whereismyai
Turnbook
Turnbook is a local memory tool for AI agents that stores conversations on user hardware without spending model tokens.
Turnbook provides local long-term memory for AI agents, operating entirely on the user computer without calling an LLM to save data. It records conversations word for word from supported terminal and desktop apps, creating a shared memory pool across different models and sessions. The software uses a multilingual embedding model and word search to retrieve relevant past turns when agents need context. It supports English and Korean languages, masks secrets before storage, and allows folder sharing or file exports for team collaboration. Users install it via pip or setup scripts to connect clients like Claude Code, Codex CLI, Cursor, and Copilot CLI.
Turnbook at a glance
Key features
- Stores every conversation turn locally
- Shares memory across multiple AI apps and models
- Performs local multilingual embedding search
- Masks sensitive secrets before saving data
- Supports memory export and import as files
- Enables encrypted folder sharing across PCs
Use it for
- Sharing project decisions across different AI coding agents
- Retrieving past context and implementation details across sessions
- Managing local long-term memory without cloud services
- Collaborating on project progress across teammate AIs
Alternatives to Turnbook
- AI Memory — Shared memory for coding agents that works across machines and team members.
- Alook — Connects existing local coding agents to team communication channels.
- OpenViking — Unifies agent memory, knowledge RAG, and skills into a single directory structure.
- Engram — Single Go binary with zero dependencies and built-in full-text search.
- Agent Beacon — Retains coding agent knowledge across tools so errors do not repeat.
- Memori — Reduces LLM token usage and spend by over 97% with targeted recall.
- IAI Memory Engine — Provides persistent, local, and encrypted memory for AI agents without APIs.
- Tigerless Agent Memory — Maintains agent history in portable, greppable Markdown files without API keys.
- MuscleMemory — It cuts input tokens, tool calls, and execution time while maintaining task success.
- oMLX — It uses paged SSD KV caching to reduce agent TTFT to under 5 seconds.
- claude-mem — It shares persistent, searchable agent memory across sessions and devices.
- Memorax Code — Carry project architecture and verified engineering decisions across coding sessions.
All Turnbook alternatives