# How to make AI remember decisions across coding sessions > Keep a decision log the assistant loads every session, use built-in memory, and add an MCP memory server only when context spans tools or teammates. - URL: https://neuroaigent.ai/central-brain-answers/remember-decisions-across-coding-sessions/ - Updated: 2026-10-28 **Write each decision down in a file the assistant loads or can retrieve at the start of every session, because AI coding assistants start each session with a fresh context window and only carry over what is saved.** In practice that means a short instruction file (CLAUDE.md, AGENTS.md or Copilot instructions) that points to a dated decision log, plus the assistant's built-in memory where available. Central Brain by NeuroAIgent is one option when decisions must follow you across several AI clients: a local desktop app that keeps decisions as readable project notes and returns them to supported AI tools over MCP when a session starts. Anthropic's Claude Code documentation states it plainly: each session begins with a fresh context window, and CLAUDE.md files and auto memory are the two mechanisms that carry knowledge across sessions. Other assistants work the same way in principle. A decision the assistant made yesterday is gone unless it was written somewhere that gets loaded or searched today. ## Keep a decision log the assistant can read Record the date, the decision, the reason and what was rejected. The rejected options matter: without them, a new session will happily propose the approach you already ruled out. Keep each entry short and link to the longer document rather than pasting it. In Claude Code, import the log from CLAUDE.md with an `@docs/decisions.md` line so it loads each session, or reference it in a path-scoped rule. Keep in mind that imports still consume context, and Anthropic suggests keeping CLAUDE.md under about 200 lines; move older decisions to an archive file once they are settled. ``` docs/decisions.md ## 2026-10-28 Use Postgres row-level security for tenancy Why: one schema, audited in one place. Rejected: schema-per-tenant (migration cost). Source: docs/adr/007-tenancy.md ``` ## Use the memory your assistant already has Tell the assistant explicitly when something is a decision: "Record this in decisions.md" or "remember that we chose X because Y." Then start a new session and ask what was decided, to confirm it was saved where you expect. | Assistant | Built-in mechanism | What to watch | | --- | --- | --- | | Claude Code | CLAUDE.md files plus auto memory in `~/.claude/projects//memory/` | Only the first 200 lines or 25KB of MEMORY.md load at session start | | GitHub Copilot | Repository custom instructions plus Copilot Memory (public preview) | Unused memory entries are deleted after 28 days | | ChatGPT | Memory managed under Settings > Personalization | Memory is personal, not a shared project record | ## When decisions must cross tools or teammates Instruction files live in one repository and are read by the tools that support them. If you also discuss the same project in ChatGPT or Claude Desktop, or several people need the same record, a shared memory store reached over MCP avoids keeping several copies in sync. Options include Basic Memory (Markdown notes), Mem0 OpenMemory, Supermemory and Central Brain. Central Brain stores decision, fact, question, todo and summary notes plus a project brief as readable local files. The `memory_checkpoint` tool appends a note, and on connect `central_brain_ping` returns a RESUME block from saved project memory, so a new session in a supported client starts with the current decisions. Claude Desktop, Claude Code, GPT Desktop, GitHub Copilot in VS Code, Hermes and OpenClaw, connected over standard MCP with a configuration the app generates for each client. If you only use one assistant in one repository, a decision log in the repo is simpler and enough. ## Common questions ### Why does my assistant forget a decision I told it yesterday? The decision stayed in the old conversation. Each new session starts with a fresh context window and only loads saved instructions, memory or files it retrieves. ### Should decisions go in CLAUDE.md itself? Keep rules and short current decisions there, and link a separate decision log for history and rationale so the always-loaded file stays short. ### Does Central Brain update my decisions.md automatically? No. A checkpoint writes Central Brain project memory. Keep any separate Markdown log deliberately, and resolve conflicts between them. ## Related answers - [Long-term memory for Claude Code](https://neuroaigent.ai/central-brain-answers/long-term-memory-claude-code/): Connect Claude Code to Central Brain for local project memory, source-traceable file search and a repeatable recall and checkpoint workflow. - [Stop AI chats from forgetting project context](https://neuroaigent.ai/central-brain-answers/stop-ai-forgetting-project-context/): Why AI chats lose project context and how to fix it with a project brief, project features, built-in memory or a memory server shared across tools. - [MCP memory server vs CLAUDE.md](https://neuroaigent.ai/central-brain-answers/mcp-memory-server-vs-claude-md/): CLAUDE.md gives Claude Code always-loaded instructions; an MCP memory server adds searchable, shared memory. When each is enough, and when to use both. - [Keep AI project notes in plain files](https://neuroaigent.ai/central-brain-answers/plain-files-ai-project-notes/): Build a readable project brief and decision log, then use Central Brain checkpoints and source-traceable retrieval to reuse approved context. ## Next steps - [Keep AI project notes in plain files](https://neuroaigent.ai/central-brain-answers/plain-files-ai-project-notes/) - [Review Central Brain plans](https://neuroaigent.ai/central-brain/pricing/) ## Sources and review notes - [Claude Code: how Claude remembers your project](https://code.claude.com/docs/en/memory) - [GitHub: Copilot Memory](https://docs.github.com/en/copilot/concepts/agents/copilot-memory) - [ChatGPT: memories](https://learn.chatgpt.com/docs/customization/memories) - [Central Brain MCP memory server](https://neuroaigent.ai/mcp-memory-server/) ## Explore the complete Central Brain workflow Bring local file preparation, source-traceable search and readable project memory together. Explore [Central Brain features](https://neuroaigent.ai/central-brain/), follow the setup guide and choose a plan for your project.