Search

CLI for AI coding agents: persistent tasks, memory, events, and deterministic resume across crashes and session resets.

Zero-token execution layer for AI agents — define workflows once, execute forever. DAG engine with reasoning nodes, event sourcing, scheduling, and secret vault via 6 MCP tools over SSE.

BACH v3.7.1 — Text-based OS for LLMs. Personal Agentic OS with 109+ handlers, 373+ tools, 932+ skills, portable agents, MCP servers, bridge system (Telegram/REST), LLM chain orchestration, and full EN/DE multilingual support.

Currency exchange agent built using Microsoft Agent Framework hosted in scalable Azure Container App

Convenience layer over Semantic Kernel for Python

Integration Agent Framework and Agent 365 to extend Agent for 👀monitoring and 🔮M365 MCP

Executable contracts for multi-agent AI coordination. Write contracts once in AL, transpile to Python/JavaScript/Go/Rust/C#. CrewAI, LangGraph, and AutoGen agents execute identical logic—deterministic behavior guaranteed. Production-ready Python (67/67 tests), 134/134 stdlib tests passing.

APEX — Agentic Process Executor. Natural language→schema-validated plans→deterministic tool execution. Pure-functional, zero hidden state. Gemini 2.5 Flash, Python 3.11+, SQLite, Pydantic.

🎭 A production-grade multi-agent AI framework for writing professional novels — with persistent memory, automated continuity checking, and a 5-agent editorial pipeline.

Website for the Agent Framework Dev Project - https://agentframework.dev

langgraph graphic design tool

🗣️ AgentRound — 多模型 AI 圆桌讨论框架。让多个 AI 模型围绕同一主题展开多轮辩论，支持并发调用、人类实时介入、智能 Token 裁剪、Rich 终端渲染和 Markdown 导出。兼容任意 OpenAI 兼容 API。

A centralized processing engine that decomposes big problems into sub-problems, builds solutions as composable building blocks, and uses a layered agent ecosystem (Thinker, Planner, Dispatcher, Orchestrator, Critic, Analyst, Judge, etc.) to break down, document, verify, and solve iteratively.

An 🧪 experimental, 🧭Parlant's ARQ (Attentive Reasoning Queries) into 🔷Microsoft Agent Framework via middleware.

Browser-based AI-native chat client built on open standards such as MCP, agent resources, prompts and structured outputs. Client-only runtime with no backend logic, registry or personas. Run agents, tools and workflows via compatible backends with streaming responses and streaming UI rendering.

🚀 V1-MultiAgent: 开源多Agent协作框架技术文章与教程 | 从零构建生产级Multi-Agent系统

SpoonOs Exaspoon monorepo: Unified repository for all ExaSpoon projects including exaspoon_next, exaspoon2, exaspoon-demo, and n8n_pack

An agent operating system where agents are born, sleep, heal, evolve, and die. Local-first, no frameworks, raised by wolves.

Official JSONFIRST community node for n8n — Convert natural language to governed JDON intents

Dynamic AI Agent Framework - Create, orchestrate, and manage AI agents with YAML configs, MCP tool integration, and linear workflow execution using AutoGen and Google Gemini.