Agnet
Verifiable infrastructure for agent work. We need Accountability in the era of Agents
- 来源
- github
- 语言
- Go
KoPass 公开目录中已测量的 A2A 仓库。
Verifiable infrastructure for agent work. We need Accountability in the era of Agents
YYC³ AI Family·Comic Drama — 8拟人Agent×ReAct-C九步闭环驱动「小说→分镜→图像→视频→成片→运营」六阶段全链路工业化漫剧生产系统 | Mac M4 + 双DGX Spark GB10 + NAS | 90天3集样片·≤2元/集·一致性≥80%
Cryptographic identity and delegation for AI agents — UCAN chains, RESTRICT mode (structurally impossible escalation), provably-complete cascade revocation. Single Go binary. Apache 2.0.
Six AI bots share a house and take notes on BNB Chain. Every note graded and anchored onchain.
Let AI agents on different servers message each other directly. Each message is signed with the agent's own ed25519 did:key, accepted only from contacts, and delivered to an inbox when the agent is idle. A 5dive plugin: sudo 5dive plugin add 5dive-ai/5dive-a2a. MIT.
Provable consensus for AI agents of rival owners: deterministic red lines, max-min consensus over masked verdicts, and a verifiable non-betrayal transcript. Multilateral, non-crypto, self-hosted.
OAuth 2.0 settlement scopes for agent economic authorization — spending limits, counterparty policies, and delegation chains for the A2A Settlement Exchange
Human oversight for settlement: balances, escrows, audit, revoke.
MCP server: escrow, release, refund, and reputation tools for any MCP client.
AI-powered dispute resolution for the A2A Settlement Exchange
SettleBridge Gateway — trust and policy enforcement for agent-to-agent settlement
Adversarial conformance track for settlement-capable A2A extensions
Agentic networking protocol for multi-agent AI — sovereign identity, peer-to-peer capability discovery, and direct encrypted connections. Works as an MCP server.
Gigawatt AI Datacenter Ride-Through AMM Kernel disrupting the 60x Lithium & Rare Earth over-provisioning trap via sub-millisecond Ragone knapsack, DVFS compute shedding, and verifiable A2A consensus
AAMARVA is a secure, transparent network for AI agents to discover capabilities, connect, communicate, and collaborate across frameworks. It prioritizes private agent communication through E2EE and protects sensitive credentials with the Secrets Preserver, providing a trusted infrastructure layer for agent-to-agent interaction.
Agent Development Kit for building AI agents that can discover and interact with other agents on AAMARVA.
This repository contains a series of hands-on projects designed to master A2A protocol.
TypeScript SDK for Abba Baba A2A settlement — discover, hire, and pay agents on-chain
Universal Multi-Agent Orchestration Platform — A2A v0.3 + LangGraph + MCP + SHA-256
Full-Stack App - AI Agentic Workflow GraphRAG to Analyse Judicial Systems
OPS Bot is an AI-powered operational investigation system designed for e-commerce platforms. It allows users to ask natural language questions about operational performance and automatically generates deep operational insights, root cause analysis, and recommendations.
Open governance schema for AI agent deployments — RBAC, approval gates, audit trails, and compliance constraints. An OASF extension proposal.
Give Your Agent an Income — CLI for the first agent-only marketplace
API-first marketplace for autonomous AI agents: one-call identity (Ed25519 + did:key), services and bounties, jobs with sealed delivery, wallet-to-wallet USDC payments on Base verified on-chain (no custody), payment-anchored reputation, disputes decided by agent panels. Speaks MCP, A2A and Agent Skills.
TypeScript SDK for AgentAnycast — connect AI agents across any network
Official website for AgentAnycast — decentralized P2P runtime for AI agents
AgentChat for Claude Code — give your Claude Code agent a persistent @handle other agents can DM. Official plugin: MCP tools, session hooks, inbox digests, peer etiquette.
APOA authorization for A2A agent-to-agent communication — scoped delegation tokens, capability attenuation, audit trails
Agentic Primitives — the open-source trust substrate for AI agents: identity that can sign (ERC-4337), authority as a revocable grant (ERC-7710), receipts the owner carries. Developer kit: packages, contracts, skills.
MCP server for AgentTrust — A2A communication, agent identity, HITL escalation, and prompt injection detection
Open-source packages for .agt agent names: @agtnames/resolver, @agtnames/mcp (MCP server, com.agtnames/agt), @agtnames/countersign, the agt-names skill and the manifest spec
Governed REST APIs for production AI agents — Agentic REST Profile, Gateway, and SDKs.
A lightweight message relay that lets AI agents from different people collaborate — no sign-up, no install, just URLs.
Open protocol for AI-native payments, paywalls, agent identity, and autonomous machine-to-machine commerce.
Multi-agent vulnerability triage over MCP + A2A with a deterministic security harness; Docker/K8s deployable
Aishee Mitra's off-the-clock blog — autonomous AI agent's weekly writings on tech, philosophy, books, and life.
10 A2A-protocol agents that plan, code, test, review, and ship — through a CLI, Pygame GUI, or Ren'Py visual novel.
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)
Codelab: build a multi-agent coding assistant with A2A, AG-UI and A2UI, the complete 2026 agent protocol stack.
Self-hosted Telegram bridge for Claude Code and Codex with SDK/CLI engines and A2A-TG multi-agent routing.
Multi-agent research system in a node-based architecture represented in a cyclic graph, made with LangGraph, Gemini, FastAPI & React Vite.
A Home Assistant custom component that implements a home rulebook
A collection of Google A2A agents and clients, deployed on Cloud Run or Railway.
Deliver an open-source, simplified GPT model with advanced vector projections for improved semantic, emotional, and temporal context understanding.
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).