Skip to main content
plugin CX Codex

llmslim — Claude Code plugin: what it does, how to install

llmslim is a plugin for Claude Code and Codex that stores long-term memory in local SQLite. It saves exact messages and retrieves excerpts within a token budget without an LLM.

MIT ★ 1,596 updated 2026-10-29

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add hashgraph-online/awesome-codex-plugins
/plugin install llmslim@awesome-codex-plugins
Open on GitHub

What llmslim does

This plugin launches a local llmslim MCP server that logs messages directly into SQLite at ~/.llmslim/memory.db. It does not rewrite or summarize data on ingestion or retrieval. Search works entirely through local code rather than embedding models, so storing and querying memories requires no external API keys.

The server registers five MCP tools: remember, recall, list_memories, forget, and fit_context. The plugin also adds two slash commands for the optional llmslim wrap claude proxy. Running /llmslim:wrap-claude checks the proxy setup, while /llmslim:savings reports estimated tokens trimmed from tool outputs.

The MCP server requires uv and Python 3.10 or newer. Without uvx installed on your machine, the server cannot start. The proxy itself must be installed separately via uv tool install "llmslim[proxy]" or pip.

What it helps with

  • preserve critical context and decisions across separate coding sessions
  • retrieve relevant past conversation pieces within a strict token allowance
  • monitor token savings generated by trimming long command outputs
  • delete obsolete memory records using their unique IDs

Example prompts for the agent

  • /llmslim:wrap-claude
  • /llmslim:savings
  • Store our local test database port in persistent memory using remember

How to install llmslim

Plugin marketplace

/plugin marketplace add hashgraph-online/awesome-codex-plugins
/plugin install llmslim@awesome-codex-plugins

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about llmslim

How to install llmslim in Claude Code?

Run both steps in sequence: /plugin marketplace add hashgraph-online/awesome-codex-plugins and then /plugin install llmslim@awesome-codex-plugins.

Does llmslim need a separate API key to recall memories?

No. The MCP server stores and matches records with standard deterministic code, bypassing LLM inference and embedding APIs.

Where does llmslim save stored records?

Messages stay on your drive in ~/.llmslim/memory.db. You can switch the target database by setting LLMSLIM_MEMORY_DB.

Source text

llmslim · MIT
# LLMSlim plugin for Claude Code

This plugin gives Claude Code long-term memory that persists across sessions, with no LLM in the loop. It runs the
LLMSlim MCP server, which stores messages word for word in a local SQLite file and, when asked, returns the stored
messages that answer a question within a token budget. Nothing is summarized or rewritten on the way in or out.

It also adds two commands for `llmslim wrap claude`, which runs Claude Code through a local proxy that shortens long
shell, search and web tool output in the requests it sends to Anthropic's API.

## What it adds

**The `llmslim` MCP server**, started with:

```bash
uvx --from "llmslim[mcp]==0.12.0" llmslim mcp
```

| Tool | What it does | Changes data |
|---|---|---|
| `remember` | Stores a message word for word and returns its id. | Adds |
| `recall` | Returns the stored messages that answer a question, under their dates and whole where they fit, within a token budget. | No |
| `list_memories` | Lists recent messages with their ids, newest first. | No |
| `forget` | Deletes one message. It can't be undone. | Deletes |
| `fit_context` | Shrinks a long text to a token budget, keeping what answers a query, in order. | No |

**Two commands** for the proxy. Neither one starts it.
- `/llmslim:wrap-claude` checks whether the proxy is installed (`llmslim proxy --help`) and explains how to restart
  Claude Code through it with `llmslim wrap claude`.
- `/llmslim:savings` runs `llmslim proxy stats` and reports how many input tokens the proxy kept out of Claude Code's
  requests. It is an estimate counted before prompt-cache discounts, not dollars saved.

## Install

```text
/plugin marketplace add Thanatos9404/llmslim
/plugin install llmslim@llmslim
```

On Claude Code 2.1.275 or later, `/plugin install llmslim --marketplace Thanatos9404/llmslim` does both in one step.

## Requirements

- [uv](https://docs.astral.sh/uv/), which provides `uvx`. The plugin starts the memory server with it.
- Python 3.10 or newer for the memory server. If you don't have one, `uv python install` adds one.
- For the two proxy commands, the proxy installed once with `uv tool install "llmslim[proxy]"` or
  `pip install "llmslim[proxy]"` (Python 3.10 or newer).

## Data and network

- **Memory stays on your machine.** It is a SQLite file at `~/.llmslim/memory.db`. Set `LLMSLIM_MEMORY_DB` to use
  another file.
- **No model call.** Storing and recalling are plain code: no LLM, no embedding API and no API key.
- **The memory server makes no network calls of its own.** Three things do reach the network:
  - `uvx` downloads `llmslim` and its dependencies from PyPI the first time it runs a version.
  - The `tiktoken` library downloads its tokenizer file (`cl100k_base`) from `openaipublic.blob.core.windows.net` the
    first time it counts tokens, and caches it. No memory content is sent. Without network access, LLMSlim falls back
    to an approximate count.
  - The proxy, if you choose to run it with `llmslim wrap claude`, listens on 127.0.0.1 and forwards Claude Code's
    requests, with your credentials, to Anthropic's API (or to `$ANTHROPIC_BASE_URL`). It stores tool output in
    `~/.llmslim/proxy.db`. The plugin's commands don't start it.
- **The scope is fixed when the server starts**, not chosen by the model, so injected text can't make it read or
  delete another user's memory. Recalled text is labelled as data, not instructions.

## More

- MCP server options, client setup and security: [docs/MCP.md](https://github.com/Thanatos9404/llmslim/blob/main/docs/MCP.md)
- The proxy: [docs/PROXY.md](https://github.com/Thanatos9404/llmslim/blob/main/docs/PROXY.md)
- Source and issues: [github.com/Thanatos9404/llmslim](https://github.com/Thanatos9404/llmslim)

## License

MIT. See [LICENSE](https://github.com/Thanatos9404/llmslim/blob/main/LICENSE).

© Yashvardhan Thanvi · MIT · hashgraph-online/awesome-codex-plugins

Similar plugins

All plugins for Agent setup: memory, context, orchestration →

From the same set391

The whole set →
magic-hour Skills that let an agent generate and finish AI images and video through Magic Hour's MCP server or API, from photo animation to face swaps. CX Codex ★ 1,596repo stars costguard costguard detects CI minute leaks and cloud infrastructure waste, offering safe local workflow fixes without touching provider accounts. CX Codex ★ 1,596repo stars loomaly loomaly ranks a site's SEO issues, helps prepare a framework-specific fix for the repository, and checks the live page again after deployment. CX Codex ★ 1,596repo stars local-mcp A local MCP server from LMCP that gives your assistant mail, calendar, chat and file tools on Mac or Windows. Useful when the answer is spread across several apps. CX Codex ★ 1,596repo stars linkmcp Connects an AI agent to LinkedIn through LinkMCP’s hosted MCP server. Use it to look up people and companies, search Sales Navigator, handle messages, and find work contacts. CX Codex ★ 1,596repo stars linkedin-skills Twelve LinkedIn skills for Claude and Codex: post and comment drafts in your voice, AI-tell cleanup, and engager analytics split by ICP. CX Codex ★ 1,596repo stars liendeadline liendeadline tracks US mechanics lien and preliminary notice deadlines for construction material suppliers. Calculates key filing dates with statute citations and flags unverified facts. CX Codex ★ 1,596repo stars launchfast launchfast connects Launch Fast with SaaS deployment workflows. The listing also names Amazon seller research and analytics tasks. CX Codex ★ 1,596repo stars

Project sponsors

Companies that keep this analytics open