翻訳待ち：OpenContext – Persistent, project-local memory for AI coding agents via MCP

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。

MCPSTRICT TYPESCRIPTZERO-CONFIG Persistent, Project-Local Memory for AI Coding Agents Coding agents forget decisions between sessions. OpenContext MCP exposes a lightweight Model Context Protocol server that enables AI agents to read and write durable .opencontext/ markdown rules. $ View on GitHub project / .opencontext tree.opencontext .opencontext/ ├── architecture.md ├── api-contracts.md └── coding_rules.md previewarchitecture.md 01# Architecture 02 03## Authentication 04 05We use JWT with refresh tokens. 06 07### Access Token 08- 15-minute expiry 09- Stored in memory only 10 11### Refresh Token 12- 7-day expiry 13- HttpOnly secure cookie 14- Rotated on each use Without vs. With OpenContext AI agents are powerful — but only if they remember what matters. Without Memory Session context vanishes Agents lose all memory of prior decisions, conventions, and architecture between sessions. Architectural rules get broken Without persistent rules, agents re-implement patterns that conflict with your codebase. Agents re-ask conventions "Should I use Zod or Yup?" — the same question, every session, no memory of past answers. With OpenContext Plain .md storage in your repo Plain markdown files that persist across every session. Agents read before acting. Zero cloud or account lock-in Open any .opencontext/ file in your editor. Human-readable, machine-readable, no magic. Team-wide alignment via Git Commit shared rules to your repo, or .gitignore for private local context. Your choice. Get Started in 3 Steps Go from zero-install setup to a codebase with durable, searchable memory in one guided workflow. Step 01 Add OpenContext to your MCP Client Add the OpenContext MCP entry to your client configuration. No global install is required. Your client launches the server via npx over stdio. Core command ["npx", "-y", "opencontext-mcp"] Config path opencode.json / project MCP settings Transport: stdio OpenCode config { "mcp": { "opencontext": { "type": "local", "command": ["npx", "-y", "opencontext-mcp"], "enabled": true } } } Two Lightweight MCP Tools Minimal surface area. Maximum utility. Every tool your agent needs. save_context Persists a markdown context entry under .opencontext/ with the given topic name. Auto-creates the directory if it doesn't exist. Overwrites existing files with the same topic name. topicstring Topic name used as the filename. Use kebab-case or snake_case (e.g. "architecture" creates architecture.md). contentstring Full markdown content to write. Supports headers, lists, code blocks, and all standard markdown. File is overwritten on each call. Latest state always wins. read_context Reads a specific topic file or discovers all available topics when called without arguments. Returns raw markdown content. topicstring (optional) Topic name to retrieve. Omit entirely to list all available topic filenames. Returns markdown string or array of topic names. Agent Workflows & Ready Prompts OpenContext becomes useful when your agents are explicitly told when to read and write durable memory. Drop these prompts into your planning and implementation workflows. universal-system-instruction.txt Always use read_context before modifying code. Use save_context when establishing durable rules or API contracts. Git Strategy Choose whether OpenContext becomes shared project memory or a purely local working layer. Shared Team Memory git add .opencontext Commit plain markdown rules to the repository so architecture decisions, API contracts, and coding conventions stay visible to the whole team and can be reviewed in CI. Local Private Notes .opencontext/ Keep scratchpads, debugging notes, and developer-specific rules local by adding the directory to .gitignore. The workflow stays transparent without sharing personal context.