MCP & Agent Protocols
50 entriesOpen protocols and standards for tool integration, agent-to-agent communication, and interoperable AI systems.
ADK-Rust
assessA community-built Rust framework for constructing LLM-powered AI agents with multi-provider support, inspired by Google'...
Agent Communication Protocol (ACP)
holdIBM Research's REST-based open protocol for AI agent interoperability, enabling agents built on different frameworks to...
Agent Skills Specification
adoptAn open standard for packaging reusable procedural knowledge as markdown files that AI coding agents can discover, load,...
Agent Swarm
assessOpen-source TypeScript/Bun multi-agent orchestration framework by desplega.ai with lead/worker Docker isolation, session...
Agent2Agent Protocol (A2A)
assessAn open standard by Google for AI agent-to-agent interoperability, enabling capability discovery and task exchange over...
Agentic AI Foundation (AAIF)
assessLinux Foundation governance body for AI agent infrastructure, hosting MCP, Goose, and AGENTS.md under vendor-neutral ope...
AGENTS.md
trialAn open cross-platform specification for a repository-root Markdown file that provides AI coding agents with project con...
AgentScope Runtime
assessPython FastAPI-based agent deployment runtime by Alibaba's Tongyi Lab with five sandbox types, Agent-as-a-Service stream...
Agno
assessOpen-source Python framework, stateless FastAPI runtime (AgentOS), and control-plane UI for building and operating multi...
AIO Sandbox
assessAn all-in-one Docker container bundling browser, shell, filesystem, VSCode Server, Jupyter, and MCP server into a single...
Amazon Bedrock AgentCore
assessAWS's fully managed platform for building, deploying, and operating production AI agents at scale, integrating sandboxed...
ArcKit
assessA toolkit of 67 AI-assisted slash commands for enterprise architecture governance, vendor procurement, and design review...
Arrakis
assessSelf-hosted open-source sandbox platform using Cloud Hypervisor microVMs for secure AI agent code execution with native...
Augment Code
trialAI coding agent platform for professional software teams, built around a proprietary Context Engine that semantically in...
BeeAI Framework
assessIBM Research's open-source Python and TypeScript framework for building production-grade multi-agent AI systems, hosted...
Claude Code
trialAnthropic's terminal-based AI coding agent with file access, command execution, layered memory, and MCP integration.
Claude Flow (Ruflo)
assessOpen-source multi-agent orchestration framework for Claude that deploys coordinated swarms of specialized AI agents with...
Cline
trialOpen-source VS Code extension providing an autonomous AI coding agent with a Plan/Act workflow, multi-provider LLM suppo...
Codex CLI
trialOpenAI's open-source terminal AI coding agent with OS-level sandboxing, subagent delegation, and AGENTS.md support.
Cognithor
assessPre-v1.0 Python agent operating system by a solo developer running local-first on Ollama or LM Studio, featuring a Plann...
Contentful
assessHeadless CMS providing structured content management and delivery via REST and GraphQL APIs for multi-channel publishing...
DeerFlow
assessA ByteDance SuperAgent harness that orchestrates specialized sub-agents for long-running tasks like deep research, code...
Dify
assessAn open-source platform for building LLM-powered applications via a visual drag-and-drop workflow builder with built-in...
FetchCoder
assessClosed-source terminal coding agent by Fetch.ai, powered by ASI1 LLM, with built-in Agentverse MCP integration for deplo...
ForgeCode
assessOpen-source Rust-based terminal AI coding agent with three specialized built-in agents, a skills framework, ZSH plugin i...
Gemini CLI
assessGoogle's open-source terminal AI coding agent using Gemini models with a ReAct loop, 1M token context, and a generous fr...
GitNexus
assessOpen-source code intelligence engine that indexes repositories into a precomputed knowledge graph and exposes 16 MCP too...
Google Agent Development Kit (ADK)
assessGoogle's official code-first Python framework for building, evaluating, and deploying AI agents, optimized for Gemini bu...
Goose
trialAn open-source, MCP-native on-machine AI agent by Block that autonomously executes multi-step development workflows with...
gptme
trialPersonal AI agent CLI that gives LLMs direct access to the terminal, file system, browser, and desktop. Provider-agnosti...
Langflow
assessA visual IDE for building AI agents and RAG applications with native LangGraph integration for stateful multi-agent work...
Leash by StrongDM
assessContainer-based sandbox that monitors AI agent syscalls via eBPF and enforces access policies written in Cedar.
LibreChat
trialA self-hosted AI chat platform providing a unified ChatGPT-like interface for multiple LLM providers with MCP integratio...
llms.txt
assessA community-proposed web standard placing a structured Markdown index file at /llms.txt on a website to help AI language...
MemPalace
assessLocal-first open-source AI memory system using a hierarchical palace metaphor (Wings/Rooms/Halls) over ChromaDB vector s...
Mistral Vibe
assessMistral AI's open-source Python CLI coding agent with conversational codebase interaction, configurable approval profile...
Model Context Protocol (MCP)
trialAn open standard by Anthropic that defines how AI assistants connect to external tools, data sources, and services via a...
Neovate Code
trialOpen-source CLI coding agent from Ant Group with a Vite-style plugin architecture, 30+ LLM providers, MCP integration, s...
Nori CLI
assessOpen-source Rust-built TUI that unifies Claude, Gemini, and Codex under a single terminal interface via Zed Industries'...
Open WebUI
trialA self-hosted, provider-agnostic web interface for LLMs with built-in RAG, MCP support, RBAC, and Ollama integration for...
OpenCode
assessAn open-source AI coding agent with a terminal UI, desktop apps, and IDE extensions, connecting to 75+ LLM providers via...
Persistent Agent Identity
assessPattern of giving AI agents durable, self-editing identity files (persona, expertise, tool knowledge, and notes) that ev...
Portkey AI
assessEnterprise AI gateway for routing LLM requests to 250+ providers with failover, caching, guardrails, and cost management...
RAGFlow
assessOpen-source Apache-2.0 RAG engine by InfiniFlow specializing in deep document understanding (OCR, layout analysis, table...
Salesforce
assessEnterprise CRM and cloud platform company, whose April 2026 Headless 360 initiative exposes its entire platform as APIs,...
Skills.sh
assessVercel's directory and CLI for discovering and installing reusable SKILL.md packages across 40+ AI coding agents.
Superblocks
assessEnterprise low-code platform for building governed internal applications using AI — Clark AI agent generates React apps...
Thunderbolt
assessOpen-source, self-hosted enterprise AI client by MZLA Technologies (Mozilla) offering multi-platform native apps, multi-...
Weaviate Engram
assessMemory and context layer for AI agents built on Weaviate, organizing persistent semantic memory by topic across sessions...
zindex
assessManaged diagram infrastructure for AI agents, providing a proprietary Diagram Scene Protocol (DSP), Sugiyama-based layou...
Related Reviews
Optimizely Vendor Analysis: Digital Experience Platform for Experimentation, CMS, and Commerce
Optimizely (vendor homepage) · Apr 24, 2026
Agent Communication Protocol (ACP) — Welcome & Introduction
IBM Research / BeeAI Team (no individual byline) · Apr 23, 2026
Collaborator AI: Infinite Canvas Agentic Development Environment
Unknown · Apr 23, 2026
Agents CLI in Agent Platform: create to production in one CLI
Ivan Cheung, Pier Paolo Ippolito, Elia Secchi · Apr 23, 2026
The AI Engineering Stack We Built Internally — On the Platform We Ship
Ayush Thakur, Scott Roe-Meschke, Rajesh Bhatia · Apr 22, 2026