One memory for every agent you and your team use — Claude Code, Codex, Cursor, Copilot, Antigravity, Hermes, ChatGPT, Claude on the web, Grok Bot, Muse and any harness that speaks MCP or runs a command. Decisions, documents, screenshots and PDFs, recalled the way you ask for them, governed like company data, shared through a mesh where your local agents and web bots talk to each other, and answered honestly: when the answer isn't there, your agent hears "That isn't in SuperLocalMemory." — not a confident guess.
Open-source governed, local-first memory control plane for AI agents and teams. arXiv:2608.08253
⭐ If SuperLocalMemory keeps your agents from guessing, star the repo. It helps other developers find it.
Agents forget everything between sessions. The usual fix — a vector store with a save button — makes it worse: it always returns something, even when nothing it holds answers the question, and your agent builds on it. This is a memory brain, not a bucket: it understands what was saved (who, what, when, which project), keeps it true over time, governs who may see it, and refuses to bluff. Four arXiv papers describe how it works.
In Mode A, core remember and recall make no model-provider call: no API key, no cloud account, no Docker. Anything that sends data out is a choice you make, and the docs say exactly what goes.
Install
The easiest way: let your AI agent install it. Copy the block below into Claude Code, Codex, Cursor or any agent that can run commands. It reads the setup guide, asks you one question, sets everything up and tells you what works. No terminal commands for you to learn.
Install SuperLocalMemory on this computer for me. Follow
https://github.com/qualixar/superlocalmemory/blob/main/SETUP_FOR_AGENTS.md
step by step and show me what each step printed. Ask me only one question,
before turning on anything optional: whether I also want to find my pictures,
screenshots and PDFs by describing them. Connect SuperLocalMemory to the agent
I am using. When you finish, run slm doctor and tell me in plain words what works.
No AI agent? One line in Terminal (macOS and Linux). It brings its own Python, sets everything up, connects the AI tools it finds and opens the dashboard; no Python or npm needed beforehand:
curl -fsSLo get-slm.sh https://raw.githubusercontent.com/qualixar/superlocalmemory/main/scripts/get-slm.sh && sh get-slm.sh
Add pictures and documents from the start with sh get-slm.sh --media at the end. It downloads the script first, so you can read it before it runs. Windows: use the agent prompt above, or npm or pip below.
Prefer the terminal? Both routes end in the same setup: your text memory on this machine, and, if you say yes, your pictures and documents too.
npm, the primary route (Node 18+). It installs SLM into a package-owned virtual environment:
npm install -g superlocalmemory # add --media to also turn on pictures and documents
slm setup # pick Mode A to keep everything on this machine
slm connect claude-code # or codex, cursor, windsurf, zed, claude-desktop, jetbrains, opencode ...
pip, the other primary route (Python 3.12 to 3.14), in a Python virtual environment you activate:
python3 -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
python -m pip install superlocalmemory # or, without a venv: pipx install superlocalmemory
slm setup
slm connect claude-code
slm media enable # optional: pictures and documents (about 1.5 GB; needs 16 GB of memory)
uv: uv tool install --python 3.12 superlocalmemory installs slm as an isolated tool, with nothing to activate; see Linux install.
Claude Code plugin:claude plugin marketplace add qualixar/superlocalmemory, then claude plugin install superlocalmemory@qualixar. Codex:slm connect codex, then slm codex install.
Two models, one memory. Text is searched with a small local text model (nomic). If you turn on pictures and documents, a second local model (Google's EmbeddingGemma 2) reads them, and one recall returns both. The picture model unloads after 30 minutes without use, so it holds no memory while you only work with text. Details: pictures and documents, getting started, agent setup steps.
Repository clone: ./scripts/install.sh install (macOS, Linux) or .\scripts\install.ps1 -Action Install (Windows). Runs on Windows, Linux and Apple Silicon macOS (platforms).
30-second example
$ slm remember "We deploy the API blue-green; rollback is a DNS flip." --kind decision
Queryable ✓ 1 facts
$ slm remember "Staging DB is Postgres 16 on port 5433."
$ slm recall "how do we roll back the API"
1. [0.67] We deploy the API blue-green; rollback is a DNS flip.
$ slm recall "zxqv plorth wimble"
That isn't in SuperLocalMemory.
$ slm remember "Staging DB moved to Postgres 17 on port 5434." --replaces <id>
Replaced ✓ 1 fact(s). To undo: slm review-correction ... rollback 1
$ slm recall "which port does staging postgres use"
1. [0.68] Staging DB moved to Postgres 17 on port 5434.
Real output from a fresh Mode A install, trimmed. Scores rank memories; they are not probabilities.
Why SuperLocalMemory: twelve superpowers
1. It knows when it doesn't know. Every recall comes back in one of three tiers: a supported answer; the closest memories, labelled "I don't have this exactly — here are the closest memories"; or "That isn't in SuperLocalMemory." for nonsense. Just after a start it says it is still warming up and shows what it has found, so you never hear "empty" when the truth is "not ready yet". Your agent stops building on the wrong memory.
2. A second opinion that never leaves your Mac. On Apple Silicon, SLM installs Laya, a small on-device model that judges whether the memories found actually answer the question. Prefer the cloud, or not on a Mac? Jev does the same check online, only after you tick its consent.
3. Your documents and screenshots become a knowledge base you can ask. Save a photo, a screenshot or a PDF and find it weeks later by describing it — "the slide with the quarterly numbers". The picture model is Google's EmbeddingGemma 2, running on your computer: one model reads both your words and your pictures, so a description finds the image. OCR runs locally too, every PDF page is indexed by its picture and its text, and every answer cites its file and page. No generative model ever looks at your files.
4. Karpathy's LLM-wiki idea, built in — with search kept. Andrej Karpathy's LLM-wiki pattern turns raw documents into an organised knowledge base with an index and a health check. SLM does that from the data it already stores — a document index of every file with its people, projects and dates, and a document health check that finds empty pages, unlinked documents, duplicate pages and contradicted facts — while keeping real hybrid search for the moment you need to find something.
5. It looks after itself.Memory health describes your older memories in the background — dates, names, projects, kinds — only ever by adding, never touching what you wrote. Anything that moves or deletes waits for your Fix, and Undo puts it back.
6. Governed, not just stored. Every save passes an admission check and gets a receipt. Every read respects roles, workspaces and scopes. Every erasure reaches every copy — summaries, caches, indexes, picture mirrors — and comes with a verifiable receipt. Every action lands in a hash-chained audit trail. Built for teams and for GDPR, not bolted on.
7. Memory with a sense of time. Every fact knows when it happened and when SLM learned it. Ask what was true last month, or what SLM knew before a date. Corrections replace a fact and stay undoable; unused memories fade the way human memory does.
8. It never floods your context window. Layered recall gives an agent a one-line glance, the facts, or the full surrounding context — under a hard token budget it sets. The agent digs deeper with expand only when it needs to, and cache and reversible compression stop you paying for the same output twice.
9. Many agents, one brain. Every write records which agent made it, with trust scores against memory poisoning, so ten agents can share one memory without poisoning it.
10. Your agents talk to each other — even across the internet. Through SLM-Mesh, the agents on your computer and the bots on the web finally share one conversation. Claude Code, Codex and Hermes sessions exchange messages, waits, locks and shared state, on one machine or several, so one agent can hand work to another and two never edit the same file at once. And the bots you allow — ChatGPT, Claude on the web, Grok Bot, Muse — join the same mesh: a bot in your browser can message the agent on your laptop by name and read its reply. Every message arrives labelled as data, never as instructions; a web bot reads new messages when its next turn starts.
11. It learns every day, and it can't quietly get worse. Every reported outcome teaches it: ranking learns which memories actually helped, stable habits become soft prompts for new sessions, and agent skills are measured and revised. A new ranker is promoted only on a statistically valid win and rolled back automatically if it slips. Work runs as bounded loops that end only when an independent gate passes — never on an agent's word — and multi-step pipelines run as bounded graphs with Bounded Loops, whose finished runs SLM keeps as read-only evidence.
12. Science, not vibes. Four arXiv papers back every layer: information-geometric retrieval, biologically inspired forgetting, Bayesian trust against memory poisoning, and governed memory with measured costs. The core math runs without a language model, and the published benchmarks state exactly how they were measured.
SuperLocalMemory is part of Qualixar's AI Reliability Engineering work: agent memory that is observable, bounded and honest about what it doesn't know.
Watch it work
The full eight-minute demo: one memory shared by your coding agents and bots, every tab.
Add SuperLocalMemory to your app
You do not need to wait for an app store. Every app below can take SuperLocalMemory straight from this GitHub repository, qualixar/superlocalmemory, in two steps.
Step 1, once per computer. Install SuperLocalMemory: npm install -g superlocalmemory (or pipx install superlocalmemory). Your memory lives on this computer from then on.
Step 2, in each app you use:
Your app
What to do
Claude Code (terminal and desktop app)
Type /plugin marketplace add qualixar/superlocalmemory, then /plugin install superlocalmemory@qualixar
Claude Desktop
Run slm connect claude-desktop, then restart Claude Desktop
ChatGPT, Claude on the web, Muse, Composio
Open the dashboard (slm dashboard) → Web access → turn it on, then add the link it shows as a connector in that app (step-by-step)
Codex (terminal and desktop app)
Run codex plugin marketplace add qualixar/superlocalmemory --ref main, then codex plugin add superlocalmemory-codex@qualixar
Cursor (editor and Agents window)
Run slm connect cursor, then restart Cursor
VS Code (Copilot chat in the editor)
Install the SuperLocalMemory extension (.vsix from the latest release: Extensions → ... → Install from VSIX)
VS Code Agents window, GitHub Copilot CLI
Run slm connect copilot-cli; for the skills, add qualixar/superlocalmemory in the Agents window's Plugins screen
Antigravity
Run agy plugin install "$(npm root -g)/superlocalmemory/antigravity-plugin"
Grok CLI
Run grok plugin install 'qualixar/superlocalmemory#plugin'
Grok Bot
In Grok's Plugins screen, add the marketplace qualixar/superlocalmemory and add superlocalmemory
Muse CLI
Run slm connect muse, then muse plugins install "$(npm root -g)/superlocalmemory/muse-plugin" and muse plugins approve superlocalmemory
Hermes (terminal and desktop app)
Run hermes plugins install 'https://github.com/qualixar/superlocalmemory.git#hermes-plugin', then slm upgrade-hosts --host hermes --apply
Run slm connect <app>, for example slm connect windsurf
Anything else that speaks MCP
Add a server with the command slm and the argument mcp
Restart the app after adding SuperLocalMemory. Then ask it something like "What do you remember about this project?" The plugin guide has the details for each app, and slm doctor checks your setup.
Works with your agents
Every harness, every bot, one memory. Any harness that speaks MCP (slm mcp, or http://127.0.0.1:8765/mcp/) or can run a command (slm remember, slm recall) can use SuperLocalMemory. The packaged plugins are ready-made examples, not a limit.
Host
Connect
You get
Claude Code
claude plugin install superlocalmemory@qualixar
MCP, 16 skills, 4 agents, /slm-loop, session and recall hooks
What the plugins teach your agent. Every plugin is built from one source, so every host gets the same 16 skills (recall, remember, sessions, governance, scopes and profiles, the knowledge graph, mesh, bounded loops, cache, compression, Web access, pictures, and two for bot computers) and 4 agents (a memory advisor, an optimize advisor, a governance advisor and a loop runner). Hooks run at session start, after tool use and at the end of a session, and every hook fails open: a hook problem never blocks your agent. Plugins, skills and hooks
Everything SLM does
Recall that knows when it doesn't know
Capability
What you get
Docs
Three honest tiers
Supported; closest memories (up to three, labelled); or "That isn't in SuperLocalMemory." Hooks that inject memory automatically only ever inject supported answers
While models load, recall shows what keyword search found under "SuperLocalMemory is still warming up — results may be incomplete. Try again in a few minutes."
depth 0 (a one-line glance), 1 (the facts), 2 (with source, session neighbours, related entities and corrections); a hard max_tokens cap; expand drills into one result
Fact, event, status, opinion, rule, decision, how-to, plan, correction. "What did we decide" favours decisions; confirmed rules and decisions load at every session start
A small on-device model for Apple Silicon (about 1.1 GB). Installed by default by setup and offered after an upgrade; nothing ever leaves the machine. Opt out with slm setup --no-laya or SLM_SKIP_LAYA=1. Calibrate it to your own memories in the background with slm embedder calibrate.
Jev — online, any computer
The same check on Windows, Linux or macOS, through TypeSafe or OpenRouter with your own key. It sends the question and the top three memories, and only after you tick its consent. It never turns itself on.
The verdict is one input to the support decision, with its own time budget, and the Answer Check tab shows verdicts, timing and how often memory had no answer — without storing your questions. Answer check
Documents, pictures and your notes
Capability
What you get
Docs
Pictures you find by describing them
PNG, JPEG, GIF and WebP. Google's EmbeddingGemma 2 runs locally and puts text and pictures in one search space, so your words find the image; OCR (Apple Vision on a Mac, RapidOCR elsewhere) makes the text inside it searchable; location data is never read
Pictures live in their own store and never leave your computer; erasing a memory erases its picture. Off by default, one click to turn on; needs 16 GB of memory
While your computer is idle, older memories get event dates, names, projects, tags and kinds filled in — only by adding, never by editing what you wrote, and never over a value you set
Repairs that move or delete anything — junk entity links, hidden memories still in use, saves that didn't finish — wait for your Fix; every run can be undone
An Ebbinghaus retention cycle and Langevin lifecycle move neglected memories toward archive; fading memories are quantized to fewer bits and folded into one gist
A bandit and a learning-to-rank model learn from outcomes; a new ranker is promoted only on a statistically valid win and rolled back automatically if it gets worse
Cloud backup to GitHub or Google Drive, encrypted before upload; a restore point before every store update; a restore keeps a safety copy and rolls back if it fails
ChatGPT, Claude on the web, Grok Bot and Muse join the mesh with your permission: list peers, message a named bot, read the inbox. Messages arrive labelled as data, never as instructions
"Done" means an independent gate passed (tests, a linter, a schema), never the agent's word; every lap is stored as auditable memory. Multi-step graphs run in Bounded Loops, and SLM keeps their finished runs as read-only evidence
A: no language model at all. B: a model on this machine (Ollama, where Google Gemma 3 4B is the default and Gemma 4 is in the model picker, or any local OpenAI-compatible server). C: your own endpoint or a cloud provider
Every app, plugin and extension gets full (58 tools: all of memory, SLM-Mesh, optimize, loops; 5 more while images are on) unless you choose otherwise. That fits hosts that cap the total number of MCP tools at about 100, with room for your other servers. To change it for every app at once, run one command and restart your apps:
slm tools # current set, and how many tools each set has
slm tools set power # any name below; `slm tools set default` goes back to full
To change one app only, set SLM_MCP_PROFILE in that app's MCP config (slm connect <app> --profile <name> writes it); it wins over the saved choice for that app. Per-app details
Recorded on a test install with fictional memories. The eight-minute full demo walks through every pane.
Architecture
The free local core is complete on its own; Web access is optional. Architecture in detail
Privacy
Nothing leaves your computer unless you turn on a feature that sends it, and each one says exactly what goes:
What leaves
Only when
A question and the top three memories
You turn on Jev, the online answer check, and tick its consent
Memory text
You choose Mode C, a cloud embedder or reranker, a model on another computer, or Jev kind typing (its own consent)
Encrypted backup files
You connect GitHub or Google Drive backup
Mesh messages
You configure mesh peers, or allow a web app to message your bots
Tool calls from web apps
You turn on Web access and add an app; the database stays on your computer
Pictures, documents, Laya and Mode A never send anything. Secrets in memory text are redacted on every outbound path. Security policy
Benchmarks
These numbers come from the published architecture paper (arXiv:2603.14588), whose retrieval core SLM still runs. They are not a fresh run of the current package.
Configuration (architecture paper)
LoCoMo
Scope
Mode A, retrieval + GPT-4.1-mini answers
74.8%
10 conversations, 1,276 questions
Mode A, raw (no LLM anywhere)
60.4%
10 conversations, 1,276 questions
Mode C, cloud embeddings + GPT-4.1-mini
87.7%
1 conversation (Conv-30), 81 questions
A LoCoMo score is comparable only when the subset, answer model and judge match. Method and ablations
Research
Four arXiv preprints by Varun Pratap Bhardwaj describe SLM:
SuperLocalMemory is made by Varun Pratap Bhardwaj at Qualixar: AI Reliability Engineering — memory, contracts, tests and loops that make AI agents dependable enough to trust with real work.
Stronger together. SuperLocalMemory remembers. Jev Decision Layer makes your agent's bounded choices typed and checked. Bounded Loops ends work only when an independent gate passes. Use them together and Qualixar gives your agents the whole AI Reliability Engineering environment: memory they can trust, decisions they can defend, and work that is provably done.
If SLM keeps your agents from forgetting, star the repository. It's how other developers find it.
अभी टूल सूची नहीं है। रिमोट सर्वर को पहले हेल्थ चेक के बाद सूची मिलती है।
FAQ
सवाल
Superlocalmemory कैसे इंस्टॉल करें?
इस पेज पर Cursor, Claude Desktop, Claude Code या VS Code के लिए stdio कॉन्फ़िग कॉपी करें। यह पब्लिशर का इंस्टॉल इस्तेमाल करता है, PlugMCP प्रॉक्सी नहीं।
क्या Superlocalmemory के लिए API key चाहिए?
इस रिकॉर्ड में कोई ज़रूरी एनवायरनमेंट वेरिएबल दर्ज नहीं है।
Superlocalmemory कौन सा ट्रांसपोर्ट इस्तेमाल करता है?
Superlocalmemory stdio पर लोकल चलता है।
Superlocalmemory की पिछली जाँच कब हुई थी?
पिछली जाँच 2026-11-10 को हुई। Open-source governed, local-first memory control plane for AI agents and teams. arXiv:2608.08253
