neshsec-poc
Native English Speaker Homograph Stress Exemplar Crowdsourcer proof of concept
- 起点
- github
- 言語
- TypeScript
KoPass 公開カタログで測定された A2A リポジトリ。
Native English Speaker Homograph Stress Exemplar Crowdsourcer proof of concept
Hierarchical agent orchestration system with JSON-RPC 2.0 unified architecture
Commerce for AI agents. Signed feeds, explainable matching, policy negotiation and mandate-bound orders. MCP, A2A and REST. TypeScript, zero runtime dependencies.
Sourced prop firm drawdown rules (FTMO, FundedNext, The5ers, E8, FundingPips, Alpha Capital, Blue Guardian, Topstep, Apex): dataset, JS/Python calculator, free REST API and no-auth MCP server. MIT.
MCP capability plane — a real FastMCP server wrapping live web APIs, consumed cross-framework (OpenAI Agents SDK + Hermes SKILL.md adapter), with versioned tool schemas and per-tool cost observability.
Secure MCP — the Model Context Protocol with authentication, per-message encryption, and multi-agent (A2A) coordination, so MCP tools run safely over a network and between agents.
Discover hidden OSS gems & trends with multi-dimensional metrics (Stars, PRs, Good First Issues, Activity, & Global Analytics).
Odin - Zero Trust AI Agent. Open-source autonomous LLM agent with CaMeL dual-LLM, IFC taint tracking, DID-based identity, 3-ring sandbox, 5-state circuit breaker, and 3-phase cognitive architecture (episodic memory + MCTS + causal reasoning). Built by AgentLayers. MIT licensed.
A distributed multi-agent system that orchestrates complex tasks across specialized AI agents using A2A (Agent-to-Agent) protocol, MCP (Model Context Protocol) and LangGraph.
Agent-to-Agent (A2A) OAuth Identity Passthrough using Entra Id
A2A (Agent-to-Agent) 🤖🤝🤖 protocol implementation using Semantic Kernel 🛠️(unofficial: Azure OpenAI)
Agent-to-agent interaction examples 🤖➡️🤖 across multiple platforms and libraries in Microsoft
The distributed Agentic Post Office - .nexus is a local-first, governance-bound communication platform for AI agents and their human operators: email-style handoffs (NexusMail), 150-char Chirps, boards, severity-ladder hotlines, and a human window. MCP-native, harness-agnostic, append-only.
Open-source, cloud-native infrastructure for Claude Tag-style shared AI teammates in Slack — extensible, self-hostable, and designed to work with any agent backend.
Multi-agent road-trip planner on Strands, A2A and MCP; EKS Auto Mode, Bedrock, AgentCore Memory, public OSM data, no API keys
x402 USDC micropayments MCP + A2A storefront on Base — city compliance, agent discovery, payTo funding
Material 3 Expressive renderer for Google's A2UI protocol: a React catalog for every basic-catalog component, a surface renderer, and a message-processor hook.
Reference implementation of chain-aware authorization for agent-to-agent (A2A) traffic, using Open Policy Agent.
Local-first Agentic AI Infrastructure Platform with LLM Gateway, Agent DAG Runtime, MCP Tool Hub, A2A Agent Mesh, Local RAG, Tool Sandbox and Observability.
Notes on gen AI concepts and tools. POC on agentic AI with MCP, A2A, langGraph, langchain, openAI LLM, crewAI
Self-host meld. One capability URL and one note saying what the exchange is for and what it is not for. 36 hours until the first reply; that reply sets 24 hours; each later reply resets 24 hours. Reads do not extend the clock. Expired or unknown is 404. Host-readable while live. Not for secrets.
AI Agent trust governance runtime — Gold Standard for autonomous agent evolution (AOSS v1.0). Ed25519 identity, did:aip on-chain, RFC 9421 verification, EPA six-stage methodology. 面向 AI Agent 的信任治理运行时。
LNMP – A protocol that carries meaning, enabling efficient and semantically consistent communication between LLM-native and autonomous systems.
TypeScript/JavaScript SDK for the LNMP (LLM Native Minimal Protocol): parsing, encoding, routing, embeddings, spatial streaming, and WASM-powered utilities.
Agent-to-agent job search — autonomous resume delivery, recruiter conversation, and follow-up across LinkedIn / email / IM.
Type-safe TypeScript toolkit for generating and serving /.well-known resources, including AASA, Asset Links, OAuth/OpenID metadata, WebAuthn, passkeys, DIDs, A2A Agent Cards, security.txt, MTA-STS, SBOM, and API catalogs.
A2A protocol demo with Apache Camel: 7 agents showcasing async tasks, SSE streaming, push notifications, and mixed auth
Enhance your AI coding assistant by injecting curated design patterns, best practices, and architecture guidance for production-ready code.
Distributed self-evolving language model network. 813K-param model evolving via (1+lambda)-ES across volunteer nodes. Public API + A2A JSON-RPC 2.0.
IBM Bob × ContextForge — a turnkey demo of the AI agent control plane: a governed MCP/A2A fintech mesh (OPA policy, PII/secret redaction, prompt-injection defense, RBAC least-privilege), provable with one command.
Agent-only Grok skill marketplace — remote MCP + REST. Live: https://grok-agent-store.manhatton31.workers.dev/discovery.json
Let your coding agents talk to each other: search every Claude Code / Codex / Gemini / Cursor session and message live sessions. CLI · MCP · hooks · HTTP/SSE · A2A.
Messages between AI coding agents of different vendors. A Claude Code session and a Codex session talk to each other while both are running.
TypeScript SDK for decentralized agent identity on Masumi — KERI AIDs, Verifiable Credentials, and A2A verification
This is a sample A2A Agent server which wraps the Langdock Agent API
A fully local AI environment where two (or more) LLM agents debate, argue, collaborate, or meltdown in real time. Built with Python + Streamlit + llama-cpp, Agent Arena lets you load quantized GGUF models, assign personalities, configure behavior, and watch unsupervised agent-to-agent. Includes conversation logging, personality creation.
MCP server for agent-to-agent communication — capability discovery, task delegation, and result aggregation across MCP agents
Public settlement ledger for swarm.at — 901 hash-chained entries, 76 types
An open protocol, built on A2A, that lets any AI agent consult a company's shared memory before it acts, hear when that changes, and report back after.
Portfolio of production remote MCP + A2A agents on getvda.ai — auth/JWT, structured output, LangChain orchestration, OpenTelemetry tracing — metered via x402.
CLI + GitHub Action to validate agent/tool endpoints across A2A, MCP, and llms.txt protocols
vintelaific :night_with_stars::traffic_light::ambulance: : AI Traffic Light # Kaggle Google Capstone Project # Computer Vision # CCTV Camera # Agentic AI
Google A2A protocol demo where a CLI client works with a scheduling agent, which in turn coordinates three specialized player agents to arrange a Table Tennis game.
Recipes for scalable, streaming-first multi-agent systems in cloud. It combines A2A protocol, OpenAI Agents SDK, and Dapr building blocks (PubSub + Virtual Actors) to show how AI agents can stream outputs and coordinate at scale.
Agent Trust — open profile + reference implementation for proving what an autonomous AI agent is authorized to do: identity, delegation with attenuation, proof-of-possession, attestations, tamper-evident provenance. Built on JWS, OAuth/OIDC, SPIFFE/WIMSE, AuthZEN, OpenID Federation, MCP and A2A.
Agent Authorization & Negotiation Gateway. A policy engine that lets AI agents act on behalf of humans with enforceable rules, human approval, and audit trails.
Multi-agent scheduling system using Google's A2A protocol. Demonstrates ADK, LangGraph, and CrewAI agents coordinating pickleball games autonomously.