Openai agents

Fast markdown RAG with multi-provider embeddings (Vertex AI, Gemini, OpenAI, Voyage), incremental indexing with mtime/size fast-path, stale vector pruning, Milvus vector store.

Build AI-powered software with task planning, workflow orchestration, and automated code generation using LangGraph4j and Java.

Session continuity for AI coding agents — your agent picks up where it left off. Persistent memory for Claude Code, OpenAI Codex CLI & Google Gemini CLI, sharing one local db: auto context injection, compaction handover, semantic search (KO/EN/JA), error→solution recall. 100% local, zero config, zero API cost.

Risk-adaptive Codex workflow with policy-level caps, native quality gates, and optional Superpowers handoff.

Simple OpenAI GPT API reference chatbot, that demonstraits basic turn based chatbot principles.

Image generation CLI that reuses your Codex (ChatGPT) login.

A unified CLI for multiple AI language models with AWS Bedrock integration, MCP support, and autonomous agent capabilities. Access 13+ AI providers (Claude, OpenAI, Gemini, Bedrock, and more) through one interface with secure file operations, approval workflows, and agent-driven automation.

A tiny and fast coding agent written in Rust.

Open-source desktop writing assistant for clearer writing, translation, and quick notes.

Self-hosted AI gateway. Route, translate and track requests across providers, with access keys, budgets, and a built-in dashboard.

Reusable SwiftUI chat framework for local and cloud LLM inference on Apple platforms

Ferrox - High-performance, stateless LLM API gateway written in Rust. Sits in front of LLM provider APIs (Anthropic, OpenAI, Google Gemini, AWS Bedrock) and exposes a single OpenAI-compatible HTTP API surface. Inspired by nginx/envoy proxy design — stateless, lock-free, horizontally scalable.

A native macOS reader that treats a PDF like a book — realistic page turns, 9 reading themes, and AI author personas grounded in your own library. SwiftUI + AppKit, BYOK.

A multi-platform chatbot framework for LLMs. Connect to various large language models via multiple instant messaging apps — QQ, WeChat, Telegram, Discord, and more. 😄 Extensible with plugins and modules. 👍 Built on Python 3.11+ with a Quart-based web panel. Beginner-friendly — learn plugin development quickly. 🎉

Skainet Bridge — local automation bridge for AI agents: one process, one port. MCP server + client, REST, browser extension, sandboxed exec. Independent project, unaffiliated.

Quira is a next-gen Python RAG framework featuring speculative vector search, Context Tetris for token compression, and differential caching to eliminate redundant API costs.

基于okx交易所的2阶段价格行为ai自主交易机器人bot，2pa agent web界面，支持BTC等加密货币、黄金、原油、美股量化机器人，支持deepseek、longcat等openai兼容模型，实现ai agent自动盯盘，自动分析，自动交易，自动下单，止盈止损设置

KinetAios

Turn vague agent prompts into precise, verifiable XML specs — then execute them. Headless multi-CLI generator skill (Claude, Grok, Codex, Gemini). Agent Skills + skills.sh compatible.

給非技術用戶與 AI agent 使用者的中文 meta instruction：重點不是讓 AI 盲目服從，而是要求先核實、少亂動、可驗收、出事可追溯。

Agent orchestration toolkit for Rust (under development)

Personal AI assistant — voice, vision, memory, multi-model routing, meeting overlay

Hermes image generation provider for OpenAI-compatible endpoints and Codex Auth

FinOps Pilot is an autonomous procurement and payment-recovery agent for engineering teams.

Safely resumes interrupted Codex CLI turns and selected retry/wait states from tmux.

A practical Generative AI engineering lab exploring LLM foundations, tokenization, deployment strategies, and real-world AI system design.

Split PDF textbooks into organized chapter files using AI-powered bookmark and TOC analysis. Supports OpenAI-compatible APIs.

CodePass: Cursor quota for China | Alipay | Claude GPT Gemini Composer | 国内 Cursor 额度 支付宝

Human-AI Co-design for Clinical Prediction Models

⚡ n8n Automation & AI Specialist | Building intelligent workflows to automate manual processes. Certified by Hashtag Treinamentos.

An AI-powered terminal coding assistant inspired by ClaudeCode CLI. Generate, edit, and refactor code directly from the command line using natural language.

CLI automation tool for creating ChatGPT accounts in bulk with parallel batch support, automatic OTP verification, and results export.

PickleShell ChatGPT Plugin - Interactive sessions with your local AI agent from ChatGPT

Your own private AI workstation — frontier-class local models, a 15-tool agent, and secure remote access, all self-hosted on your GPU. No cloud, no API keys.

Build an agent in minutes. Add production controls when you need them.

MCP server + Python CLI for AI agents to do tarot, I Ching, and Xiao Liu Ren divination. Audited local scripts generate the result; the model only interprets.

Made by GPT-5.6 Sol. Quality-preserving chief-engineer skill for Codex with phase lifecycles, model-pinned dispatch, and fail-closed verification.

Execution-first multi-agent engine — YAML Charterfiles, TPC fear metrics, Muscle-Memory, Boss hierarchy. GraphRAG alternative. pip install flowchart-charter-engine

A low-level, async-first Python framework for building AI agents — opinion-free primitives, composable middleware, and typed seams (mypy --strict) with zero core dependencies.

Learn LLM fine-tuning with an end-to-end guide for beginners and developers using Unsloth, LoRA, PEFT, and Google Colab

LLM-powered knowledge graph engine with ontological entity resolution, orbit-based proximity scoring, and hybrid semantic-graph retrieval.

Open GTM methods for AI-native founders — SaaS GTM, startup market entry, hardware GTM. Agent skills for Claude, Cursor, Codex. Free MIT.

A local-first personal AI agent that lives on your Android phone. Permanent memory, scheduled autonomous work, self-written mini-apps, and an optional home-screen launcher. Your data stays on the device — bring your own API key, or run a local model and keep the whole loop offline.

Isolated Claude Code dialects for Codex, Kimi, Cursor, Copilot, Gemini & more — embedded CLIProxyAPI, no manual proxy setup. macOS only.

Keep GPT and DeepSeek conversations continuous in Codex Desktop, allowing the two models to work alternately within the same project. 在 Codex 桌面应用中实现 GPT 与 Deepseek 任务上下文双向交接，让两个模型在同一个项目下交替工作。

短剧镜头反推工具：上传视频/图片，抽取关键帧，并调用自己的视觉大模型生成镜头关键词、运镜 脚本和视频生成提示词。

Cross-platform Codex setup that enforces Luna-only subagents with a PreToolUse hook.

Neovim integration for the OpenAI Codex CLI with terminal and app-server backends

API Scraper — Hunt down leaked API keys in GitHub commits, validate them against live endpoints, and check remaining balances. Multi-service support for OpenAI, Anthropic, DeepSeek, Google Gemini, Mistral, AWS, and more. Features a dark-themed PyQt5 GUI with concurrent scraping, auto-export, and import of previous results.

Free, open-source Codex usage tracker for the macOS menu bar: monitor 5-hour/weekly limits and reset times locally. 免费开源的 Codex 用量监控工具。

OpenDeck plugin that shows local Codex task status on a Stream Deck key

Self-hosted ChatGPT backup tool — export all your conversations, projects (with files), and custom GPTs as JSON, Markdown and HTML. Zero dependencies, runs locally with a web UI.

Check in detail your usage of Codex, with charts, price estimate and more !

Semantic pipes for your terminal - PDFs, images, audio, video, and text through Unix verbs that understand

Codex AI game studio: 85 skills, 163 curated tools, Unity/Godot/Unreal/Blender workflows, img2threejs, reversible automation, and visual QA.

Turn your Claude subscription into a multi-tenant agent API with rate limits, cost tracking, autonomous objectives, and an admin dashboard. Self-hostable, no API key.

Plug-and-play skills and prompts for every AI coding agent

Codex skill for mandatory Direct/Single/Parallel/Sequential preflight before subagent delegation.

Use third-party and Chinese model APIs as bounded Codex subagents while keeping Codex as the main agent.

SERPsmith helps AI agents research, create, and publish evidence-led, SEO-ready content.

Self-hosted AI gateway: OpenAI/Anthropic-compatible APIs, virtual keys with token budgets, exact+semantic response cache, reverse MCP governance (REST→MCP), Prometheus/Langfuse observability — fake-provider-first, zero credentials to try.

Local-first literature RAG workbench for PDF, Zotero, Chatbox, and OpenAI-compatible APIs

OpenAI Codex provider for DeepSeek Harness with device-code OAuth, Codex CLI import, token refresh, and a web settings panel.

Visual Tales Generator is an AI pipeline transforming text into visuals. It uses OpenAI API, Flux Dev diffusion models, and LoRA fine-tuning. An agent processes JSON, NLP ensures character consistency, and a model-agnostic architecture uses system prompts. It generates Pixar-style 3D storyboards via Replicate API, automating visual storytelling.

Local OpenAI-compatible proxy that exposes opencode's free Zen models (deepseek-v4-flash-free, hy3-free, nemotron, ...) to any agent - Cline, Roo, Continue, Aider, mimo. No accounts, no keys, one command.

Unofficial, experimental Codex skill for safely auditing and cleaning closed subagent histories without touching main conversations.

Astrbot go移植版本，使用DeepSeek进行辅助创作，快尝尝这些只能跑起来的代码😋

Laravel-native LLM observability, traces, cost tracking, latency, errors, and alerts for your AI calls

Terminal coding agent that executes tools (real think>tool>result loop with confirm + undo, MCP tools in-loop) and rewrites its own system prompt from feedback with metrics + auto-rollback. Free by default via the FCM model router.

Mook - a full-stack RAG proof of concept. FastAPI backend with document ingestion (PDF, Excel, URL) and vector search, a React/Vite front end, and pluggable LLM providers: Claude CLI, Azure OpenAI, OpenAI, or an offline mock for testing.

The ultimate AI infrastructure platform: One API, every leading model, zero integration friction.

Solana AI Agent is an innovative AI entity developed on the Solana blockchain. It merges cutting-edge artificial intelligence with social media features and decentralized trading. This dynamic digital being aims to connect the realms of Solana, AI, social media, and cryptocurrency

AEGIS OS™ - Secure AI Agent Platform - 12 security layers, 5 AI backends, RBAC, TLS, MCP/A2A. Built in Rust.

Tamper-proof memory + cryptographic audit trail for AI agents. HIPAA, SOC2, GDPR compliance built-in. Trust score for every response. Python & TypeScript SDKs. Rust-powered.

ACode is Roo Code fork with optimized automations, Roo Code gives you a whole dev team of AI agents in your code editor.

Automatic collection of free instances of AI text models (ChatGPT, Claude, llama and others)

Simluated Personal Language Teacher with LLM, TTS and STT

Create your own application with Vibeit.

A collection of AI prompts I've built for real business use cases. Covers content creation, data analysis, coding help, customer support, education, and professional writing. Each prompt includes examples and I'm constantly adding new ones based on what works.

Zero-config LLM cost & quality monitoring for Node.js - automatically log AI API calls and collect user feedback for analysis using Coolhand.

Streamlit AI交互平台

Enable developers to integrate AI chat/copilot capabilities into web apps while ensuring users keep control over which provider/model is used and how data flows.

OpenAI/Anthropic compatible LLM inference server for Apple Silicon

Self-hosted MCP server for hybrid semantic code search and repository intelligence.

Lightweight AI Agent framework with smart context management, streaming support, and tool calling. Build production-ready agents in 8 lines of code.轻量级AI Agent框架，支持智能上下文管理、流式响应和工具调用。8行代码构建生产级Agent。

AI-powered Jira CLI and MCP server for humans and agents manage issues, sprints, boards with interactive wizards, multi-provider AI (OpenAI/Gemini/Anthropic), and an 14-tool MCP server for AI assistants

E2E encrypted AI agent platform — Python, native MCP, multi-agent delegation, live browser canvas, saved templates for govt appointments. Works on Claude, MiniMax, OpenAI, Ollama, or Claude CLI.

🚀 Build your SaaS application faster with expert AI agents covering development, infrastructure, design, QA, and product management throughout the lifecycle.

presentation-skill: PowerPoint/PPTX skill for Codex and ChatGPT agents to build, edit, and QA presentations, slides, and slide decks.

CodingBuddy is a terminal-native coding agent written in Rust. It combines chat, planning, tool execution, patch workflows, indexing, and long-running autopilot loops in one cross-platform CLI.

TaskForce is a modular, open-source, production-ready TypeScript agent framework for orchestrating AI agents, LLM-powered autonomous agents, task pipelines, dynamic toolchains, RAG workflows and memory/retrieval systems.

Warden is a Multi-agent CLI assistant with a custom LLM adapter layer. Swap between Ollama, DeepSeek, OpenAI, Anthropic, Gemini, and any OpenAI-compatible endpoint via one .env line. Deep mode runs a planner, parallel executors, and a self-evaluating loop. Memory stores in PostgreSQL.

🧠 Autonomous AI Assistant & Agent — where every action is constrained, governed, executed, and cryptographically receipted.

Local, private AI for your laptop.

OpenClaw × Claude Code 精华整合 — 记忆系统、提示词架构、熔断机制

A recursive Deep Research Assistant powered by OpenAI and Resonate's Distributed Async Await.

🧠 A warm, empathetic therapy-style mental health chatbot built with LangGraph, GPT-4o, MongoDB, and Streamlit — supports emotional understanding, risk detection, coping guidance, and memory-based chat context.

Seelenmaschine是一个具有记忆和人格的LLM聊天机器人。它能够进行纯文本对话,并具有持久化的记忆系统,可以记住对话历史,并形成对用户的理解。Seelenmaschine is an LLM chatbot with memory and personality. It is capable of having plain text conversations and has a persistent memory system that remembers the history of conversations with the user and develops an understanding of the user.

One Docker. Zero Worries. A containerized server-side agent platform with white-label branding, multi-user RBAC, and per-session Docker sandbox.

Autonomous agent monitoring GenAI, AI agents, QA & testing landscape – delivering structured intelligence reports for QA Managers