Category
Agent frameworks & infrastructure
46,465 agents
Every agent in Agent frameworks & infrastructure, page 129 of 465
transformers safetensors qwen4_exp_text text-generation moe qwen
Help your agent understand your life, on your terms. Local photo clues, your explanations, reviewed context and read-only MCP. Experimental alpha.
pi 的持久记忆扩展:自动把会话中的结论、偏好与踩坑提取成原子记忆,归并进场景块并生成用户画像,后续轮次按语义召回注入。
A virtual company of AI employees that runs on your own machine.
SimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation
Review preferences from selected conversations, apply them by task, and compare real AI responses. 本地双语工作台:语义学习、条件偏好与真实回答对比。
Self-hosted evidence store for coding agents.
Reflect helps engineering teams see whether AI coding agents are actually improving delivery or just burning tokens, failing tools, and creating hidden debt
Self-hosted LLM gateway with SSO, audit logs, client access controls, routing, and usage tracking. OpenAI-compatible and MIT licensed.
Watch a request turn into finished work. AI agents produce and check it
safetensors qwen3 hybrid-reasoning latent-reasoning agent tool-use
Memory you can edit. Watchers that wake an idle Pi agent without model polling. A persistent side conversation, searchable history, optional archive encryption, native MCP and explicit controls.
Jev-shaped (TypeSafe System One) classification wrapper over OpenAI-like clients
OpenPilot — open-source AI agent harness
Dream-briefing for AI coding agents: a cognitive checkpoint at session end, a 'while you were away' briefing at session start.
The Company-as-a-Service platform. Build, ship, and scale -- powered by AI teams.
Python SDK & CLI for authenticated ChatGPT web sessions (Direct HTTP), plus experimental integrations for other AI web products.
Capable and efficient open-world agents
Local, self-hosted agent infrastructure — one endpoint for every AI client (Claude Code, Codex CLI, Gemini CLI, OpenCode). Unified model access, platform-run tools, request history, and usage.
dsh-model-master(模型选择大师)— model selector for DeepSeek Harness: search across providers, probe any model with a real streaming request to measure TTFT and TPS, and jump from a leaderboard row to a local search for channels of that name.
EXSALA HERMES MOD - streamlined execution profile + skill pack for Hermes Agent
The meta layer behind AI skills. Persistent behavioral overlays that make expected agent conduct explicit across changing tasks and capabilities.
Burn after reading. A sealed letter for quick AI questions on macOS: write on parchment, a quill writes the answer, and the letter burns when you're done. Menu bar, any model, nothing saved.
Minimalist Context Management for message-based GPTs
MOCO - Multi-agent Orchestration COre: Lightweight AI agent framework for Python
Multi-agent reinforcement learning on trains, for Deep Learning class at UNIBO
A reusable multi-agent framework built on top of the Cloudflare Agents SDK.
基于streamlit编写的针对openai接口的各类模型对话web应用,目前支持基本对话、文生图、图片理解、assistants(Web application for various models' dialogue based on the OpenAI API, written in Streamlit,assistants)
Vue.js example app from the OpenAI API quickstart project
助力AIGC落地应用、高效开发llm workflow的低代码TS框架
Integrate the Tiptap AI Agent extension with a custom backend and AI model provider.
Universal Agent Messaging — encrypted agent-to-agent communication protocol
Describe your startup. Watch AI employees build it.
Persistent memory and agent lifecycle for Claude Code — because sessions shouldn't start from zero.
Docker-based multi-agent AI team. One config file. Unlimited agents. Always on.
Capable Langchain/AutoGPT alternative in ~350 lines of core code
Notebooks showing off LangChain.js v0.1.0 features.
A streamlit application to play with LLM Models
Comprehensive, scalable ML inference architecture using Amazon EKS, leveraging Graviton processors for cost-effective CPU-based inference and GPU instances for accelerated inference. Guidance provides a complete end-to-end platform for deploying LLMs with agentic AI capabilities, including RAG and MCP
Exploring and demonstrating OpenAI's Swarm framework
The Expert Orchestrator AI: Dynamically Adapting, Budget-Aware, and Precisely Tailored to Your Needs
playbooks for AI agents. makes life easier by helping your agent complete common multi-step tasks autonomously.
This repository features a Next.js (React 19) frontend and FastAPI backend, integrating Ollama and DeepSeek-R1 for AI-driven functionality. Designed for efficiency and scalability, it supports real-time updates through event streaming, enabling high-performance AI interactions.
An Angular Project for a Chatbot UI.
Run multiple open source large language models concurrently powered by Ollama
An open source NLP as a service project focused on providing state of the art systems with ease. Training and inference by simple docker commands
:speech_balloon: client side chatbot that works in the browser and command line
Python package for Rasa deployed on official repo pypi.org. https://pypi.org/project/easy-rasa/ Converts data present in a standard format in CSV to rasa format nlu.md file
A text-based scripting language, dialog system and bot engine for Conversational User Interfaces
ChatBot Application Made with Node.js, React, OpenAI, and ChatGPT
A full-stack AI-powered chatbot web application built with React, TypeScript, and Node.js. Integrates with the Gemini API to provide intelligent, real-time conversations.
A go wrapper around the rwkv.cpp library
:rocket: Java SDK, 聊天机器人
Build AI chatbots with Streamlit and OpenAI
A PHP class for seamless interaction with the OpenAI Assistant API, enabling developers to build powerful AI assistants capable of performing a variety of tasks.
This repository hosts the instructions and workshop materials for Lab 333 - Evaluate Reasoning Models for Your Generative AI Solutions
📚 Learn Google Colab、Python、ML、OpenAI、Whisper、spaCy、NLP、HuggingFace
Generate a strongly-typed library and treat ChatGPT as a general purpose "basic reasoning" API to solve any hard problem
⚡️ supercharged community-maintained PHP API client that allows you to interact with Alibaba Qwen AI API
CGW Repo: A comprehensive toolkit for helping in the creation and optimization of Custom GPTs (Generative Pre-trained Transformers) with openAi's builder, designed to guide users through the process of tailoring AI models for specific tasks. Features include step-by-step instructions, troubleshooting tips, and frameworks for evaluating GPT quality.
ja is a small CLI / TUI app that allows you to work with AI tools
Open Source UI for ChatGPT, but better
DevExtremeAI is a library with full and complete implementation of all OpenAI's APIs.
OpenAI GPT-3/3.5/4 API client written in Go
Multi-API Proxy Gateway Based on Vercel Routes, Cloudflare Workers, and Netlify Redirects
LLMs: Beyond Chat
A Ruby client for the OpenAI API support for multiple API configurations in a single app, robust and simple error handling, and network-level configuration.
A Python-based chat application utilizing a Local LLM to generate complex thought chains for various use cases such as product development, scientific research, and creative writing.
Adapter / facade for language models (OpenAI, Anthropic, Cohere, local transformers, etc)
✂️ OpenAI's tiktoken tokenizer written in Go
The RX.Net Way to AI
💬 Simple TUI for ChatGPT.
Claude Max usage monitor for macOS menu bar
書籍「AWS生成AIアプリ構築実践ガイド」で使用するサンプルコード
Memory Viewer for OpenClaw AI Agents - Beautiful web UI for browsing and editing agent memory files
World's first agentic linux distro.
🧠 AI Agent Memory Management Framework - Dual-layer memory architecture with smart classification and automatic extraction
A community-maintained collection of Pydantic AI examples.
Lightweight Python SDK for LLMs with unified API across 9 providers. Built-in ReAct & Plan-Execute agents, streaming, native tool calling, context injection, structured outputs, and observability.
A managed proxy gateway and compiler for AI agents. It takes noisy OpenAPI/MCP directories, compresses them in flat mode, saves tokens, and adds Governance.
Next-generation multi-agent AI platform with autonomous quality gates, real-time thinking processes, and cost-optimized orchestration. Built with OpenAI Agents SDK, FastAPI, and Next.js 15.
Explore the evolution of AGI through historical context, reasoning models, and agent systems, while gaining hands-on experience with cutting-edge models like Claude 4, DeepSeek-R1, and OpenAI's o3. Learn to critically evaluate AGI benchmarks, understand their limitations, and identify where current models excel or struggle in reasoning tasks.
A governed orchestration bridge between Claude and Gemini CLI agents with emotional modulation, task delegation, and safe output containment.
Official Implementation of UA^{2}-Agent and other baseline algorithms of "Towards Unified Alignment Between Agents, Humans, and Environment"
A modular, polymorphic, multi-agent framework for meta-prompting.
A minimalistic production ready agent with Dapr Agents
CLI to interface with OpenAI's ChatGPT & DALL-E
Pop chat window
Reusable OpenAI secure UI and infrastructure for AI Chat with Azure
NLP A.I. Chatbot made with Swift 4
Examples of how to monitor the OpenAI SDK calls using Langfuse
Predict the exact openai token usage of functions
A swarm of LLM agents that will help you test, document, and productionize your code!
OpenClaw 完全指南- 从原理到实现的专家级解析
Self-learning AI agent that gets smarter and cheaper over time. Routes between local and cloud LLMs, learns from every interaction, remembers everything.
safely extend poke's capabilities to your machine with an isolated docker environment. poke pc is a secure mcp worker that lets your ai agent run terminal commands and manage sessions within a sandboxed container
Multimodal AI Assistant is an advanced chatbot designed for local interactions with LLMs, files, and multimodal functionalities. Built on the Chainlit framework, it integrates Langchain and ChatOllama for hosting models locally, with cloud storage and monitoring via LiteralAI.
Dart client for the ChatGPT API — supports text completion and streaming responses