MCP

11 min read

OpenCode is the fastest-growing open-source AI coding agent - 160K GitHub stars, 7.5M monthly users, 75+ model providers. Here is how to set it up, configure models, and use it effectively in your workflow.

Chrome 149 ships an origin trial for WebMCP - a proposed web standard that lets developers expose JavaScript functions and HTML forms to AI agents. Here is what it does, how to implement it, and why it matters for the future of agentic browsing.

Headroom is a context compression layer that intercepts your AI agent's tool outputs and strips 60-95% of the tokens before they hit the model - with benchmarked accuracy preserved.

Headroom is an open-source context compression tool that reduces tokens sent to LLMs by 60-95%, available as a Python library, proxy server, or MCP server - with no code changes required.

8 min read

Before an AI agent gets tools, files, APIs, MCP servers, or deployment access, decide what it can read, write, call, log, and roll back.

8 min read

Prompt injection stops being an abstract LLM risk once an agent can call tools. The practical defense is data boundaries, structured handoffs, tool guardrails, and approval gates around side effects.

7 min read

Anthropic's knowledge-work plugin repo is trending because it packages skills, connectors, slash commands, and sub-agents around job functions. The interesting shift is from personal prompts to team-distributed operating systems.

CodeGraph builds a local SQLite index of your codebase so Claude Code, Cursor, and Codex CLI spend far fewer tokens exploring files - trending on GitHub with 12k stars and real benchmark numbers.

CodeGraph hit 7,800+ stars with 1,900 added in a single day - a local MCP knowledge graph that lets Claude Code explore codebases with drastically fewer API calls.

8 min read

Anthropic's Stainless acquisition is not just an SDK deal. It is a bet that agents need generated SDKs, CLIs, docs, and MCP servers from the same source of truth.

agentmemory is a self-hosted MCP server that gives Claude Code, Cursor, and Gemini CLI searchable long-term memory across sessions - with 12 auto-capture hooks and 51 tools, no external database required.

agentmemory gives AI coding agents a persistent brain - capturing session context automatically via 12 Claude Code hooks and 51 MCP tools, with 95.2% retrieval accuracy and 92% token savings over context-pasting.