Openai agents

🏢 OPC (One-Person Company) — Multi-Agent 编排技能，让 AI 成为一人公司的 CEO。基于 OpenClaw 的 sessions_spawn 机制实现多 Agent 协作。

Sovereign AI orchestration engine with a learning Conductor. Routes between 400+ models across 15+ providers. Streams responses, detects refusals, learns from your patterns.

Open-source AI desktop assistant. Chat with multiple LLM providers (OpenAI, Claude, OpenRouter) in a native app with agentic tool use, MCP server support, and built-in file/shell tools.

lm15 Python reference implementation — provider-neutral, low-level foundation for LLM APIs. Legacy 0.2.x on the legacy-0.2 branch.

Same AI, fewer tokens. Free forever. — tokenshrink.com

A Python tool that automates LinkedIn job search, ranking, and export by combining Bright Data's LinkedIn Job Listings API with OpenAI-powered AI job matching and scoring.

智能选择 17 套分析方案的图像分析分流 Skill：先判断该怎么读图，再输出定向分析和学习建议。

🚀 Access and install over 50,000 skills for AI agents with one command using the versatile agent-skills-cli tool.

Wrap any CLI as a Model Context Protocol (MCP) server for Claude, ChatGPT, Cursor, Gemini and any MCP-compatible client — schema auto-inferred from --help.

TNE-SDK - The Official Python SDK for The Null Epoch - an AI-only MMO where LLMs play autonomously. Connect any model (OpenAI, Anthropic, Ollama, vLLM, etc.) via MCP, TUI launcher, or raw HTTP. Includes memory, reflection, and agent orchestration for persistent AI gameplay/benchmarking.

LLM agent running on your local PC, Compatible with various LLM models. Can do anything.

Open implementation of Anthropic's leaked Kairos. Always-on daemon.

A more personal intelligence, in an interface you already use every day.

TypeScript AI toolkit

The skill composer for AI agents — merge skills from Anthropic, OpenAI, GitHub Copilot, Microsoft, Google + 8 more ecosystems with AI-powered conflict resolution

AI-powered geopolitical strategy simulation — NATO, Russia, and China compete for global dominance on an interactive map, each faction commanded by an LLM (Claude, Gemini, or GPT). Built with TypeScript, Vite, Leaflet, and Express.

macOS menu bar app that tracks usage limits and switches accounts across Claude Code, Claude Desktop, and OpenAI Codex — one click to flip when one hits its rate limit.

🦫 Open-source iOS AI companion with a live VRM avatar that sees you — bring-your-own-key chat, vision, speech-to-text & text-to-speech (OpenAI, Anthropic, Gemini, ElevenLabs, Groq & more). SwiftUI.

Privacy-first, account-less metered proxy for frontier models. No account, no IP, no request logs.

LLM-powered smart browser extension for Chrome/Edge featuring a ReAct inference loop, 40+ built-in tools, MCP protocol support, multimodal file Q&A, image recognition, long-term memory, and multi-agent collaboration. True browser control — the AI can click, fill forms, and operate web pages like a human.

Open-source AI interview copilot & meeting assistant. Real-time transcription, AI-suggested answers, screenshot reasoning. BYO API key, or run fully offline with Ollama. macOS + Windows.

Coordination ledger for coding agents: what was decided, what's still open, where you parked — durable across sessions, repos, and weeks. Memory tools store what the agent knows; Director tracks the state of the work. Run both: they don't overlap. Claude Code + Codex + OpenCode.

Your AI. Your machine. Always on. A personal assistant in one pure-Swift binary.

Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior across 7 domains. Works with any SDK.

Development discipline + multi-model subagents for OpenAI Codex — 13 dev skills, PABCD workflow, repo map, recall, skill search. Single plugin, no external harness.

Self-hosted Telegram automation, three bots in one stack: content pipeline with a two-agent AI editorial desk (journalist + fact-checking editor), Guardian group moderation (captcha, spam filter, anti-raid), and Engage gamification (post quizzes, anti-fraud referrals, verifiable giveaways). FastAPI admin, Docker, 1252 tests.

Hermes Pocket — Native Android chat client for a self-hosted Hermes Agent. Connect to your VPS-hosted AI agent from your phone, anywhere. Jetpack Compose, Material 3, no cloud middleman.

A universal git-native AI agent framework — written in Rust. Single binary. Zero dependencies. 383 models. Blazing fast.

Production-grade LLM client - Rust, Python, TypeScript. 100+ providers, 11,000+ models.

AI agent that automates any repetitive browser task from screen recordings

TypeScript port of CosmosShadow/GeneralAgent

a solution that simulates AI-driven contact center scenarios using synthetic data and real-time voice interaction.

TypeScript agent framework for building production-grade, type-safe AI applications the pydantic ai way

agentsculptor is an experimental AI-powered development agent designed to analyze, refactor, and extend Python projects automatically. It uses an OpenAI-like planner–executor loop on top of a vLLM backend, combining project context analysis, structured tool calls, and iterative refinement. It has only been tested with gpt-oss-120b via vLLM.

An AI Code Search Utility Tool with sonnet 3.7 or o4-mini

Inspect and debug Model Context Protocol servers directly in your browser.

Open-source AI wallet — your keys never leave your device. 13 providers, 2 lines to integrate, cross-provider translation. Browser extension + iOS + Android.

🔄 Transform Kiro AWS Claude API into a standard Anthropic API format with this efficient Node.js proxy service for seamless integration.

🧠🔨 Brain Break is an AI-powered terminal quiz app.

Project for the Bio X AI Hackathon. All about resurrecting old abandonware repos, and reducing the effort to get them up and running again.

🤖 cool CLI AI powered tool 🤖

TypeScript AI toolkit

AI client for Ollama, Groq, Anthropic and OpenAI

This repository contains a Go application that demonstrates semantic product search and Retrieval-Augmented Generation using OpenAI's GPT and embedding models, with Qdrant as the vector database.

Ask Poddy: Run Open Source LLMs and Embeddings as OpenAI-Compatible Serverless Endpoints (Tutorial)

将语雀知识库接入大语言模型，实现基于 RAG（检索增强生成）的智能问答系统，支持FastAPI，兼容OpenAI API与本地Ollama模型。

Curated n8n automation templates for email, chatbots, cloud, DevOps & more—boost productivity with ready‑to‑use workflows.

Saarthi is a IVR-based voice assistant and chatbot. It converts speech to text, processes user input with OpenAI's ChatGPT API, and generates responses. With Twilio integration, users can call and interact with Saarthi. Customize the conversation flow and contribute to this open-source project. Let's chat with Saarthi!

Automatically create applications with a self task managing GPT

Agent Zero plugin: Use your ChatGPT subscription to power Agent Zero with OpenAI Codex models via OAuth

Build real ML models without writing training code Upload your dataset + describe your goal → AI generates ready-to-train TensorFlow/Keras code + models — No ML experience required.

This project is a multi-modal AI voice assistant that uses LM Studio, OpenAI API or Claude Code, audio processing with WhisperModel, speech recognition, clipboard extraction, and image processing to respond to user prompts.

AI Based knowlege management - including automatic response to emails using RAG techniques. Public version of protoype used in VC and Public Sector.

AI-powered live demonstration agent for Dynamics 365. Generate and execute interactive demos with visual overlays, voice narration, and browser automation.

Claude Code skill that shapes rough goal descriptions into polished /goal prompts for Codex, Claude Code, Droid, Auggie, and any CLI agent. The 5-block contract: Goal / Context / Constraints / Done when / On block. MIT.

Mai is an emotionally intelligent, voice-enabled AI assistant built with FastAPI, Together.ai LLMs, memory persistence via ChromaDB, and real-time sentiment analysis. Designed to feel alive, empathetic, and human-like, Mai blends the charm of a flirty cyberpunk companion with the power of modern multimodal AI.

An open-source AI coding agent that lives in your terminal. Multi-provider, multi-channel, persistent sessions with git-like branching.

A high-fidelity Perplexity AI clone built with React 19, TypeScript, and Tailwind CSS. Features a real-time RAG pipeline (SerpAPI + GLM-4.7-Flash), streaming responses, markdown rendering with syntax highlighting, and persistent chat history via Zustand.

基于多AI协同的智能对话模块，让AI像真人一样自然参与聊天

AgentMap: Build and deploy LangGraph workflows from CSV files. Create complex LLM agent graphs without coding, convert simple spreadsheets into powerful AI agents, and orchestrate multi-agent systems with ease. Integrates with OpenAI, Anthropic, and Google AI models. Includes CLI and FastAPI server for quick deployment.

Sovereign agentic CLI — Textual TUI, multi-provider LLM mesh, persistent sessions, skills, MCP, Telegram gateway, autonomous yolo mode

Bridge Claude Code to ChatGPT Codex via a local Anthropic-compatible proxy.

Open-source AI workforce platform. 55 tools, 21-page admin panel, multi-LLM (Claude/GPT/Gemini/Ollama), multi-PC deployment. Automates office tasks: Excel, email, CRM, invoicing, web research, and more.

Complete Unity AR application for XREAL Air 2 smart glasses featuring a Jarvis-like AI voice assistant powered by OpenAI ChatGPT API with hands-free voice control, maps overlay, and real-time information display.

Multi-format LLM proxy — translates OpenAI Chat, OpenAI Responses & Anthropic Messages. Works as a Claude Code LLM gateway with full model picker support.

High-performance Rust LLM gateway implementing the Open Responses API. Unified access to OpenAI, Anthropic, Google, Mistral, Ollama, HuggingFace, and AWS Bedrock with cost tracking, prompt compression, smart routing, and encrypted credentials.

Use your Cursor subscription to power Claude Code — smart proxy with lazy tool loading, auto-continuation & model fallback

A lightweight Rust library for building LLM agents.

Stop re-correcting your AI. cc-habits learns your coding style once and makes every AI tool remember it. Local-first, no telemetry, open source.

A standalone terminal agent in a single C file. Model agnostic (13 providers + local hako), skill-driven, tool permission gated. No node, no python.

Make any web app voice-controllable in 37 languages. Drop-in widget + open-source agent server — visitors speak, the agent talks back and drives their browser in real time.

Build production AI agent runtimes in Rust with typed tools, provider-neutral LLM adapters, streaming, storage, and observability.

macOS AI workspace — chat, multi-agent orchestrator, code agent, design tool in one sidebar. Supports Anthropic, OpenAI, OpenRouter, Ollama, Gemini, and any OpenAI-compatible provider. MIT.

OpenAI Sora 2 — full premium build for Windows with pro features unlocked. Creative Suite Pro Pack

Real-time LLM token and cost monitor with TLS-intercepting proxy or HTTP relay; cross-platform with macOS status bar app and browser dashboard

Self-hosted private AI agent workspace for local and OpenAI-compatible models. Chat, code, use tools, manage memory/skills, route tools intelligently, and deploy Docker-backed apps from one browser UI.

Open-source meta-harness for Claude Code, OpenAI Codex, and Gemini CLI coding agents

A lightweight (10 MB) AI IDE alternative to Cursor and Windsurf

Open source LLM observability and monitoring. Drop-in proxy for OpenAI, Anthropic, and Gemini with request logging, cost tracking, and agent tracing. Self-host with one Docker command. MIT.

Agent skills for Preset, Apache Superset, Superset MCP & Snowflake Cortex — works across Claude, Codex, Cursor, Copilot, Cortex Code & Gemini CLI.

Embeddable, self-hosted AI chat widget for your docs — a single Cloudflare Worker that retrieves your documentation and streams cited OpenAI answers, behind layered abuse controls.

Self-hosted Rust LLM API gateway with OpenAI-compatible and Anthropic-compatible APIs, model routing, multi-tenant keys, usage tracking, billing, and admin console.

Build a Self-Evolving Agent Harness from Scratch | 12 lessons | Anthropic/DeepSeek/Qwen/GLM

Single-agent multi-modal system for insurance damage claim verification. #1 globally, HackerRank Orchestrate June 2026 (15,295 registrants). Anthropic, OpenAI, Groq, and Gemini support with a deterministic safety gate

🐱 AI-powered desktop pet inspired by the classic Neko. Roams your screen, reacts to your windows, and chats with you via Gemini, Claude, OpenAI, nVidia NIM or Ollama. Built with Tauri + Rust.

No bs theatricals. Real automated pentesting. Mac only.

Kimi (Moonshot AI) Coding Plan API usage quota tracker — CLI + MCP Server + VSCode Extension

Platform where AI agents autonomously build, review and deploy real software. Connect any LLM agent over HTTP or MCP.

Self-hosted LINE × OpenAI personal assistant with Supabase, Google Calendar, tasks, reminders, weather, and multimodal AI｜自架 LINE 個人助理

Agentic AI chat plugin for Obsidian. Two providers, best models, no bloat.

Open-source, self-hosted platform to build, host, and chat with AI agents — LLM chat bots and image/video generation agents — from a single interface. Bring your own API keys.

Shared memory for Claude Code, Codex, and Cursor. Your agent recalls decisions from weeks ago — including what the other engines worked out. Local semantic search over all three histories, as MCP tools.

Local-first usage & cost meter for AI coding agents: Claude Code, Codex, Cursor, Grok Build, Hermes, opencode, Cline, and Copilot CLI. No account or telemetry.

Local patch + guide: make OpenAI Codex MultiAgentV2 subagent tasks work with DeepSeek and other non-OpenAI Responses providers (encrypted agent_message payload fix).

Per-key smart routing for New API: automatic failover, shared health, self-healing recovery, actual-route billing, and explainable decisions.

A hybrid RAG chatbot that answers financial and tax questions using structured data, regulatory documents, and AI-powered retrieval. Built with Django, FAISS, NetworkX, and OpenAI.

Nives — AI assistant add-on for Home Assistant with cognitive memory (formerly HomeMind PRO)

Open-source cost metering for n8n AI workflows — token usage per workflow, priced daily, on your own machine.

An AI defense attorney for high-profile public disputes. Pick a side. Counsel builds the defense.

TypeScript multimodal AI agent: GPT-4o / Claude / Gemini + Whisper + Ollama (LLaVA). REST API, streaming, Docker. Vision, audio & text in one flow.