Thanatos9404/llmslim

Long-term memory and context selection for AI agents and coding tools, with no LLM call.
LLMSlim stores what users and agents say word for word, then returns the parts that answer a question within a
token budget you set. It runs as an MCP server, a Python library or a small HTTP server.
Examples • Documentation • Live Studio Playground • Sarvam Integration • Benchmarks • Changelog
A real Python session with llmslim 0.11.1 from PyPI, typed by a script and recorded with asciinema ( script , recording ).
## Use it in 30 seconds
Each MCP setup below starts the same server, llmslim mcp, with uv (Python 3.10 or
newer). Memory goes to a local SQLite file, ~/.llmslim/memory.db.
One click:
| Tool | Run |
| Claude Code | claude mcp add llmslim -- uvx --from "llmslim[mcp]" llmslim mcp |
| Claude Code plugin | /plugin marketplace add Thanatos9404/llmslim, then /plugin install llmslim@llmslim |
| Codex | codex mcp add llmslim -- uvx --from "llmslim[mcp]" llmslim mcp |
| GitHub Copilot CLI | copilot mcp add llmslim -- uvx --from "llmslim[mcp]" llmslim mcp |
| Gemini CLI | gemini extensions install https://github.com/Thanatos9404/llmslim |
| Hermes Agent | hermes plugins install llmslim --enable, then hermes config set context.engine llmslim: a context engine that compacts long conversations locally (plugin) |
The first start downloads LLMSlim and its dependencies. If a client gives up waiting, run
uvx --from "llmslim[mcp]" llmslim mcp --help once to fill uv's cache, then restart the client.
Python (pip install llmslim, Python 3.10 or newer):
python
from llmslim.memory import Memory
mem = Memory("memory.db") # a SQLite file; or "postgresql://..." (llmslim[postgres]), "mongodb://..." (llmslim[mongodb])
mem.add([{"role": "user", "content": "I'm allergic to peanuts."}], userid="asha")
context = mem.search("Am I allergic to anything?", userid="asha", budget=1500)
print(context.text) # put it in your prompt as data, not instructions
TypeScript (npm install llmslim, Node 18 or newer), against llmslim serve (pip install "llmslim[server]"):
ts
import { LLMSlim } from "llmslim";
const slim = new LLMSlim(); // http://127.0.0.1:8080 unless LLMSLIMBASEURL is set
await slim.memories.add({ userId: "asha", messages: "I'm allergic to peanuts." });
const context = await slim.memories.search({ userId: "asha", query: "Am I allergic to anything?", budget: 1500 });
Runnable examples, each with a test: Claude Code memory,
LangChain agent, Pydantic AI agent,
big logs and TypeScript.
If LLMSlim is useful, a star helps others find it. Feedback is welcome in issues.
## What it does
Five MCP tools: remember, recall, listmemories, forget and fitcontext.
Stores messages word for word in SQLite, Postgres or MongoDB. Nothing is summarized or extracted on the way in.
Recalls within a token budget. recall returns the stored messages that answer a question, under their dates
and whole where they fit, within the budget you set. fitcontext shrinks a long log or document to a budget.
Fixes the scope at server start. The user and agent ids are set when the server starts, not by the model, so a
model steered by injected text can't read or delete another user's memory.