A developer on Hacker News is asking whether anyone is using Google's A2A (Agent-to-Agent) protocol, noting that while it was unclear six months ago, the rise of agent-based systems and the MCP protoc…
Signet is building a Session Continuity Protocol to prevent AI coding assistants from losing context when their window limits are hit. The system uses passive checkpoints, agent-initiated digests, and…
Signet is consolidating its fragmented TypeScript recall surfaces into a single canonical explicit recall engine and API, aiming to reduce duplication and preserve metadata. The plan keeps hybridRecal…
Signet is building a CLI bridge to expose installed MCP servers as subcommands and adding usage analytics to track invocations. The new `signet mcp` command group will let operators test tools directl…
A developer shares practical advice for shipping AI agents that survive production, emphasizing that the model is not the bottleneck—state management, crash recovery, and tool integration are. The pos…
C1 launched enterprise-managed authorization (EMA) for the Model Context Protocol (MCP), enabling governed AI agent access to enterprise tools. Anthropic implemented the first EMA support in Claude, w…
A new pattern called the Verified Identity Agent Bridge (VIAB) solves the problem of preserving human identity when bridging consumer AI platforms to enterprise agents. The bridge verifies the human a…
A developer argues that while AI coding tools can generate code quickly, they often fail to understand the hidden contracts and context of real software systems. The developer advises teams to focus o…
A developer released Memharness, an open-source bi-temporal memory primitive for AI agents that stores facts with provenance in a single SQLite file without LLM calls. The tool enables agents to answe…
Researchers introduced Decoupled Search Grounding (DSG), a vendor-agnostic architecture that separates search from reasoning in LLM agents, enabling independent control over retrieval policy, provider…
AlphaAvatar, an open-source and self-hostable realtime full-multimodal personal AI assistant runtime, has been announced. The system integrates voice, text, visual input, face identity, speaker detect…
Recall, a new open-source memory substrate for AI agents, introduces a push-based memory model where agents automatically check, update, and supersede facts without manual queries. The tool runs local…
A developer built a Docker MCP server with 50 tools after finding 11 existing packages fragmented across different licenses and feature sets. The server, which has achieved over 3,042 weekly downloads…
DeusData released Code Intelligence MCP Server, a code intelligence engine that indexes repositories in milliseconds and the Linux kernel in 3 minutes, providing structural queries in under 1ms via a …
AgentGraph released an update introducing four primitives for agent trust: verifiable identity via W3C DIDs, tamper-evident evolution history, third-party security attestation, and social/transitive t…
Vlk, a native MCP server, provides persistent working memory for IDE coding agents by exposing a single tool, vlk_time_travel, that prunes dead memory slots from SQLite and injects learned lessons. Th…
Salvager, a filesystem-level safety net for AI coding agents, automatically saves every file revision to enable recovery from agent-caused damage. The tool runs as a passive watcher with zero configur…
A2UI and MCP Apps combine declarative and custom agentic UIs, offering three architectural patterns for integrating native component rendering with custom iframe embedding. Developers can serve A2UI p…
Vessel Browser, an open-source Chromium-based browser designed for persistent web agents, has been released. It provides durable state, MCP control, and a human-visible supervisory UI for long-running…
Keystone 2.0, an agent harness framework, introduces a new vocabulary with eleven primitive kinds in two layers and a dashboard for observability. The update includes a built-in MCP server, evals with…