Category
Agent frameworks & infrastructure
46,465 agents
Every agent in Agent frameworks & infrastructure, page 111 of 465
OpenAI model implementation for the ADK-Go
Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems
Application toolkit based on the JADE framework. Functionalities for time aspects, agent environment interaction, visualization and load balancing, focusing on the usability for end users.
Self-hosted multitenant platform for AI agents and Telegram bots with event-driven architecture
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers
🤖 基于AutoGen的AI辩论系统 | 🗣️ 支持中文交互 | 🔄 多智能体协作 | 📝 自动记录辩论过程 🤖 AI Debate System based on AutoGen | 🗣️ Chinese Interaction | 🔄 Multi-Agent Collaboration | 📝 Auto Debate Recording
LLMProxy is an intelligent large language model backend routing proxy service.
AI 多模型 API 聚合与协议转换网关:统一调用并互转 OpenAI Chat/Responses、Claude、Gemini 等格式,Provider 仅需实现原生协议。Multi-LLM gateway & protocol transformer: unify and convert OpenAI Chat/Responses, Claude, Gemini, etc.; providers implement native only.
Simulation Streams is a programming paradigm designed to efficiently control and leverage Large Language Models (LLMs) for complex, dynamic simulations and agentic workflows.
Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence
A lightweight, production-ready multi-agent framework
SDK Client for Agent Command Center
I use n0x as my ChatGPT replacement.
C bindings for the OpenAI API
Step by step code samples showing how AI agent architectures evolve from simple to production ready using AWS services including Amazon Bedrock AgentCore Runtime.
Make stochastic AI systems durable with one decorator
Unified MCP context intelligence platform — pip-installable CLI that absorbed 6 foundational repos. Context engineering for AI agents.
Open-source bundle of agent methodologies and Hermes-compatible skills.
AI Agents internals - system prompts, tool architectures, and implementation patterns
Scalable agent registry for AI agents using A2A protocol AgentCard with semantic search. AWS serverless (Lambda, S3 Vectors, Bedrock). Python SDK & React Web UI.
Real, runnable Flue agents on Cloudflare. Examples teach one product at a time; recipes compose. Every snippet ships an E2E test that deploys an ephemeral Worker, asserts, and tears it down.
Self-hosted MCP memory server for personal use and teams
A declarative meta-language for orchestrating multi-agent workflows. Readable by humans. Executable by LLMs. Portable across models.
A scalable AI chatbot platform built with FastAPI and LangGraph, featuring multi-agent orchestration, multi-tenant vector storage, cross-chat memory, and voice call capabilities through LiveKit integration.
Human-in-the-loop multi-agent task orchestration platform for Git-based software workflows.
The open-source, local-first alternative to LangSmith. No cloud. No setup.
Postman for AI - design, evaluate, and debug LLM interactions with full transparency.
Multi-backend observability CLI for metrics, logs, and traces — unified interface, AI-Agent friendly
🚀 Transform Antigravity into standard Claude and Gemini APIs, enabling seamless tool use, structured outputs, and workaround support for MCP issues.
HYBRO Hub: local & remote AI agents — private, powerful, unified.
🌿 Prune your AI agent's context window. Reduce token usage by 70-95% with hierarchical memory. Replace flat MEMORY.md with a bonsai-shaped domain tree. Progressive disclosure, zero dependencies. Works with OpenClaw and any LLM agent framework.
Hands-on labs for Microsoft Foundry - Azure's unified PaaS for enterprise AI. Notebooks + Bicep covering provisioning, agents (incl. hosted Copilot SDK + REST), MCP, Foundry IQ knowledge bases, guardrails, red-teaming, and fine-tuning.
Switch Claude Code, Claude Desktop and ChatGPT/Codex to third-party models from one desktop app. Local proxy converts Anthropic/OpenAI formats automatically.
Agent emotional continuity with PAD state, trust, appraisal, and compact emotion logs.
A practical guide to AI engineering — LLMs, RAG, agents, evals, and production ops. Built for engineers who ship AI systems.
Local streaming reverse proxy between AI coding agents (Claude Code, Cursor, Codex) and model APIs (Anthropic, OpenAI, Gemini, MiniMax). Meters every token + USD cost, compacts bloated context to cut pay-per-token API spend, and runs shadow-eval to prove quality held. ccusage-style metering + live local dashboard.
this is the blog of LLM and MultiModel which is study method
Build Your First Copilot Challenge (Foundry Edition)
MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games
Terminal UI toolkit for agentic and chat apps, built on rich + prompt_toolkit.
Auto-evolving LLM Agent Harness - Benchmark-driven evolution via Claude Code + self_evolution.md guide
Tandem lets you connect and control any coding agent—including Claude, Codex, or Hermes—across different devices. It allows all your agents to coordinate with each other seamlessly, whether you're working from a browser, a terminal, or any other client.
AI 原生多租户 SaaS 开发框架 — FastAPI + Vue 3 + PostgreSQL,内置 AI Agent、RAG、插件系统、RBAC、异步任务等核心能力,助力快速构建行业 SaaS 应用。
Hosted persistent memory for AI agents over MCP. Tell it a recalled memory helped or misled, and it re-ranks what comes back next. Shared rooms for multi-agent work. One key or OAuth across Claude Code, Cursor, VS Code and ChatGPT. MIT, in the official MCP Registry.
A local-first desktop application for AI agent workflows.
Smart AI proxy router that connects Claude Code, Cursor, Codex, Copilot, and 50+ coding tools to 40+ AI providers with 100+ models. Saves 20-40% tokens via RTK compression, auto-fallback from subscription to cheap to free providers, multi-account round-robin, and a local dashboard.
Open-source AI agent that reasons by blending many AI models, does real work on its own, and keeps learning — safe, self-hostable, and fully yours.
gradio region:us
gradio region:us
gradio region:us
transformers safetensors mistral text-generation conversational fr
transformers safetensors gguf gemma2 text-generation conversational
transformers safetensors llama text-generation conversational en
transformers gguf code deepseek bf16 text-generation
transformers safetensors gemma2 text-generation conversational ar
gradio region:us
transformers safetensors qwen2 text-generation chat conversational
OpenFang 中文本地化版:面向中文用户的开源 AI Agent OS
The memory layer for investment agents.
Agent-SDK without CLI dependencies, as an alternative to claude-agent-sdk, completely open source
My LLM Agent Learning
Forkable shell substrate for a single code repository — DB-backed identity, memory, roadmap, content; harness-agnostic boot. We build the data layer, we rent the harness.
Agent memory for LLM agents: 7 neuroscience-inspired layers (working, episodic, semantic, procedural) with FSRS-style spaced repetition and memory consolidation. TypeScript, no third-party dependencies in the core packages; Model Context Protocol (MCP) server, Vercel AI SDK middleware. Paper: arXiv 2604.23878 · reproduction packages on Zenodo.
Open-source cost metering for n8n AI workflows — token usage per workflow, priced daily, on your own machine.
A curated paper list on agentic artifact creation, an emerging paradigm in which AI agents autonomously construct and iteratively refine artifacts.
MAS-Orchestra: train, inspect, and vibe-code multi-agent systems with RL-learned orchestration and MASBench
You're the boss. Claude and Copilot are your employees. Give them desks, assign them work, and watch them build — in a pixel-art office.
Practical evaluation techniques, benchmarks, and examples for production AI agents: RAG, tool use, planning, memory, safety, reliability, and cost.
transformers safetensors jais2 text-generation conversational ar
Agent-first multi-tenant Next.js template (rules, sub-agents, skills, Better Auth, Prisma)
Moved to PostHog/coherence — development continues there as @posthog/coherence.
A local-first context engine designed for seamless human-agent and multi-agent collaboration. It systematically synthesizes, organizes, and maintains multi-format workspaces, turning raw notes, code, tables, and documents into a structured, high-signal knowledge base accessible to both users and autonomous agent ecosystems.
Local control plane for Claude Code on Windows and macOS: switch LLM gateways in one click behind a fixed endpoint, SSE keepalive proxies, key pools with live balances, GitHub accounts with TOTP, statusline, Telegram remote.
Persistent memory MCP server for AI agents — Rust, 19 tools, knowledge graph, Hebbian learning, episodic memory, contradiction detection, prospective triggers, Bayesian calibration, zero-config Docker setup.
A multi-agent platform for transforming enterprises into AI-ready organizations — built on Amazon Bedrock AgentCore, powered by AWS.
Content agent template for the eve agent framework
Free, unlimited Google Gemini Pro API proxy completely compatible with OpenAI and Anthropic standards. Features auto cookie refresh, account pooling, and a beautiful admin dashboard.
AI agent skills for thinking clearly, making better decisions, and getting things done. Strategy, research, decision-making, planning, risk management, negotiation, execution, strategic thinking, BMAD-METHOD elicitation, reasoning, business strategy, market research, competitive intelligence, forecasting, scenario planning, problem solving, priorit
Real-time agent visualization in pixel office for Claude CLI and Claude macOS app with basic Codex support /// Real time визуализация ИИ агентов в виде пиксельного офиса для Claude CLI и Claude macOS app с базовой поддержкой Codex.
Sub2API 0.2.7 OpenAI OAuth 插件:Excel2API BPS 隧道、Codex CLI 工具目录、请求时区与并行降智检测。
explicit intent layer for agent-to-agent protocols and token-efficient RAG discovery.
让非多模态模型(DeepSeek 等)把图片识别委托给任意 OpenAI 兼容的多模态模型。零厂商硬编码,主模型支持视觉时自动隐藏自己。
端到端智能体平台:把本机的 AI Agent 变成人人可用的 Web 产品(Vue 3 + Flask + Go WS 网关 + Docker 部署)
Instant context compaction for Hermes Agent. Builds the compaction summary in milliseconds with no LLM call, keeping the exact commands, exit codes, errors and files, each linked back to its original message. Based on the VCC paper.
😎 A curated list of guides, use cases, tools, and news for Muse, Meta's personal AI agent.
MASRubric: Auditing Information Flow in Multi-Agent Systems with Failure-Distilled Pitfall Rubrics.
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory via SQLite + FTS5, and enforces routing across 17 platforms through MCP + hooks. Works with Claude Code, Gemini CLI, VS Code Copilot, OpenCode, Codex CLI.
🤖 Каталог ИИ-инструментов для разработчиков на русском (2026): AI-IDE, Cursor, Copilot, Claude Code, Codex, агенты, MCP, код-ревью, тесты, LLMOps, локальные LLM, российские сервисы
⚡ One API for 20+ LLM providers. OpenAI-compatible, single binary edge gateway, streaming & rate-limiting.
这是一套围绕 Stanford CS224N: Natural Language Processing with Deep Learning 整理的系统课程笔记。仓库以课程 19 节 Lecture 为主线,从 Word Vectors、RNN、Attention、Transformer 一路延伸到 Pretraining、Post-training、PEFT、RAG、Agents、Reasoning、Multilinguality、Interpretability 与 Multimodality。
Run a company of AI agents from a pixel-art office: hire in a character creator, watch them work and chat, design the office, spend earned coins in the Market. Claude, Codex, Gemini, OpenRouter.
Qavor 是面向开发者的 AI Agent 构建、扩展、运行与观测全栈平台。后端 Go + CloudWeGo Eino,前端 Vue 3 + Vite,整合模型管理、Agent 编排、RAG 知识库、MCP/Skill 工具扩展、Redis 异步队列与 SSE 流式服务,并提供内置链路追踪与数据总览。
A LangChain-powered multi-agent system with agent routing, skill routing, and execution harness.
LangGraph agent template with MCP.
Fluent GPT App, an open-source, multi-platform desktop application that brings the power of GPT models to your fingertips. Designed with a sleek Fluent interface, it offers a unique and customizable chat experience on Windows, macOS, and Linux.
Dashboard that allows the user to visualize in a clear and intuitive way how the OpenAI models are being used.
Easily manage ChatGPT conversation variables
The state-of-the-art in multi-agent Reinforcement Learning is the MADDPG algorithm which utilises DDPG actor-critic neural networks where each agent uses centralized critic training but decentralized actor execution, and is capable of learning either cooperative or competitive environments. This is demonstrated on the Unity Tennis Environment.
code for DyPS: Dynamic Parameter Sharing in Multi-Agent Reinforcement Learning for Spatio-Temporal Resource Allocation