit trail, and attestation refer solely to cryptographically-signed records produced by the software. Full functional-use disclaimer in README.

AgentGuard Spend plugin for Hermes Agent (Nous Research). One-step install of local spend caps + signed audit logs for every Anthropic/OpenAI call your Hermes agent makes. No proxy, prompts never leave your machine.

Python SDK for AgentGuard - AI Agent governance and monitoring platform

MCP server to search and discover connectors from AgentHotspot.com marketplace

AgentHub openai package

Ergonomic LLM Agents

Agentia Web App and API Server

Production-grade LLM gateway with cost tracking, budget alerts, conversation memory, streaming, guardrails (PII/injection defense), Redis caching, and multi-provider routing

Agentic API gateway for OpenAI-compatible inference servers

A Python SDK for MCP tool integration with LLM providers

Simple building blocks for agentic AI systems with MCP client and conversation management

Type definitions for the Agentic Commerce Protocol specification

Automatic context window management for AI agent SDKs

Agentic Context Engineering utilities for OpenAI Agents.

Django integration for building agentic apps with the OpenAI Agents SDK

Universal agent protocol gateway — translate between A2A, MCP, OpenAI Assistants, and REST in one config file.

Drop-in SDK to add an AI memory layer to any application. Works with OpenAI, Anthropic, Gemini, Claude.

A Python SDK for MCP tool integration with LLM providers

A multi-agent LLM orchestrator for academic peer-review.

AI-powered browser testing framework using natural language and OpenAI

Zero-dependency Python SDK for building AI agents: multi-agent orchestration, tool calling, MCP, RAG, memory, guardrails, evaluation and tracing.

Lightweight cost tracking for LLM pipelines and AI agents

Persistent memory + multi-agent channel for any AI stack. The memory that never forgets.

Production-grade multi-agent framework with minimal dependencies

A package for building intelligent agents through OpenAI's API.

Framework-agnostic AI agent library for building single and multi-agent systems

Python Toolkit for Declarative AI Agent Development

AI-powered IRC agent with multi-provider LLM support

Production-grade, provider-agnostic Python framework for building agentic AI systems

LLM-neutral Python agent framework with built-in multi-channel messaging and document automation.

Cognitive continuity infrastructure for long-lived AI agents — cross-model state reconstruction, semantic recall, cognitive compression

Python client for AgentVault — AI-native credential vault for autonomous agents.

Lightweight agents on top of Pydantic AI with true soft tools and conversation history

Python SDK for AgentLens — observability for AI agents

The interactive debugger for LLM agents. Pause, inspect, and fork any agent mid-run.

Estimate costs and lint agent workflow YAML files

Trace AI agent execution — LLM calls, tool calls, costs and latency

AgentLoop SDK — middleware that turns human corrections into searchable memory for your agent.

Drop-in OpenAI SDK wrapper for AgentLoop — adds memory retrieval and turn logging to chat.completions.create calls. Supports streaming.

AgentMake AI: an agent developement kit (ADK) for developing agentic AI applications that support 16 AI backends and work with 7 agentic components, such as tools and agents. (Developer: Eliran Wong)

AgentMake AI MCP Servers - Easy setup of MCP servers running AgentMake AI agentic components.

WebUI for AgentMake AI; AgentMake AI: a software developement kit for developing agentic AI applications that support 16 AI backends and work with 7 agentic components, such as tools and agents. (Developer: Eliran Wong)

Persistent memory for OpenAI agents — store, recall, and forget.

A decentralized marketplace for agent capabilities - The Hands of AI Agents

Trust & governance layer for OpenAI Agents SDK — policy enforcement, trust-gated handoffs, and hash-chained audit trails

AI-powered development platform: Multi-agent system for requirements discovery, conversational document building, and test automation

Fastest way to build, prototype and deploy AI Agents.

Production-Ready AI Agent Runtime - Automate everything with LLM-powered agents

Deterministic record, replay, and git-bisect for AI agent runs. Reproduce a broken run byte-for-byte offline, then binary search to the commit that broke it.

Multi-language code execution against a real directory for AI agents

A shared to-do list for AI agents. Dependency-aware task queue, zero dependencies, pure Python.

Lightweight observability for AI agents — track costs, tokens, and traces

Zero-config agent observability SDK — auto-captures LLM calls, costs, and traces

Lightweight AI incident detection. Catch cost spikes, latency anomalies, and prompt bloat before they hit your users.

OpenAI- and Anthropic-compatible API server that routes through agent CLIs

Lightweight, hackable multi-agent orchestration lab (CLI + Python) with transcripts, checkpoints, budgets, and pluggable providers/tools.

Arcade Integration for OpenAI Agents

Extends the functionality of the OpenAI Agents Python SDK.

A Python SDK for MCP tool integration with LLM providers

Model adapters for OpenAI Agents SDK

CLI scaffolding tool for OpenAI Agents SDK projects following Mutta conventions

A Python adapter for using Google Gemini with OpenAI Agents SDK

Visual Agent Workflow Engine — run AI agent pipelines from YAML configuration

Intelligent Multi-Model Router for LLM Selection

The babysitter for your AI agents. Watches costs 24/7 and alerts you if something goes wrong.

Forked version of OpenAI's Swarm library

Wire-level prompt introspection for LLM SDK calls. See exactly what was sent, with credentials redacted by default. Anthropic, OpenAI, any httpx-based client.

A harness-engineered AI agent runtime with tool isolation, self-correction, and permission scoping

Zero-config OpenAI usage tracking for AgentWatch — prompts never leave your server

Wrap agents, ship APIs - Turn agent CLIs into libraries and OpenAI-compatible servers

Aglet ModelProvider that talks to any OpenAI-compatible chat-completions endpoint.

Production-grade AI agent framework — the Next.js for AI agents

Multi-agent AI system for video transcription using OpenAI Whisper, ChromaDB, and AutoGen