You can now make Claude Code, Gemini CLI, and other coding agents...

You can now make Claude Code, Gemini CLI, and other coding agents 10x more powerful by giving them long‑term memory!

It just takes a single line of code.

Here’s a step‑by‑step breakdown (100% local):

Coding agents have a major limitation: they forget everything between sessions.

Without memory, they can’t retain project context, past fixes, or key decisions.

What they need is a persistent memory layer to store and recall context.

Let’s see how to set that up.

We’ll use Cipher, an open‑source memory layer for coding agents.

You can run Cipher as an MCP server so coding agents like Claude Code, Gemini CLI, or plugins for VS Code, Cursor, and Windsurf can connect directly and use its memory layer out of the box

github.com/campfirein/cip…

First let's install Cipher and set up your environment:

• Install globally: npm install -g @byterover/cipher
• Add .env with your provider (we’ll use Ollama for local embeddings, but OpenAI/Gemini also work)
• Create memAgent/cipher.yml to define your model + system prompt

Next, let’s add Cipher as an MCP server so agents can discover it automatically

• Update "settings.json" if you are using Gemini CLI
• If you’re using Claude Code, add the same config to .mcp.json

Now your coding agents can connect to Cipher locally and have long‑term memory

Here’s how it works: I ask Gemini CLI to analyze my project structure.

It connects to Cipher MCP tool, maps the structure, detects patterns, and saves them locally.

This context is now reusable across Claude Code, Cursor, or any other connected coding agent.

By default Cipher stores context locally, but you can connect it to vector or graph databases for persistence.

ByteRover takes it further by storing context in the cloud, sharing it with your team, and making it usable across agents.

Check it out here: byterover.dev/?source=su1

Cipher is built for coding agents.

It works with Cursor, Windsurf, Claude Desktop, Claude Code, Gemini CLI, AWS Kiro, VS Code, Roo Code (via MCP), and even agents like Kimi K2.

GitHub Repo: github.com/campfirein/cip…

Don't forgot star the Repo!

If you found it useful, reshare it with your network.

Follow me → @Sumanth_077 for more such content and tutorials on ML, LLMs and AI Agents!


x.com/Sumanth_077/st…