Openai agents

Agentic AI inference with x402 (HTTP 402) pay-per-request on Solana USDC — no API keys, no registration.

A small OpenAI Python SDK based personal AI agent with local skill support.

Local queue and auto-continue runner for Claude Code sessions and Codex App tasks.

Wrap your Anthropic / OpenAI Python client. Every tool call is inspected by Clavenar before it runs.

OpenAI Agents SDK sandbox provider backed by cocoon microVMs

An autonomous MCP agent that provides token-efficient code analysis, documentation retrieval, and implementation guidance for large library repositories using a dedicated OpenAI-compatible LLM.

An unofficial external role runner for the OpenAI Codex CLI

Benchmark full-context-in-prompt vs. RAG for a document, against Ollama, vLLM, LiteLLM, Open WebUI, or any OpenAI-compatible backend

AI-powered Python debugger — run a broken script, get root cause, explanation, and fix

LLM-powered multi-platform bot framework (Telegram + Discord; OpenAI + Anthropic)

Expose Django REST Framework serializers and viewsets as OpenAI / MCP tools with automatic JSON Schema generation

Python base for DLLM-compatible conversational applications.

Use Eden AI with Haystack to build AI applications with 500+ AI models through one unified, OpenAI-compatible API.

An OpenAI-first agent harness core for controlled, durable, and observable agent runtimes

Unofficial OpenAI-compatible HTTP bridge for Factory Droid

A Python-first Agentic AI Framework — provider-agnostic, async-first, middleware-driven

Run OpenAI Agents SDK agents on Flyte.

OpenAI-compatible models on Genkit

Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Vertex AI).

A command-line interface for OpenAI models

A proxy service converts ModelScope and SiliconFlow image APIs to OpenAI-compatible format

InfoLang memory Session for the OpenAI Agents SDK.

inis.run sandbox provider for the OpenAI Agents SDK (beta)

LLM agent policy for Inspect Robots: frontier LLMs (Claude, GPT, anything OpenAI-compatible) drive any registered embodiment through tool calls.

Give your OpenAI Agents SDK agent a June memory — wrap any Session to mirror conversations into a searchable, cited June knowledge canvas, add a memory-search tool, and backfill existing session databases.

Tiny, zero-dependency AI agent framework: tool-calling loop, function-to-schema tools, and memory over any OpenAI-compatible endpoint.

LiteLLM / OpenAI-compatible gateway doctor CLI (ping, tokens, context bench)

Sage - a terminal AI assistant for OpenAI-compatible API endpoints

Universal LLM API client for 165 providers — chat, streaming, tools, embeddings, search, OCR, plus an OpenAI-compatible proxy and an MCP server.

Lightweight Python framework for building LLM agents with tool calling and RAG

Model names, pricing, and free-tier metadata for OpenAI, Anthropic, and Google Gemini.

LLM plugin to serve an OpenAI Chat Completions API endpoint

A tiny, readable circuit breaker for LLM calls: hard budget caps that fail over to a free local model instead of raising or overspending.

Multi-format LLM API compliance testing tool — validates endpoints against OpenAI Chat, Open Responses, Anthropic, and Google GenAI specs.

Fit chat history into any model's context window: token estimation, sliding-window packing with a running summary, and overflow detection. Zero dependencies, no AI inside.

Composable pre-call and post-call hooks for LLM API calls: pricing, budgets, cost caps, rate limits, event log, observability.

The pre-merge check for LLM model, prompt, schema, and provider changes

A GitHub Action and CLI that detects risky changes to LLM prompts and AI configuration before they ship to production

Resilient cascading LLM inference across multiple providers with failover, circuit breaking, and retry cooldowns

Streaming privacy gateway for configurable PII transformation and OpenAI-compatible proxy traffic.

Local smoke tests for live LLM models, latency, and cost

Track LLM token usage, enforce policies & budget limits, and trigger alerts — across OpenAI, Groq, OpenRouter, AWS Bedrock, and custom providers.

Per-query token ledger for LLM pipelines: record what the API reports, answer with one GROUP BY. Zero dependencies, dashboard included.

Lightweight terminal tool to check remaining credits / quota across LLM providers. Zero dependencies.

LLM plugin for ZenMux.ai - OpenAI Chat Completions + Anthropic Messages API

A lightweight, personal Claude Code-style agentic CLI for LOCAL LLMs (LM Studio).

A lightweight Python decorator for caching, rate limiting, and retrying LLM API calls.

Intelligent routing, load balancing, and failover for LLM providers

Unified interface to call OpenAI and Anthropic-compatible LLM APIs from Python

A production-ready routing, fallback, and rate-limiting client for OpenAI-compatible LLM endpoints.

Use the OpenAI Python SDK with your own ChatGPT subscription

AIGP governance adapter for openai

MCP-Bastion security middleware for LiteLLM (100+ LLM providers via one OpenAI-compatible API).

MCP-Bastion security middleware for Ollama local models (OpenAI-compatible API).

MCP-Bastion security helpers for OpenAI Agents SDK tools and messages.

Expose any MCP server's tools as OpenAI function-calling tools, and execute OpenAI tool calls back against it.

OpenAI Agents SDK testing helpers for MCP Test Harness

Durable OpenAI Responses adapter for the MemoFlow Python SDK

Closed-loop, self-improving agent engine: Claude Code, Google Antigravity and OpenAI Codex compete for the Editor seat via blind-tournament judging, a deterministic referee (Haskell decision kernel + verified Python fallback) polices the flow, and git + an objective fitness signal arbitrate every change. Persistent sessions, context-rotation memory, AST code graph, temporal experiment knowledge graph.

ChatGPT-5.4 Nano 中转服务 SDK - 每天免费 1.0K tokens，国内开箱即用

Neutral LLM gateway: typed contracts, provider adapters and explicit retry, fallback, usage and cost accounting.

A unified Python interface and API server for running local Large Language Models.

Claude Managed Agents-shaped control plane backed by the OpenAI Agents SDK.

OpenAI Agents SDK tools and a mandatory pre-execution gate for RelayShield's MCP registry risk and prompt-injection breach checks.

Normalize OpenAI-compatible API failures, plan conservative retries, redact logs, and inspect SSE streams

OpenAI v1 API-compatible HTTP service backed by HuggingFace Transformers

A self-metering guardrail that counts and caps your OpenAI token usage against a daily (UTC) cap.

A pure-stdlib hybrid Code-as-Action scientific research agent.

A vendor-neutral FinOps and measurement toolkit for AI usage, cost, efficiency, and business outcomes.

Lightweight LLM-as-judge evaluation CLI — score model outputs on 5 dimensions and compare runs (OpenAI / OpenRouter / Ollama)

OpenTelemetry Official OpenAI instrumentation

OpenTelemetry Official OpenAI Agents instrumentation

OpenAI Agents SDK tools for the OptionsAhoy equity-compensation calculators.

Ory Agent Security for the OpenAI Agents SDK — per-tool authorization, activity logging, and identity propagation via a tool-input guardrail. Built on ory-argus.

git diff, but for LLM behavior — behavioral regression testing for language models.

Graph RAG library leveraging post-graph space sub-grouping and pgvector on PostgreSQL with OpenAI-compatible LLMs.

OpenAI Assistants API integration for the Preference Profile Exchange (PPX).

Client helper for ProxyLLM, the OpenAI-compatible LLM gateway: one-line OpenAI client wiring plus the autonomous email-OTP account signup flow.

Phone approvals for OpenAI Agents SDK agents. Your agent asks, your user taps Approve or Deny.

The official OpenAI Codex agent — same as OpenAI's, full coding toolset. GPU via providers.

A pip-installable Python library providing drop-in RAG evaluation capabilities using RAGAS

A simple, extensible toolkit for building advanced multi-agent Retrieval-Augmented Generation (RAG) pipelines in a few lines of code.

Self-hosted RAG engine: hybrid dense+sparse retrieval, 28-format ingestion (docs, URLs, images, audio, video), 6 vector backends, 8 embedding providers, 12+ generation providers with automatic fallback, query rewriting (HyDE/contextual/multi-query), structured JSON output, real per-call cost tracking, and standalone retrieval via retrieve(). Composable with the optional ragleap-graph package for knowledge-graph-augmented retrieval. BYOK, no vendor lock-in, no hardcoded model defaults.

Build semantic search, multi-provider question answering, and REST APIs over your documents in a few lines of Python.

RunAPI OpenAI TTS SDK for speech generation in JavaScript, Python, Ruby, Go, Java, and PHP

AI-powered multi-agent framework to plan, generate and heal Selenium Python tests (pytest + pytest-bdd)

Structured thinking as a pluggable layer for any OpenAI-compatible API

Spectron agent memory for the OpenAI Agents SDK

Sprites sandbox provider for the OpenAI Agents SDK

Swap between LLM providers (Groq, OpenAI, Anthropic) through one interface, with automatic fallback and optional schema validation.

TAPM v2 hook for OpenAI Agents SDK (in-process library instrumentation)

OpenAI integration for telemetry.dev Python SDK

Time-aware semantic LLM cache — automatically invalidates stale AI answers

Local DLP reverse proxy for LLM traffic

TTTPS Proof-of-Time ASGI middleware for vLLM: cryptographic audit-trail timestamps for OpenAI-compatible completions via the public KPP Provenance API

Sign OpenAI agent tool calls with Vouch Credentials.

Own your LLM's web search: a local search -> fetch -> rank pipeline that replaces hosted web_search tools at a fraction of the cost

A gateway that exposes local Wyoming services via OpenAI-compatible API endpoints

Claude Agent SDK–shaped Python API for the Grok Build harness — any model

Framework-agnostic conformance suite for AI agent implementations