Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors

mcp gemini openai cursor copilot codex cline ai-agents claude kimi a2a anthropic openai-proxy free-ai qwen ai-gateway deepseek llm-gateway claude-code token-saver

• Updated Nov 12, 2026
• TypeScript

Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.

agents linux-foundation a2a generative-ai a2a-protocol a2a-mcp a2a-server

• Updated Nov 11, 2026
• Shell

Open-source generative UI framework: agents stream layout data, and apps render it with native components in React, Angular, Lit, Flutter, SwiftUI and Jetpack Compose.

react agent angular mcp lit flutter swiftui jetpack-compose a2a llm generative-ui a2ui

• Updated Nov 12, 2026
• TypeScript

Bindu: The identity, communication, and payments layer for AI agents.

machine-learning autonomous-agents a2a agent-communication ai-agent eu-ai-act agent-orchestration

• Updated Sep 6, 2026
• Python

An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

go sdk ai mcp gemini agents multi-agent-systems a2a vertex-ai llm genai multi-agent-collaboration aiagentframework agents-sdk

• Updated Nov 12, 2026
• Go

The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

nodejs cli skills mcp gep a2a agent-framework autonomous-agent ai-agent prompt-engineering llm-agent agent-protocol memory-system self-evolving self-evolution auditable-ai prompt-governance skill-library agent-evolution evomap

• Updated Nov 12, 2026
• JavaScript

The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, and dispute resolution as one open, catch-all Agent Skill / Claude Code plugin.

opencode web3 codex escrow ai-agents dispute-resolution adjudication a2a agent-skills claude-code x402 erc-7710 agentic-commerce claude-skill claude-plugin erc-8004 genlayer openclaw agent-payments hermes-agent

• Updated Oct 26, 2026
• TypeScript

AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x

python open-source ai mcp multi-agent multi-agent-system a2a agent-framework llm llms genai agentic ai-agents-framework aiagents agentic-ai ag2

• Updated Nov 12, 2026
• Python

Platform for building and running AI agents across the full lifecycle — build, test, deploy, monitor, improve. Hosts your agents, runs their tools, and coordinates them over an event mesh, with sessions, artifacts, auth, evaluators, and observability built in.

python go framework mcp multi-agent event-driven workflows agents harness multi-agent-systems solace ai-agents a2a agentic-ai a2a-protocol agent-mesh

• Updated Nov 5, 2026
• Shell

Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator

agent ai runtime mcp gemini openai k8s acp claude a2a chatgpt chatgpt-api deepseek mcp-servers mcp-server mcp-client mcp-tools mcp-host mcp-gateway a2a-mcp

• Updated Nov 12, 2026
• TypeScript

Learn Agentic AI using Dapr Agentic Cloud Ascent (DACA) Design Pattern and Agent-Native Cloud Technologies: OpenAI Agents SDK, Memory, MCP, A2A, Knowledge Graphs, Dapr, Rancher Desktop, and Kubernetes.

docker kubernetes redis kafka rabbitmq mcp openai postgresql-database serverless-containers a2a dapr dapr-pub-sub dapr-service-invocation openai-api dapr-sidecar rancher-desktop dapr-workflow langmem agentic-ai openai-agents-sdk

• Updated Oct 26, 2025
• Jupyter Notebook

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

python agent cli skills mcp tui acp a2a agent-framework mcp-server mcp-client agent-skills

• Updated Nov 10, 2026
• Python

Portable AI agent runtime for the JVM. One @agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human approvals, and governance over WebSocket, SSE, gRPC, or WebTransport/HTTP3. Speaks MCP, A2A, and AG-UI.

java spring-boot mcp websocket sse event-driven multiagent acp ai-agents rag quarkus a2a llm anthropic langchain4j spring-ai crewai agentic-ai koog embabel

• Updated Nov 12, 2026
• Java

Sprix AI at 屿智同行 — state-aware SELF/COLLABORATE/HANDOFF routing for A2A agent networks.

python multi-agent-systems ai-agents task-scheduling a2a agent-routing agent-orchestration sprix-ai

• Updated Aug 28, 2026
• Python

Official Python SDK for the Agent2Agent (A2A) Protocol

agents a2a generative-ai agent2agent a2a-protocol a2a-mcp a2a-server a2a-client

• Updated Nov 12, 2026
• Python

A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.

go agent golang ai mcp evaluation multi-agent observability ai-agents rag opentelemetry a2a agent-framework llm model-context-protocol a2a-protocol ag-ui graph-workflows

• Updated Nov 12, 2026
• Go

Samples using the Agent2Agent (A2A) Protocol

agents a2a generative-ai a2a-protocol a2a-mcp a2a-server a2a-client

• Updated Nov 8, 2026
• Jupyter Notebook

Build agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans in control. Deploy Heym on your own infrastructure.

automation mcp self-hosted workflow-automation no-code human-in-the-loop ai-agents rag a2a ai-assistant evals ai-agents-framework agentic-ai mcp-servers mcp-server no-code-automation coding-agent a2a-mcp a2a-server mcp-tool

• Updated Nov 11, 2026
• Python

A single interface to use and evaluate different agent frameworks

ai mcp agents a2a agent-evaluation

• Updated Nov 1, 2026
• Python

Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform

benchmark mcp evaluation verification nautilus long-term-memory rag local-first a2a llm llm-as-judge agentic-ai memory-layer agent-memory claude-code cross-agent

• Updated Nov 11, 2026
• Python