# AI use cases for AI Memory (akitaonrails/ai-memory) Repo: [akitaonrails/ai-memory](https://github.com/akitaonrails/ai-memory) | Use cases: 4 | Page: https://dedupedai.com/use-cases/akitaonrails-ai-memory/ ai-memory is a Rust tool that gives AI coding agents a shared long-term memory, stored as a git-backed markdown wiki, so work can be handed off between agent CLIs and machines. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Hand off a half-finished task from Claude Code to Codex: https://dedupedai.com/use-cases/akitaonrails-ai-memory/hand-off-task-between-claude-code-and-codex/ - Resume a project on another machine with the same memory: https://dedupedai.com/use-cases/akitaonrails-ai-memory/keep-project-memory-in-sync-across-machines/ - Share project knowledge across a team on one server: https://dedupedai.com/use-cases/akitaonrails-ai-memory/share-project-knowledge-with-a-small-team/ - Read and edit agent memory as plain markdown files: https://dedupedai.com/use-cases/akitaonrails-ai-memory/browse-and-edit-agent-memory-as-plain-files/ ## How to hand off a half-finished task from Claude Code to Codex with AI Memory Repo: [akitaonrails/ai-memory](https://github.com/akitaonrails/ai-memory) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Quit one coding agent mid-task and resume in another in the same directory with the open questions intact. **Who it is for:** A developer partway through a feature in Claude Code who needs to continue in OpenAI Codex, for example after hitting a usage limit or wanting a second agent's view. **The problem:** Each agent starts cold, so the architecture, failed approaches, and open questions must be re-explained by hand. **The outcome:** Codex starts in the same directory with a handoff that states where the work stopped, what failed, and what is still open. ### Steps 1. Run `curl -fsSL https://github.com/akitaonrails/ai-memory/releases/latest/download/install.sh | sh` 2. Run `ai-memory setup` 3. Quit Claude Code in the project directory 4. Run `ai-memory run codex` from the same directory ### Prompt to paste into your agent ```text Using the ai-memory repo (github.com/akitaonrails/ai-memory), set up the tool, then start in the project at through `ai-memory run`. Expected output: the new agent begins with a brief that lists the last session's status, failed approaches, and open questions. Verify the brief mentions the open questions from the previous session before continuing. ``` ### Caveat The README says AI Memory run gives Codex a private local projection of Claude's visible native history, so check what each agent can see before relying on it for sensitive work. Risk, remote script: The install command pipes a script from GitHub directly into sh, so review it first if you do not trust the source. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/akitaonrails-ai-memory/hand-off-task-between-claude-code-and-codex/ ## How to resume a project on another machine with the same memory with AI Memory Repo: [akitaonrails/ai-memory](https://github.com/akitaonrails/ai-memory) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Run memory on a server you control so a project started on a desktop continues on a laptop. **Who it is for:** A developer who works on the same repository from a desktop, a laptop, and a homelab box and loses context when switching. **The problem:** Agent notes stay on one machine, so the open questions from the desktop session are missing on the laptop. **The outcome:** The laptop agent retrieves the same project knowledge and open questions recorded on the desktop. ### Steps 1. Run `curl -fsSL https://github.com/akitaonrails/ai-memory/releases/latest/download/install.sh | sh` on the server and on each machine 2. Run `ai-memory setup` on each machine and point it at your server 3. Work on the project on the first machine until a session ends 4. On the second machine, start the agent in the same project and check that the brief lists the earlier open questions ### Prompt to paste into your agent ```text Using the ai-memory repo (github.com/akitaonrails/ai-memory), configure a second machine to use the memory server at . Expected output: the agent on the second machine shows knowledge from sessions recorded on the first machine. Verify by asking for the open questions of the project and confirming they match the first machine. ``` ### Caveat The README describes the server setup in general terms only, so the exact configuration for a remote server is not covered in the README excerpt and needs the docs. Risk, credentials: Setup creates a bearer token for the server, so keep that token file owner-only and do not share it between people. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/akitaonrails-ai-memory/keep-project-memory-in-sync-across-machines/ ## How to share project knowledge across a team on one server with AI Memory Repo: [akitaonrails/ai-memory](https://github.com/akitaonrails/ai-memory) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README Point the whole team at one AI Memory server so each person's agents can retrieve shared project notes. **Who it is for:** A team lead running a small shared codebase who wants every developer's agent to learn from the same project knowledge. **The problem:** Each developer's agent learns in isolation, so the same architecture and failed approaches are rediscovered by each person. **The outcome:** Project knowledge is shared per project, while personal handoffs stay personal, and each person's activity is attributed in an audit log. ### Steps 1. Run `curl -fsSL https://github.com/akitaonrails/ai-memory/releases/latest/download/install.sh | sh` on the server host 2. Run `ai-memory setup` on the server host 3. Have each team member run `ai-memory setup` on their own machine and connect to the shared server 4. Use the management console, built with the management-ui feature and started with --enable-management-ui, to create personal MCP API keys for each person (inferred, check the README) ### Prompt to paste into your agent ```text Using the ai-memory repo (github.com/akitaonrails/ai-memory), set up a shared memory server for and create one personal key per member. Expected output: each member's agent can search the shared project pages. Verify by searching for a known project fact from a second member's account. ``` ### Caveat The README says the management console needs a compile-time feature and a runtime flag, and the exact build and start commands are only partly shown, so read docs/management-ui.md before deploying. Risk, credentials: Each team member gets a personal MCP API key, so revoke keys for people who leave the team. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/akitaonrails-ai-memory/share-project-knowledge-with-a-small-team/ ## How to read and edit agent memory as plain markdown files with AI Memory Repo: [akitaonrails/ai-memory](https://github.com/akitaonrails/ai-memory) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Open the project's memory wiki in any text editor or Obsidian and correct it by hand. **Who it is for:** A developer who wants to audit, correct, or back up what their agents have learned about a project. **The problem:** Agent memory is often stored in opaque databases, so it is hard to inspect or fix when it is wrong. **The outcome:** The developer reads, greps, and edits ordinary .md files that hold the project's memory, and the change is picked up by the index. ### Steps 1. Run `curl -fsSL https://github.com/akitaonrails/ai-memory/releases/latest/download/install.sh | sh` 2. Run `ai-memory setup` 3. Locate the git-backed wiki of markdown pages for your project 4. Open the folder in Obsidian or any editor, correct a page, and save it ### Prompt to paste into your agent ```text Using the ai-memory repo (github.com/akitaonrails/ai-memory), locate the markdown wiki for the project at . Expected output: a list of .md page files that hold the project memory. Verify by opening one page and confirming its content matches a recent session summary. ``` ### Caveat The README says the database is a derived index, so edits to pages are the real source of truth, but the README does not say how the index refreshes after a manual edit. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/akitaonrails-ai-memory/browse-and-edit-agent-memory-as-plain-files/