Persistent memory for AI coding sessions. Captures decisions, gotchas, and context — the stuff that lives in your head, not your codebase.
Works with your AI coding tools
infernoflow runs silently in the background, capturing what your AI can't infer from code alone. Local-first, zero network calls.
Log decisions, gotchas, and in-progress work. When you start a new session, your AI loads the full context automatically.
Your AI agent calls amp_write directly through MCP — gotchas, decisions, and failed attempts get logged as you work, no copy-paste required. Optional git hook for commit messages too.
Run infernoflow switch to generate a full handoff — open threads, git activity, session duration, and next steps.
Memory stored in .ai-memory/sessions.jsonl using the AI Memory Protocol — vendor-neutral, MIT-licensed. Any AMP-compatible tool can read it. No lock-in.
Memory routes into .ai-memory/branches/<branch>.jsonl — travels with git. Switch branches, your AI sees the right context. Teammates inherit memory by checking out your branch.
Ships with MCP tools your AI calls automatically: amp_write, amp_read, amp_search, amp_handoff, amp_health, plus four infernoflow_* helpers. Zero configuration.
Three commands and your AI has persistent memory for every project.
Run npm install -g infernoflow once. Works on Node 18+.
Run infernoflow init in your project root. Creates .ai-memory/, wires the MCP server into Claude Code / Cursor / VS Code Copilot in one command, and generates the rule files (CLAUDE.md / .cursorrules / copilot-instructions.md) your AI reads automatically.
Run infernoflow log "decided to use Zustand over Redux" to capture decisions. Git hooks capture commit context automatically. Your AI reads it all on the next session start.
Run infernoflow switch to generate a rich handoff. Open threads, git activity, session duration, IDE — everything the next session needs to hit the ground running.