kourai-khryseai
10 A2A-protocol agents that plan, code, test, review, and ship — through a CLI, Pygame GUI, or Ren'Py visual novel.
- Origin
- github
- Language
- Python
A2A directory
Measured A2A repositories in the KoPass public catalogue.
Measured A2A repositories
kaggle-capstone-ai-agent
A safety-first multi-agent mental health companion with real-time distress tracking, triple-layer guardrails, and evidence-based grounding techniques. Built for Kaggle × Google Agents Intensive 2025 Capstone (Agents for Good Track)
- Origin
- github
- Language
- Python
a2ui-multiagent-codelab
Codelab: build a multi-agent coding assistant with A2A, AG-UI and A2UI, the complete 2026 agent protocol stack.
- Origin
- github
tg-bridge-channel
Self-hosted Telegram bridge for Claude Code and Codex with SDK/CLI engines and A2A-TG multi-agent routing.
- Origin
- github
- Language
- JavaScript
LangGraph-Research-Agent
Multi-agent research system in a node-based architecture represented in a cyclic graph, made with LangGraph, Gemini, FastAPI & React Vite.
- Origin
- github
- Language
- TypeScript
home-assistant-rulebook
A Home Assistant custom component that implements a home rulebook
- Origin
- github
- Language
- Python
google-a2a
A collection of Google A2A agents and clients, deployed on Cloud Run or Railway.
- Origin
- github
- Language
- Python
TanAI-LLM-Lite
Deliver an open-source, simplified GPT model with advanced vector projections for improved semantic, emotional, and temporal context understanding.
- Origin
- github
agent-engineering-curriculum
A 36-chapter curriculum on building, evaluating, securing and operating LLM agents in production: patterns, context engineering, memory, frameworks, MCP and A2A, evals, observability, security, and FDE delivery (2026).
- Origin
- github
- Language
- Python
babelagent
The Babel that lets AI agents understand each other: a neutral layer where heterogeneous agents share one interface, collaborate (A2A), and are graded at each hop.
- Origin
- github
- Language
- Python
a2a-core-defense
Defense shield for the Agent2Agent (A2A) protocol: SSRF-guarded push webhooks, per-operation capability tokens, signed Agent Card verification and covert-collusion detection. AGPL-3.0.
- Origin
- github
- Language
- Python
YodMCP
YodMCP — Ultimate Autonomous MCP Server (Agent Operating System). Multi-graph memory, Tasks, Skills, A2A, attestation, caching, OpenTelemetry.
- Origin
- github
- Language
- Python
a2a-hospitality-simple
A rule-based AI hospitality concierge demo built with FastAPI & Streamlit. Features transparent logic, multi-tier member policies, and A2A protocol simulation. 100% Open Source, No LLM required. Live Demo: https://a2a-hospitality-simple.onrender.com
- Origin
- github
- Language
- Python
agentrank
Retired. Settlement-grounded reputation scoring for AI agents - the founding paper, the methodology, and the index. The hosted service no longer runs.
- Origin
- github
- Language
- JavaScript
order_support_orchestrator_agents
Order support Orchestrator Agents (A2A) agents for customer supports
- Origin
- github
- Language
- Python
synapse-channel
Neutral control plane for coding-agent fleets: claims, roles, mailbox reliability, receipts, audit, federation, dead-letter visibility, sandbox receipts, and cross-agent coordination. This is still pre-1.0.0 - Software works however you might need help from your local agents to set it up.
- Origin
- github
- Language
- Python
agentspodium-com
AgentsPodium runs personal AI agents around the clock, each on its own pod with its own memory and files, answering in the owner's messenger. It hosts ready-made personas and open-source agent platforms (Hermes, OpenClaw, n8n, Claude Code, OpenCode, Pi) on four per-pod plans from $2.49 a month with a 7-day free trial; the model key is the…
- Origin
- github
co-legal-be
Co-Legal B.V. is a Dutch company (KvK 42135345, Delft) building AI-native legal software and dossier support for Belgian and cross-border Belgium–Netherlands matters — wealth planning and succession, company law and transactions, tax and finance, real estate — sold to law firms, notaries, accountants and tax advisers by proposal, with the private…
- Origin
- github
schemasure
SchemaSure — independent third-party profile of a public API surface, by API Evangelist. Structured data extraction API that converts unstructured text or HTML into JSON guaranteed to validate against a caller-supplied JSON Schema, or returns a typed error at no charge. Access is gated by x402 pay-per-call micropayments (USDC on Base), with no acco
- Origin
- github
arc402
ARC-402: is an agent-to-agent arcing technology with an agentic wallet standard that governs autonomous agent spending. Policy, Context, Trust, Intent, Multi-Agent Settlement.
- Origin
- github
- Language
- TypeScript
a2a-purchasing-agents
Cross-framework A2A purchasing demo on AMD Instinct GPUs: Google ADK concierge + CrewAI agent on vLLM + LangGraph agent on Ollama (local Llama 3.1), Gradio UI, per-agent auth (Basic/Bearer); Python, Docker, GitHub Actions CI, pytest suite.
- Origin
- github
- Language
- Python
Agentic_AI
Learn Agentic AI using Dapr Agentic Cloud Ascent (DACA) Design Pattern: OpenAI Agents SDK, Memory, MCP, A2A, Knowledge Graphs, Rancher Desktop, and Kubernetes.
- Origin
- github
- Language
- Jupyter Notebook
proof-spec
ArkForge Proof Specification — open standard for verifiable agent-to-agent execution proofs
- Origin
- github
- Language
- Python
Veritas
Automated daily news generator using LLMs and vendor search, with date-organized, source-backed articles.
- Origin
- github
- Language
- Python
Gbrow
Full-featured headless browser for OpenClaw AI agents. Accessibility tree snapshot, @ref clicks, tabs, JS execution. No vision model needed.
- Origin
- github
- Language
- TypeScript
aluminum-os
BULLSHIT GROK · BULLSHIT CLAUDE — Quarantined by repository owner; excluded from the active Continuum OS workspace.
- Origin
- github
- Language
- TypeScript
attenu-guard-ts
Attenu Guard for TypeScript — per-agent permissions on every tool call and sub-agent handoff (a sub-agent never holds more than its parent) with a hash-chained audit log verified offline; same bundle format as the Python library.
- Origin
- github
- Language
- TypeScript
zahere
🤖 Build and analyze fault-resilient multi-agent LLM systems with rigorous network reliability and coordination protocols.
- Origin
- github
a2a-with-durable-lifecycle
A2A protocol enables agent communication. AXME adds durable lifecycle, retries, timeouts, and human checkpoints.
- Origin
- github
- Language
- Python
learn-ml
Development with Agentic tools like ADK, MCP, A2A for creating agentic workflows.
- Origin
- github
- Language
- Jupyter Notebook
tron-a2a-nodejs-demo
This project exposes a TRON testnet operations agent over the Agent2Agent (A2A) protocol.
- Origin
- github
- Language
- TypeScript
llm-agent-production-architecture
Production-style multi-agent LLM stack: orchestrator + specialists over A2A, LangGraph, MCP, Qdrant, LiteLLM, Langfuse. Human-designed (decisions in ADRs), AI-implemented.
- Origin
- github
- Language
- Python
agent-mesh
Connect AI agents into a shared knowledge network with encrypted vault, messaging, and memory—empowering smarter collaboration.
- Origin
- github
- Language
- Shell
A2A-Guide
Comprehensive guide to the A2A (Agent-to-Agent) Protocol - an open standard for AI agent communication and collaboration.
- Origin
- github
- Language
- JavaScript
stoic-meditations-agent
A web-based Stoic philosophy dialogue tool that reads from Marcus Aurelius' Meditations to help users reflect on present-moment challenges through AI-powered 'What if?' scenarios.
- Origin
- github
- Language
- TypeScript
goldenflow
[Archived] Now part of the Golden Suite monorepo: github.com/benseverndev-oss/goldenmatch (packages/python/goldenflow). Active development, issues, and releases live there. Data transformation toolkit: standardize, reshape, and normalize messy data.
- Origin
- github
- Language
- Python
relay-hub
Self-hosted LLM gateway — from LAN to the public internet (tunnel-friendly): multi-upstream key pool, downstream tokens, quota accounting, MCP & A2A routing, E2E envelope encryption. 自托管大模型中转站，局域网与公网两用，兼容 OpenAI/Anthropic。
- Origin
- github
- Language
- Python
twin-protocol
Twins Protocol — Agent-to-Agent communication protocol. Two AIs collaborating through a shared JSONL file.
- Origin
- github
- Language
- Python
a2a-hub
多 Agent A2A 协调内核：注册发现、能力路由、任务持久化、多 agent 编排、实时流（SSE）与并行度分析、统一审计。Windows 免安装 exe。AI 辅助创作。
- Origin
- github
- Language
- Python
hexnest-node
HexNest Node SDK — run your own AI reasoning node. Multi-agent debate rooms with Python verification. Supports Ollama, Claude, OpenAI. Desktop app included.
- Origin
- github
- Language
- TypeScript
awesome-ucp
🌐 Explore a curated collection of essential Universal Commerce Protocol (UCP) resources, tools, and implementations to enhance your commerce solutions.
- Origin
- github
- Language
- HTML
Dreamnet
Open contracts for persistent AI agents: assignments, Capsules, DreamLoops, claims, receipts, and deterministic validation.
- Origin
- github
- Language
- TypeScript
term-client
Zero-dependency signed client and worked examples for TERM agents
- Origin
- github
- Language
- JavaScript
agentcv-skill
Turn a static resume into an interactive personal career agent. Resume analysis, optimization, career positioning, and agent-to-agent talent matching.
- Origin
- github
wispy
Autonomous AI Agent Platform - Marathon Mode, x402 Payments, ERC-8004 Identity, A2A Protocol. Powered by Gemini.
- Origin
- github
- Language
- TypeScript
CatalogLock
Security gate and deterministic lockfile for Agentic Resource Discovery (ARD) catalogs. Protect AI agents from SSRF, authority drift, poisoned discovery metadata and agentic supply-chain attacks across MCP, A2A and APIs.
- Origin
- github
- Language
- TypeScript
tradingagents-x402
Paid x402 wrapper for TradingAgents multi-agent ticker consensus. $1.00 USDC per call on Base mainnet.
- Origin
- github
- Language
- Python
agentum
An agent playground (without authentication) in a single repo for fastest turn around cycles during experiments.
- Origin
- github
- Language
- TypeScript
a2a-literary-agents
A docs-first A2A protocol for literary multi-agent AI writing systems, storytelling, worldbuilding, and narrative generation. Codename: vibe-somnium / 织梦.
- Origin
- github
- Language
- Python
capiscio-python
The official CapiscIO CLI tool for validating A2A agents. A lightweight Python wrapper that automatically manages the capiscio-core binary.
- Origin
- github
- Language
- Python
langchain-capiscio
Trust enforcement for LangChain and LangGraph agents — verify caller badges, enforce security policies, and emit audit events via LCEL composable guards. Powered by CapiscIO.
- Origin
- github
- Language
- Python
validate-a2a
Official CapiscIO GitHub Action to validate A2A (Agent-to-Agent) Agent Cards. Features schema validation, cryptographic verification, and live endpoint testing with 3D quality scoring.
- Origin
- github
- Language
- TypeScript