The Agentic AI Foundation is developing a standards stack built around three protocols — MCP for tool discovery and invocation, A2A for agent-to-agent authentication, message routing and state synchro…
ContextIQ proposed an audit packet for enterprises to record when an AI agent spends money, covering agent identity, accountable owner, delegated authority, approval, endpoint findings, transaction id…
Sierra and Meta announced the Personal Agent Protocol (PAP) on October 6, 2026, a third protocol layer for AI agent infrastructure that adds OAuth-based identity and authentication governance on top o…
A developer comparison explains that LangChain provides high-level components and a ready-made agent loop, while LangGraph is the low-level orchestration runtime for stateful, controllable workflows, …
Connector, an open-source control plane for AI agents from the GitHub project GlobalSushrut/connector-oss, gives every agent an identity, explicit authority, per-action admission, runtime enforcement,…
Metagente, a declarative language for building AI agents from developer Cleuton Sampaio, has shipped its interpreter as a single Rust binary that natively speaks MCP (Model Context Protocol) and A2A (…
IBM's open-source ContextForge gateway and registry, which federates MCP, A2A and REST/gRPC APIs behind a single governed endpoint, has been updated as of October 2026 and holds 4.6k GitHub stars. The…
A developer tool called X402 Inspector launched on Hacker News to validate x402 payment challenges on paid API endpoints, checking the HTTP 402 response shape, USDC amount encoding, and Base, Base Sep…
A team building an MCP gateway measured 73 MCP-related search phrases using paid keyword data, finding they total 42,270 monthly searches, with the top three phrases ("model context protocol," "mcp pr…
The Agent Communication Protocol (ACP) has been folded into A2A under the Linux Foundation, with a migration guide published for the BeeAI platform. ACP is an open protocol for agent interoperability …
Morgan Stanley has deployed over 110 APIs in production using Architecture as Code and is rethinking its API program around MCP, the open protocol for connecting LLM-based applications to tools and da…
AgentScope 2.0, an open-source Python agent framework with 32,000 GitHub stars, has added model routing, realtime voice agents across several providers' realtime APIs, A2A protocol support and MCP, pl…
A developer published a walkthrough for giving an MCP server a resolvable .agt identity on Polygon, letting any MCP-compatible client look up an agent's endpoint, capabilities and pricing model from a…
A developer has built a pre-LLM gating layer in .NET that scores individual A2A agent skills against a user request using TypeSafe's System One (Jev) classification API, exposing only the winning skil…
The Agentic AI Foundation (AAIF) introduced a sandbox phase in its project lifecycle, announced at its AGNTCon Europe event in Amsterdam, to admit open source agentic AI projects that lack significant…
A position paper posted to arXiv (2609.19203v1) argues that compound agentic AI systems need a Foundation Model Operating System (FMOS), a system layer that virtualizes foundation model interactions t…
A new namespace called .agt launched registration today, minting agent names as NFTs on Polygon so that a single lookup returns an agent's owner, per-protocol endpoints, signing keys, payment address,…
Agent Protocol Inspector reports a three-state result — not_detected, indicated, or confirmed — for each MCP and A2A protocol it scans, requiring servers to pass specific per-protocol checks rather th…
Agent Protocol Inspector generates a structured IGA Review Packet from MCP and A2A agent scans, producing a recommended decision, risk breakdown, reviewer and owner questions, and export formats for O…
ContextIQ published a curl-based tutorial for its Agent Protocol Inspector API, covering three API-key-authenticated endpoints for scanning MCP or A2A targets, retrieving a stored scan by scanId, and …