MCP
30 days · UTC
Synchronizing with global intelligence nodes...
Cursor ships Composer 2.5 in-IDE model, nudges teams toward headless agents via its SDK
Cursor released Composer 2.5, a stronger in-IDE coding model that aims to match frontier agents on real repo work. The drop lands only inside the Cur...
CLI coding agents harden: Claude Code stabilizes and resumes long runs; Copilot CLI ships workflow boosts; enterprises eye consolidation
CLI coding agents are maturing fast: Claude Code fixed reliability gaps and added /resume for long runs, while GitHub Copilot CLI shipped notable work...
OpenAI folds ChatGPT, Codex, and the API into one agentic platform under Brockman
OpenAI is merging ChatGPT, Codex, and its developer API into one product org to build a single agentic platform. Reporting says Greg Brockman now lea...
GitHub rolls out Copilot desktop app preview; CLI adds MCP discovery and reproducible setups
GitHub launched a Copilot desktop app preview with agent-driven workflows and tighter MCP integration, backed by fresh Copilot CLI updates. The new [...
OpenCode gets local, persistent memory with a MemPalace plugin
OpenCode gets persistent, local memory via a MemPalace plugin that saves chats and a lightweight knowledge graph. This TypeScript plugin auto-saves e...
Claude Code 2.1.142 gives real CLI control over background agents and removes the hidden 60s MCP cap
Claude Code 2.1.142 makes background agents fully configurable from the CLI and fixes a 60s cap on MCP tool calls. Per the [2.1.142 release](https://...
Copilot CLI 1.0.45: OpenTelemetry spans and an /autopilot switch
GitHub Copilot CLI now emits standard OpenTelemetry spans for agent tool calls and adds an /autopilot mode toggle. The [v1.0.45 release](https://gith...
Claude Code ships Agent View and goal-driven runs for observable coding agents
Claude Code now has an Agent View and a /goal command that make multi-turn coding runs observable and autonomous. The latest release adds an Agent Vi...
The enterprise AI pivot: from buying models to buying the build
Enterprise AI spend is shifting from model selection to governed integration layers that connect agents to real data and workflows. In 48 hours, vend...
Smarter Claude agents are burning 54% more tokens; the fix is backend context, not a bigger model
Smarter Claude models used as backend agents are consuming far more tokens because they must discover missing system context. A benchmarked post repo...
claude-mem goes server-side (and Apache-2.0): open-source agent memory grows up
claude-mem 13 adds an opt-in server runtime with Postgres/Redis and a /v1 API, and switches from AGPL to Apache-2.0. The v13 release lands a Postgres...
Copilot CLI 1.0.44 makes terminal agents more programmable; Copilot billing shift looms
GitHub Copilot CLI 1.0.44 adds hooks that can answer without calling a model, plus better multi-skill commands and shell behavior. The new release of...
MCP agents get safer: OpenAI Agents SDK 0.10.1 validates policies, fixes history loss
OpenAI Agents SDK 0.10.1 tightens MCP agent safety with approval-policy validation and fixes session history loss on compaction errors. The latest [O...
OpenAI shifted defaults: GPT-5.5 Instant rolls out, Agents JS now defaults to gpt-5.4-mini, AWS Bedrock path opens
OpenAI changed defaults across ChatGPT and the Agents SDK this week, which can silently shift behavior and costs if you don’t pin models. ChatGPT now...
HTTP 402 is back: x402 enables pay‑per‑call MCP servers
x402 makes true per-request payments over HTTP 402 practical for MCP servers. A clear walkthrough shows how to put a USDC paywall in front of any MCP...
Production LLM pattern: MCP boundary and runtime RAG fixes
LLM features are converging on an MCP-based boundary with runtime checks that repair RAG answers before users see them. This [AWS design](https://dev...
Airbyte launches an Agents Context Store for AI systems
Airbyte introduced an Agents Context Store to centralize agent memory and retrieved context across pipelines. Airbyte’s new store targets the messy s...
Antigravity Awesome Skills v10.10.0 ships production-audit and context-pruning skills
Antigravity Awesome Skills v10.10.0 ships a production-audit skill and a context-pruning workflow for long-running coding agents. The [v10.10.0 relea...
GitHub Copilot turns on opt‑out training for individual users; CLI adds headless MCP auth as pricing shifts stir backlash
GitHub Copilot will now use interaction data from Free/Pro users for model training by default, while enterprises are excluded. GitHub detailed that ...
MCP goes enterprise: Chrome DevTools, SAS Viya, and Appian wire agents into real systems
MCP is quickly becoming the default interface for AI agents to work against real browsers, apps, and enterprise data. Google’s Chrome team shipped an...
Chrome DevTools ships an MCP server so agents can debug and trace a real browser
Chrome DevTools now exposes a full MCP server so coding agents can drive, debug, and profile a live Chrome session. Google’s new Chrome DevTools for ...
claude-mem 12.4.x: reliability overhaul fixes silent data loss and slashes restart load
claude-mem’s 12.4.x releases quietly fix a months-long queue-drain bug, harden session/migration logic, and remove heavy startup scans. The latest cu...
Codex 0.125 hardens the app-server with Unix sockets, provider discovery, tracing, and permissions
OpenAI shipped Codex 0.125 with enterprise-leaning changes to transport, model discovery, tracing, and permissions. The release adds Unix socket tran...