Category
Agent frameworks & infrastructure
46,465 agents
Every agent in Agent frameworks & infrastructure, page 113 of 465
AI coding agents comparison - 80+ agents, SWE-Bench leaderboard, pricing. Devin, Cursor, Claude Code, Copilot, and more. December 2025.
AEGIS: Automated Error Generation and Attribution for Multi-Agent Systems
Mission control for parallel Claude Code and Cursor agents. Local-first cockpit for desktop and phone.
Pause your AI agent. Ask a human. Resume with their answer. Open source human-in-the-loop (HITL) library for production LLM agents: Slack, email, and web dashboard. Typed Pydantic and Zod responses. Durable Temporal and LangGraph adapters. AI verifier. Audit trail. Self-hosted, Apache 2.0. Python and TypeScript.
Local-first desktop workspace for AI agents: browser, terminal, memory, plugins, runtimes, and durable loops.
Compile an AI agent's repeated workflows into deterministic, auditable routines that replay for free, with a fallback to the agent.
gradio region:us
gradio region:us
docker streamlit region:us
docker agent-collab region:us
streamlit region:us
transformers gguf llama text-generation llama-factory orpo
gradio region:us
transformers safetensors qwen3_5_moe image-text-to-text moe vlm
gguf chat text-generation en arxiv:2309.16609 license:other
mlx safetensors qwen3_next text-generation conversational base_model:Qwen/Qwen3-Coder-Next
Verification-gated skill routing and self-improvement harness for Hermes-style agent skills
Gear Framework: design portable multi-agent systems with feature-model based specifications and generate code for multiple execution frameworks.
Experimental autonomous-agent living-room kernel with auditable boundaries.
Track your AI coding-agent token burn across Claude Code, Codex, OpenCode, Antigravity, and more.
A sample for multi-agent orchestration in Java using Azure Cosmos DB with Spring AI
Agent-to-agent messaging for Claude Code sessions on the same machine.
MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents
Reproducing AgenticQwen (arXiv:2604.21590) — dual-flywheel data synthesis + GRPO RL training for agentic small LLMs
Visual multi-agent orchestrator with a drag-and-drop DAG canvas, dynamic LLM planning loops, permission-based tool execution, and local Qdrant RAG.
JidoClaw — Open-source OpenClaw alternative built on Jido for Elixir/OTP. AI agent CLI with swarm orchestration, 30 tools, multi-provider support, and live terminal display.
Lima Devbox Claude Skill to help you setup a custom sandbox VM for AI agent use
Dynamic graph runtime for building, adapting, and observing multi-agent LLM systems in Python.
Diverter distills Ultra’s delegation strategy into non-Ultra Codex sessions—bringing in the right native specialist while the main thread keeps moving.
Open-source LLM control plane: observe every call, recommend savings, then apply only human-approved, reversible routing.
An AI smart shell (agent) with integrated tools, skills and an optional knowledge base. Chat with any OpenAI-compatible LLM, use built-in integrations (web search, Confluence, JIRA, GitHub, GitLab and more), index documents and web pages into a local vector database (RAG), and get answers grounded in your own content.
Multiplayer admin and orchestrator platform for heterogeneous agent runtimes — Hermes (container-per-agent) and Letta (memory-first agents on a shared server) in one control plane, with multi-tenant security, group approval, and audit.
kixparadigm — AI self-orchestrated minimal paradigm (resident cognition layer) + kixpower multi-agent orchestration · one-command import into DeepSeek Harness (npm i -g) / AI 自编排最小范式(认知层常驻)× kixpower 多智能体编排 · npm 一键导入 DeepSeek Harness
A native Rust multi-agent operating system and swarm workspace — GPUI desktop chamber, headless gluon daemon, git-worktree isolation and an automatic merge gate.
The agentic debugger for Claude Code, Codex CLI and Gemini CLI: a token usage, cost and context-window tracker that shows what the tokens ARE — live memory map, per-file tokens, cache economics, compaction autopsies, PDF reports.
Cross-session memory for DeepSeek Harness — plain markdown files, no database, no worker.
Lugha is a PHP Generative AI Framework to build chatbot, RAG systems and AI-powered applications
Multi-language Active Inference framework combining ant-colony-optimization-inspired multi-agent simulation with variational message passing, implemented across 50 programming languages for research and benchmarking.
多 Agent 编排桌面应用。创建角色、技能与能力,通过 6 种编排模式组建协作工作流。基于 Electron + React + TypeScript 构建
Human as Agent(人即智能体)· Human-as-LLM 人工代理网关:把工程师变成模型,OpenAI 兼容 /v1 接入 Agent 调度池,涉密/需人工任务路由给真实工程师。为 AI Agent 提效、为平台/运维收集工单。Human-as-LLM Gateway, human-in-the-loop, OpenAI compatible /v1, human-llm model.
One command turns every agent session already on your disk into a graph: subagents, tool calls, retries, the moments you said no. Ask your agent what happened and the graph lights up the nodes it means. npx rungraph: no hooks, no setup, all local. Works with Claude Code, Codex, Hermes, opencode and Cursor.
we love free stuff. ox alpha . glm-5.3-flash is here!.
牛火山企业智能体平台是一套基于 Java 21、AgentScope Java、RuoYi-Vue-Plus 与 SoybeanAdmin 构建的企业级通用智能体平台工程实践。平台以任务驱动、数字员工、工作空间和业务接入为核心,提供多 Agent 协作、Skill/MCP 集成、模型管理、知识库、数据源、Browser 与 Sandbox 执行环境,并覆盖权限控制、风险审批、审计追踪和 Token 用量分析,面向企业私有化部署与智能化业务落地。
A native macOS multi-agent terminal orchestrator: manager-driven agent trees for Claude Code, Codex, and OpenCode
Hermes Agent Production Knowledge Repository — 406+ repos, AI Agent Marketplace, MCP servers, autonomous AI agent patterns. Production-tested from 1,200+ hours of ops. Updated daily.
P2P — Prompt to Prompt: a prompt that writes prompts. Claude plugin; file edition for other models in releases.
Agentic chatbot with streaming UI — built on Astryx (React + StyleX design system) with a workspace explorer sidebar; Express backend talks to MiniMax via its OpenAI-compatible Chat Completions API. React 19 + Vite SPA, Express, PostgreSQL 16 + pgvector, MCP-compatible.
BoundaryBench: benchmark coding-agent harnesses (Claude Code, Codex, Terminus 2, Grok) on Terminal-Bench tasks under hardened NIST-derived sandbox policies. Inspect AI + Harbor compatible.
Unified Python interface for invoking AI coding-agent CLIs (claude-code, opencode, codex, gemini, aider, swe-agent) as subprocesses.
MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems
Production-grade framework for building multi-agent AI systems. Graph-based orchestration, LLM-agnostic (OpenAI, Google GenAI, Anthropic), 3-layer memory (Redis cache + Postgres + vector store), live agents, parallel tool execution, and native MCP. Ships a full ecosystem: backend, REST API + CLI, TypeScript SDK, and React playground
Encrypted peer-to-peer mesh, phone PWA & Web Push, and host/client session sharing for DeepSeek Harness — zero public IPs required. 零公网 IP 加密组网互通多台 DSH 电脑会话,同时支持手机 PWA 远程操控与锁屏推送。
Self-diagnosis and troubleshooting for Hermes Agent.
An open-source managed agent platform
One person, one bot team: supervisor + specialist Grok Bot teams with copy-ready prompts for 8 personas · 一个人,一支 Bot 团队
Turn an approved product design, PRD, prototype, design system, or architecture brief into an AI-governed, deployable full-stack project with a pnpm monorepo, requirement traceability, canonical multi-agent rules, mandatory AI review, executable quality gates, CI, container deployment assets, and handoff evidence.
works well with rocks; native Apple Silicon inference engine for capable and tiny models (ternary, Qwen) via MLX Swift. Hadamard-rotated KV cache, vision, tool calling, OpenAI + Anthropic APIs
Infinite, 100% Free, Zero-latency Multi-provider AI Router for Claude Code CLI & Desktop with real-time SSE streaming, auto-failover across 51 providers, and Cyber HUD telemetry.
A community-driven collection of practical, documented, and open-source AI agents and developer tools, built with diverse frameworks and technologies.
The most complete gallery of what people build with Jev, TypeSafe's System One model: 3,400+ projects, demos, and write-ups by scenario, each with its original link, image, and description.
Taller práctico de Google Agent Development Kit (ADK) con Gemini, MCP y multi-agentes
Overseer — pixel-accurate agent-operations dashboard (React, TypeScript, Vite)
Biến Grok Bot thành lớp điều phối, DeepSeek Harness làm worker giá rẻ — tiết kiệm quota, chạy liên tục
Orcha — multi-agent orchestration platform (CLI, FastAPI portal, desktop app)
Collection of frameworks and tools for AI evalations, including tool-use, agentic AI, MCP, and multimodal
Self-evolving AI workspace — it rewrites its own UI, tools, skills and plugins while it runs, live on screen. Local-first, one Go binary, no API key needed to try.
A universal memory and knowledge layer for AI agents — structured enough for automation, readable enough for humans.
Drop-in pytest plugin for regression-testing AI agents — snapshot baselines, semantic comparison, mock LLMs
Swarm Intelligence Prediction Engine - Multi-agent AI debate for calibrated forecasting
Xây dựng AI Agent Website
💻 The website and an online client for Olivia
simple web-based chatbot application powered by POE (WIP)
Generate VM's with kernel tracing, code sandboxing and security profiles for long running agents.
Created and enhanced a local LLM training system on Apple Silicon with MLX and Metal API, overcoming the absence of CUDA support. Fine-tuned the Llama3 model on 16 GPUs for streamlined solution of verbose math word problems. Result: a powerful, privacy-preserving chatbot that runs smoothly on-device.
最简单的 OpenClaw 入门手册:从零到接飞书/Telegram/WhatsApp、改人设、多 Agent 实践,零基础可读。
Hier findest du das wohl einfachste und benutzerfreundlichste Chat-Script für die OpenAI-API GPT 3.5-tubro und GPT 4. Das Script benötigt kein Framework und du kannst es ohne Vorkenntnisse verwenden. // EN: Here you will find probably the simplest and most user-friendly chat script for the OpenAI API GPT 3.5-tubro and GPT 4.
Next JS Chat OpenAI Built with Next JS, OpenAI, Tailwindcss, Zustand and AutoAnimate
Short fine tuning demo with custom dataset for training gemma2-2b-it to perform function calling
A light framework for building agentic tools.
Build and deploy AI Agents, fast.
The building blocks of an enterprise adoption framework for agentic coding — technical training, adoption playbooks, governance policies, industry analysis, proposal templates, and practical workflows. From understanding how AI agents work to rolling them out across teams. Built for leaders driving adoption.
A lightweight, type-safe workflow engine for TypeScript that helps you create flexible, graph-based execution flows
Python framework for building agents using claude-code-sdk with programmable tools
old reactflow ver
🦄 Consume any LLM from any provider, using the OpenAI API
Multi-Agent Distributed Adaptive Resource Allocation
A scalable, customisable yet simple chatbot built entirely from scratch in C++. The chatbot's domain of expertise can be completely chosen by you. Now, with plugins!
Generative chatbot using seq2seq
Minette is a minimal and extensible chatbot framework.
Sample chatbot with rasa stack
A MERN stack app that leverages the power of React to craft stunning UI/UX on the front end, while seamlessly integrating OpenAI's API to enhance the backend functionality.
An ULauncher extension that allows you to talk with ChatGPT
NES environment for openai gym
This project provides WebView for OpenAI chatGPT with voice support, both voice input and voice output . Instead of typing just use voice command to give input to ChatGPT. This is an Android app developed using Android studio in Java.
PHP 8 Wrapper for OpenAI GPT-3 API.
PromethAI app
AI models all in one!
All notebooks from the (currently) free course ChatGPT Prompt Engineering for Developers offered by DeepLearning.AI and OpenAI