MCP, ACP and A2A: connecting AI agents
Compare MCP, ACP and A2A through practical cases: when to connect tools, embed coding agents in editors, or communicate between independent services.
13 articles found
Compare MCP, ACP and A2A through practical cases: when to connect tools, embed coding agents in editors, or communicate between independent services.
Connect Claude Desktop to OpenCode with local MCP servers and extensions. Compare permissions, remote connectors, security, sessions, and architecture.
Understand MCP support for ChatGPT and OpenCode, including web versus desktop limitations, OpenRouter architecture, permissions, and agent sessions.
Explore how Graphicle combines a code graph, documentation and agent memory; examine its architecture, privacy, benchmarks and closest alternatives.
A curated map of the OpenCode ecosystem in 2026: 10 persistent-memory plugins no blog has shown you, 4 real Hacker News critiques, and the indie community's defensive response.
Honest technical deep dive into the persistent memory stack I combine daily in my projects: opencode-supermemory for auto-compact, basic-memory as main memory with Markdown + graph, and forgetful as procedural skills layer. With real configuration examples for Claude Code, Codex,
Comparative technical analysis of three native OpenCode plugins to give your AI agent persistent local memory: simple-memory (logfmt), Mnemosyne (offline Go binary), and true-mem (cognitive psychology).
Exhaustive technical comparison of three cross-platform MCP servers to give AI agents persistent memory: opencode-supermemory (cloud), basic-memory (Markdown + graph), and forgetful (atomic Zettelkasten). Works with Claude Code, Codex, Cursor and more.
Deep dive into Headroom, the open-source project (33.4k ⭐) that promises 60-95% token reduction on what you send to an LLM without losing accuracy. We test its 6 algorithms, its reversible CCR, and its proxy mode, and compare it to the rest of the ecosystem.
OpenClaw for ready-to-use agents, Vercel AI SDK with Next.js for custom development, OpenAI and Claude models, MCPs for integrations, and Cursor/Claude Code for programming. Complete analysis with practical examples and cost considerations.
A technical deep-dive into hmem (Humanlike Memory), an MCP server that models human memory in five lazy-loaded levels backed by SQLite + FTS5. How Fibonacci decay, logarithmic aging, and a curator agent solve the context window problem across sessions and machines.
A deep dive into using the PARA method (Projects, Areas, Resources, Archives) as a cognitive scaffold for AI agent memory. How Markdown files, Obsidian, and Logseq via MCP create transparent, human-editable memory systems that actually persist.
Autocomplete is a thing of the past. Discover how AI Agents like Cline and Cursor are redefining software development, allowing for multi-file editing and autonomous command execution.