superlocalmemory 4.1.20__tar.gz → 4.2.2__tar.gz

superlocalmemory-4.2.2/PKG-INFO

@@ -0,0 +1,499 @@
+Metadata-Version: 2.4
+Name: superlocalmemory
+Version: 4.2.2
+Summary: The governed memory brain for AI agents: one local memory for Claude Code, Codex, Cursor, Copilot, ChatGPT and any MCP client
+Author-email: Varun Pratap Bhardwaj <admin@superlocalmemory.com>
+License-Expression: AGPL-3.0-or-later
+Project-URL: Homepage, https://superlocalmemory.com
+Project-URL: Repository, https://github.com/qualixar/superlocalmemory
+Project-URL: Documentation, https://github.com/qualixar/superlocalmemory/wiki
+Project-URL: Issues, https://github.com/qualixar/superlocalmemory/issues
+Keywords: ai-memory,agent-memory,mcp-server,mcp,claude-code,codex,cursor,chatgpt,rag,knowledge-graph,local-first,privacy-first,gdpr,eu-ai-act,information-geometry,multimodal-memory,gemma,embeddinggemma,ollama,local-llm,jev,answer-verification,hallucination-prevention,ai-reliability-engineering,agent-to-agent
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: <3.15,>=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: httpx==0.28.1
+Requires-Dist: numpy==2.4.4
+Requires-Dist: scipy==1.17.1
+Requires-Dist: networkx==3.6.1
+Requires-Dist: mcp==2.0.0
+Requires-Dist: jsonschema==4.26.0
+Requires-Dist: python-dateutil==2.9.0.post0
+Requires-Dist: rank-bm25==0.2.2
+Requires-Dist: vadersentiment==3.3.2
+Requires-Dist: einops==0.8.2
+Requires-Dist: fastapi[all]==0.139.2
+Requires-Dist: uvicorn==0.46.0
+Requires-Dist: websockets==16.0
+Requires-Dist: keyring==25.7.0
+Requires-Dist: zeroconf>=0.140
+Requires-Dist: lightgbm==4.6.0
+Requires-Dist: orjson==3.11.9
+Requires-Dist: tomli-w==1.2.0
+Requires-Dist: tree-sitter==0.25.2
+Requires-Dist: tree-sitter-language-pack==0.13.0
+Requires-Dist: rustworkx==0.17.1
+Requires-Dist: watchdog==5.0.3
+Requires-Dist: psutil==7.2.2
+Requires-Dist: structlog==25.5.0
+Requires-Dist: portalocker==3.2.0
+Requires-Dist: pywin32==311; sys_platform == "win32"
+Requires-Dist: cryptography==50.0.0
+Requires-Dist: sentence-transformers==5.6.1
+Requires-Dist: optimum==2.1.0
+Requires-Dist: onnxruntime==1.24.4
+Requires-Dist: transformers==5.10.4
+Requires-Dist: huggingface_hub==1.5.0
+Requires-Dist: torch==2.13.0
+Requires-Dist: scikit-learn==1.8.0
+Requires-Dist: sqlite-vec==0.1.9
+Requires-Dist: lancedb==0.30.2
+Requires-Dist: pycozo[embedded]==0.3.0; sys_platform != "linux" or platform_machine != "aarch64"
+Requires-Dist: pycozo[embedded]==0.7.6; sys_platform == "linux" and platform_machine == "aarch64"
+Requires-Dist: llmlingua==0.2.2
+Requires-Dist: nltk==3.10.3
+Requires-Dist: accelerate>=1.15.0
+Requires-Dist: anyio>=4.14.2
+Requires-Dist: fsspec>=2026.6.0
+Requires-Dist: httpx2>=2.12.0
+Requires-Dist: pyjwt>=2.15.0
+Requires-Dist: setuptools>=83.0.0
+Requires-Dist: urllib3>=2.8.0
+Provides-Extra: search
+Requires-Dist: sentence-transformers==5.6.1; extra == "search"
+Requires-Dist: optimum==2.1.0; extra == "search"
+Requires-Dist: einops==0.8.2; extra == "search"
+Requires-Dist: torch==2.13.0; extra == "search"
+Requires-Dist: scikit-learn==1.8.0; extra == "search"
+Requires-Dist: onnxruntime==1.24.4; extra == "search"
+Provides-Extra: ui
+Requires-Dist: fastapi[all]>=0.135.1; extra == "ui"
+Requires-Dist: uvicorn>=0.42.0; extra == "ui"
+Requires-Dist: python-multipart<1.0.0,>=0.0.6; extra == "ui"
+Provides-Extra: injection
+Requires-Dist: tiktoken>=0.8.0; extra == "injection"
+Provides-Extra: learning
+Requires-Dist: lightgbm>=4.0.0; extra == "learning"
+Provides-Extra: performance
+Requires-Dist: orjson>=3.9.0; extra == "performance"
+Provides-Extra: lancedb
+Requires-Dist: lancedb==0.30.2; extra == "lancedb"
+Provides-Extra: cozo
+Requires-Dist: pycozo[embedded]==0.3.0; (sys_platform != "linux" or platform_machine != "aarch64") and extra == "cozo"
+Requires-Dist: pycozo[embedded]==0.7.6; (sys_platform == "linux" and platform_machine == "aarch64") and extra == "cozo"
+Provides-Extra: scale
+Requires-Dist: lancedb==0.30.2; extra == "scale"
+Requires-Dist: pycozo[embedded]==0.3.0; (sys_platform != "linux" or platform_machine != "aarch64") and extra == "scale"
+Requires-Dist: pycozo[embedded]==0.7.6; (sys_platform == "linux" and platform_machine == "aarch64") and extra == "scale"
+Provides-Extra: ingestion
+Requires-Dist: keyring>=25.0.0; extra == "ingestion"
+Requires-Dist: google-auth-oauthlib>=1.2.0; extra == "ingestion"
+Requires-Dist: google-api-python-client>=2.100.0; extra == "ingestion"
+Requires-Dist: icalendar>=6.0.0; extra == "ingestion"
+Provides-Extra: laya
+Requires-Dist: laya-mlx<0.3,>=0.2.0; (sys_platform == "darwin" and platform_machine == "arm64") and extra == "laya"
+Provides-Extra: full
+Requires-Dist: superlocalmemory[ingestion,injection,laya,learning,performance,scale,search,ui]; extra == "full"
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.1; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.21; extra == "dev"
+Requires-Dist: sqlite-vec>=0.1.6; extra == "dev"
+Requires-Dist: httpx2==2.12.0; extra == "dev"
+Requires-Dist: import-linter==2.15; extra == "dev"
+Dynamic: license-file
+
+<div align="center">
+
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/qualixar/superlocalmemory/main/assets/branding/slm-wordmark-dark.svg">
+  <img src="https://raw.githubusercontent.com/qualixar/superlocalmemory/main/assets/branding/slm-wordmark-light.svg" alt="SuperLocalMemory" width="380">
+</picture>
+
+<p align="center"><img src="https://raw.githubusercontent.com/qualixar/superlocalmemory/main/assets/mascot/slm-mascot-hero.png" width="180" alt="SuperLocalMemory mascot, a fluffy caped helper with the SLM logo, arms open"></p>
+
+### The governed memory brain for every AI agent. It lives on your machine. It never bluffs.
+
+**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.
+
+[![PyPI](https://img.shields.io/pypi/v/superlocalmemory)](https://pypi.org/project/superlocalmemory/)
+[![npm](https://img.shields.io/npm/v/superlocalmemory)](https://www.npmjs.com/package/superlocalmemory)
+[![PyPI downloads](https://img.shields.io/pepy/dt/superlocalmemory?label=PyPI%20downloads)](https://pepy.tech/project/superlocalmemory)
+[![npm downloads](https://img.shields.io/npm/dt/superlocalmemory?label=npm%20downloads)](https://www.npmjs.com/package/superlocalmemory)
+[![GitHub stars](https://img.shields.io/github/stars/qualixar/superlocalmemory?style=flat&logo=github)](https://github.com/qualixar/superlocalmemory/stargazers)
+[![License: AGPL-3.0](https://img.shields.io/badge/license-AGPL--3.0-blue)](https://github.com/qualixar/superlocalmemory/blob/main/LICENSE)
+[![Research: 4 arXiv papers](https://img.shields.io/badge/arXiv-4_papers-b31b1b)](#research)
+
+**[Install](#install)** · **[See it work](#30-second-example)** · **[Product film](https://www.youtube.com/watch?v=pyAu_vaIYZQ)** · **[Every capability](#everything-slm-does)** · **[Docs](#documentation)** · **[Website](https://www.superlocalmemory.com)**
+
+<img src="https://raw.githubusercontent.com/qualixar/superlocalmemory/main/docs/assets/gifs/recall-tiers.gif" alt="Recall in the dashboard: a real question gets its answer; a gibberish question gets 'That isn't in SuperLocalMemory.'; a real question memory cannot answer exactly gets the closest memories, labelled" width="820">
+
+
+</div>
+
+**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
+
+Three ways in. All three end in the same setup: your text memory on this machine, and, if you say yes, your pictures and documents too.
+
+**1. Ask your agent.** Copy this into Claude Code, Codex, Cursor or any agent that can run commands:
+
+```
+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.
+```
+
+**2. npm**, the primary route (Node 18+). It installs SLM into a package-owned virtual environment:
+
+```bash
+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 ...
+```
+
+**3. pip**, the other primary route (Python 3.12 to 3.14), in a Python virtual environment you activate:
+
+```bash
+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)
+```
+
+**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](https://github.com/qualixar/superlocalmemory/blob/main/docs/pictures-and-documents.md), [getting started](https://github.com/qualixar/superlocalmemory/blob/main/docs/getting-started.md), [agent setup steps](https://github.com/qualixar/superlocalmemory/blob/main/SETUP_FOR_AGENTS.md).
+
+Repository clone: `./scripts/install.sh install` (macOS, Linux) or `.\scripts\install.ps1 -Action Install` (Windows). Runs on Windows, Linux and Apple Silicon macOS ([platforms](#platform-support)).
+
+## 30-second example
+
+```console
+$ 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 <img src="https://raw.githubusercontent.com/qualixar/superlocalmemory/main/assets/branding/google-g.svg" width="18" alt="Google"> **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](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) 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](https://github.com/qualixar/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
+
+<div align="center">
+
+[![Watch the SuperLocalMemory product film: Claude Code and Codex sharing one memory](https://img.youtube.com/vi/pyAu_vaIYZQ/maxresdefault.jpg)](https://www.youtube.com/watch?v=pyAu_vaIYZQ)
+
+*The four-minute product film: Claude Code and Codex sharing one memory.*
+
+</div>
+
+## 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 |
+| **Codex** | `slm connect codex`, then `slm codex install` | MCP, 16 skills, 4 agents, `/slm-loop`, lifecycle hooks |
+| **GitHub Copilot** (VS Code, Visual Studio, JetBrains, CLI) | `slm connect vscode-copilot --here` | MCP, agent rules, 16 prompts, 4 agents, hooks |
+| **Antigravity** | `agy plugin install` the bundled plugin | MCP, 16 skills, 4 agents, `/slm-loop`, hooks |
+| **Hermes** | Native plugin | 16 skills, advisor agents, `/slm <command>` |
+| **Grok Bot and Cursor-format hosts** | Add the `qualixar` plugin marketplace | A lean plugin built for shared bot computers ([guide](https://github.com/qualixar/superlocalmemory/blob/main/docs/plugins.md#grok-bot-and-other-cursor-format-hosts)) |
+| **Cursor, Windsurf, Zed, JetBrains, Gemini CLI, Claude Desktop, OpenCode, Continue** | `slm connect <name>` | MCP in that tool's own config |
+| **ChatGPT, Claude on the web, Muse, Composio** | Optional **Web access** from the dashboard: sign in per app, read-only or read-and-save, remove any app at once | Your local memory, from the web; the database never leaves your computer ([guide](https://github.com/qualixar/superlocalmemory/blob/main/docs/remote-access/README.md)) |
+| **LangGraph, LangChain, LlamaIndex, CrewAI, AutoGen, Semantic Kernel, Microsoft Agent Framework, Google ADK, OpenAI Agents** | Framework adapters | Memory inside your own code ([adapters](https://github.com/qualixar/superlocalmemory/blob/main/docs/framework-adapters.md)) |
+| **Anything else** | Paste the [universal agent rules](https://github.com/qualixar/superlocalmemory/blob/main/plugin-src/rules/AGENTS.md) and give it the CLI or MCP | Memory discipline for any agent |
+
+**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](https://github.com/qualixar/superlocalmemory/blob/main/docs/plugins.md)
+
+## 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 | [Recall](https://github.com/qualixar/superlocalmemory/blob/main/docs/recall.md#when-memory-cannot-answer) |
+| **Warming up, said plainly** | 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."* | [Recall](https://github.com/qualixar/superlocalmemory/blob/main/docs/recall.md#warming-up) |
+| **Layered recall** | `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 | [Layered recall](https://github.com/qualixar/superlocalmemory/blob/main/docs/recall.md#layered-recall) |
+| **Hybrid search** | Semantic, keyword (BM25), entity-graph, temporal, associative (Hopfield), spreading-activation and picture channels, fused and reranked; `slm trace` shows each channel's score | [Recall](https://github.com/qualixar/superlocalmemory/blob/main/docs/recall.md) |
+| **Nine memory kinds** | 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 | [Memory kinds](https://github.com/qualixar/superlocalmemory/blob/main/docs/memory-kinds.md) |
+| **Time travel** | `--valid-at` (what was true then), `--known-as-of` (what SLM knew then), `--window 7d` | [Recall](https://github.com/qualixar/superlocalmemory/blob/main/docs/recall.md#time-travel) |
+| **Precise filters** | By project, agent, subject, kind and exact tags; an empty result says why | [Recall](https://github.com/qualixar/superlocalmemory/blob/main/docs/recall.md#narrowing-a-recall) |
+| **Corrections** | `--replaces` retires an old fact, kept and undoable; edits go through reviewed corrections with rollback | [Corrections](https://github.com/qualixar/superlocalmemory/blob/main/docs/reviewed-corrections.md) |
+| **Summaries and saved views** | Session, day and project summaries that cite their memory ids; saved views like "what did I ship this week" | [Recall](https://github.com/qualixar/superlocalmemory/blob/main/docs/recall.md#summaries) |
+| **Prompt-injection defence** | Recalled text is treated as untrusted evidence: secrets redacted, forged markers neutralised, provenance attached | [Security](https://github.com/qualixar/superlocalmemory/blob/main/SECURITY.md) |
+
+### The answer check: Laya and Jev
+
+<table>
+<tr>
+<td width="50%" valign="top">
+
+**Laya — on your Mac**
+
+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`.
+
+</td>
+<td width="50%" valign="top">
+
+<img src="https://raw.githubusercontent.com/qualixar/superlocalmemory/main/assets/branding/jev-mark.svg" width="44" alt="Jev mark"> **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.
+
+</td>
+</tr>
+</table>
+
+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](https://github.com/qualixar/superlocalmemory/blob/main/docs/answer-check.md)
+
+### 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 and documents](https://github.com/qualixar/superlocalmemory/blob/main/docs/pictures-and-documents.md) |
+| **PDFs, page by page** | Each page is indexed by its picture and its text; every answer says which file and page it came from, with a thumbnail | [Pictures and documents](https://github.com/qualixar/superlocalmemory/blob/main/docs/pictures-and-documents.md) |
+| **Document index** | A catalogue of every saved document with its pages and the people, projects and dates it mentions | [Pictures and documents](https://github.com/qualixar/superlocalmemory/blob/main/docs/pictures-and-documents.md) |
+| **Document health check** | Finds pages with no readable text, documents linked to nothing, duplicate pages and documents whose facts were contradicted | [Pictures and documents](https://github.com/qualixar/superlocalmemory/blob/main/docs/pictures-and-documents.md) |
+| **Folders and Obsidian vaults** | `slm sources add ~/Notes --kind obsidian` mirrors Markdown, canvas files, PDFs and images into memory, read-only, after showing what it would read | [CLI](https://github.com/qualixar/superlocalmemory/blob/main/docs/cli-reference.md) |
+| **From ChatGPT and your phone** | Attach a file in ChatGPT, or ask any connected web app for a one-time upload link that streams the file straight to your computer | [Web access](https://github.com/qualixar/superlocalmemory/blob/main/docs/remote-access/hosts.md) |
+| **Your data stays yours** | 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 | [Compliance](https://github.com/qualixar/superlocalmemory/blob/main/docs/compliance.md) |
+
+### Memory health
+
+| Capability | What you get | Docs |
+|---|---|---|
+| **Automatic description** | 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 | [Memory health](https://github.com/qualixar/superlocalmemory/blob/main/docs/memory-health.md) |
+| **Fix and Undo** | 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 | [Memory health](https://github.com/qualixar/superlocalmemory/blob/main/docs/memory-health.md) |
+| **Stub badge** | Receipts and session boilerplate stay listed with a **stub** badge but never become answers | [Memory health](https://github.com/qualixar/superlocalmemory/blob/main/docs/memory-health.md) |
+| **Store health** | `slm doctor` shows how findable and described your memories are; `slm db integrity` and `slm db repair` (with undo) keep the store sound | [Troubleshooting](https://github.com/qualixar/superlocalmemory/blob/main/docs/troubleshooting.md) |
+
+### The living brain
+
+| Capability | What you get | Docs |
+|---|---|---|
+| **Knowledge graph** | People, projects and tools resolved from your memories, with aliases, scenes and timelines; the Entity Explorer shows how what you know changed | [Architecture](https://github.com/qualixar/superlocalmemory/blob/main/docs/ARCHITECTURE.md) |
+| **Code graph** | Index a repository, then ask for blast radius, callers and code search by meaning | [MCP tools](https://github.com/qualixar/superlocalmemory/blob/main/docs/mcp-tools.md) |
+| **Forgetting that helps** | An Ebbinghaus retention cycle and Langevin lifecycle move neglected memories toward archive; fading memories are quantized to fewer bits and folded into one gist | [Research](#research) |
+| **Learning to rank (opt-in)** | 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 | [Configuration](https://github.com/qualixar/superlocalmemory/blob/main/docs/configuration.md) |
+| **Soft prompts and skill evolution (opt-in)** | Stable behaviour patterns become soft prompts for new sessions; agent skills are measured and revised under blind verification | [Skill evolution](https://github.com/qualixar/superlocalmemory/blob/main/docs/skill-evolution.md) |
+
+### Governance and compliance
+
+| Control | What it does | Docs |
+|---|---|---|
+| **Roles and workspaces** | Admin, member and viewer per workspace; a role in one workspace grants nothing in another; maintenance and approvals act only where you are | [Teams](https://github.com/qualixar/superlocalmemory/blob/main/docs/rbac-teams.md) |
+| **Company mode** | Every read and write attributed to a signed-in person | [Company mode](https://github.com/qualixar/superlocalmemory/blob/main/docs/company-mode.md) |
+| **Scopes** | Personal by default; shared and global only when you choose; cross-profile recall denied by default | [Scopes](https://github.com/qualixar/superlocalmemory/blob/main/docs/shared-memory.md) |
+| **GDPR** | Export (Art. 15/20) and erasure (Art. 17) across every store and every derived copy, with a verifiable receipt | [Compliance](https://github.com/qualixar/superlocalmemory/blob/main/docs/compliance.md) |
+| **Audit and retention** | A hash-chained audit trail that fails verification if tampered with; per-profile retention rules; an EU AI Act posture report | [Compliance](https://github.com/qualixar/superlocalmemory/blob/main/docs/compliance.md) |
+| **Backup and restore** | 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 | [Cloud backup](https://github.com/qualixar/superlocalmemory/blob/main/docs/cloud-backup.md), [Restore points](https://github.com/qualixar/superlocalmemory/blob/main/docs/restore-points.md) |
+
+Engineering controls that support a compliance program, not a certification.
+
+### Many agents, one memory
+
+| Capability | What you get | Docs |
+|---|---|---|
+| **Attributed, trusted writes** | Every memory records its agent; Bayesian trust scores defend against memory poisoning | [Research](#research) |
+| **SLM-Mesh** | Messages, waits, locks and shared state between sessions, on one machine or several | [Multi-machine](https://github.com/qualixar/superlocalmemory/blob/main/docs/multi-machine.md) |
+| **Bots that talk to each other** | 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 | [Bot messages](https://github.com/qualixar/superlocalmemory/blob/main/docs/remote-access/hosts.md#bot-messages-and-the-two-new-permissions) |
+| **Bounded loops and graphs** | "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](https://github.com/qualixar/bounded-loops), and SLM keeps their finished runs as read-only evidence | [Bounded Loops bridge](https://github.com/qualixar/superlocalmemory/blob/main/docs/bounded-loops-bridge.md) |
+
+### Context savings
+
+| Capability | What you get | Docs |
+|---|---|---|
+| **Exact cache** | Tool output and file reads cached with a TTL; a hit skips the repeat call | [Optimize](https://github.com/qualixar/superlocalmemory/blob/main/docs/optimize-overview.md) |
+| **Reversible compression** | Large output shrunk safely; the exact original comes back by id | [Optimize](https://github.com/qualixar/superlocalmemory/blob/main/docs/optimize-overview.md) |
+| **Three ways in** | Works through a proxy (`slm wrap claude`), MCP tools or a skill; `slm optimize savings` shows what you saved | [Proxy setup](https://github.com/qualixar/superlocalmemory/blob/main/docs/proxy-setup.md) |
+
+### Modes, dashboard and scale
+
+| Capability | What you get | Docs |
+|---|---|---|
+| **Three modes** | **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 | [Configuration](https://github.com/qualixar/superlocalmemory/blob/main/docs/configuration.md) |
+| **Dashboard** | Search, knowledge graph, Entity Explorer, answer check, Memory health, documents and images, connected apps, bot messages, governance: `slm dashboard` | [Dashboard](https://github.com/qualixar/superlocalmemory/blob/main/docs/DASHBOARD-COVERAGE.md) |
+| **Scale engine** | SQLite + sqlite-vec are canonical; optional LanceDB and CozoDB copies serve only once they match SQLite | [Scale engine](https://github.com/qualixar/superlocalmemory/blob/main/docs/scale-engine.md) |
+| **Durable writes** | Every save moves raw → queryable → complete with a receipt; failures keep the evidence and retry; text saves under load are queued, never refused | [Architecture](https://github.com/qualixar/superlocalmemory/blob/main/docs/ARCHITECTURE.md) |
+| **Model switching** | Change the embedding model in the background while recall keeps working, with one-step rollback | [CLI](https://github.com/qualixar/superlocalmemory/blob/main/docs/cli-reference.md#embedding-models-and-store-health) |
+| **Remote access on your network** | `slm remote` serves memory to other computers over TLS, one revocable key per client | [Deployment](https://github.com/qualixar/superlocalmemory/blob/main/docs/distributed-deployment.md#remote-access-over-tls) |
+
+## MCP memory server: tool profiles
+
+Pick how many tools your agent sees with `SLM_MCP_PROFILE`.
+
+| Profile | Tools | For |
+|---|---:|---|
+| `core` | 19 | Remember, recall, expand, sessions, optimize, correction review |
+| `code` | 39 | Core plus code graph, memory kinds, Brain evidence, profile switching, bounded loops |
+| `mesh` | 9 | SLM-Mesh coordination only |
+| `full` (and unset) | 58 | Memory, kinds, Brain, optimize, skill evolution, mesh, loops, views and summaries (63 with pictures and documents on) |
+| `power` | 70 | Full plus administration, lifecycle and diagnostics (75 with pictures and documents on) |
+| `whole` | 110 | Every registered tool |
+
+stdio: `{"command": "slm", "args": ["mcp"]}` · HTTP: `http://127.0.0.1:8765/mcp/` · [MCP tools](https://github.com/qualixar/superlocalmemory/blob/main/docs/mcp-tools.md)
+
+## See it
+
+| Memory health: Fix and Undo | Knowledge graph |
+|---|---|
+| <img src="https://raw.githubusercontent.com/qualixar/superlocalmemory/main/docs/assets/gifs/memory-health.gif" alt="Memory health card: hidden memories that are still in use are fixed with one click, and Undo restores exactly what changed"> | <img src="https://raw.githubusercontent.com/qualixar/superlocalmemory/main/docs/assets/gifs/knowledge-graph.gif" alt="Knowledge graph: nodes settle into clusters, a click on a person shows the memory behind it"> |
+| **Entity Explorer** | **The answer check at work** |
+| <img src="https://raw.githubusercontent.com/qualixar/superlocalmemory/main/docs/assets/gifs/entities.gif" alt="Entity Explorer: projects and tools with their facts and timeline"> | <img src="https://raw.githubusercontent.com/qualixar/superlocalmemory/main/docs/screenshots/dashboard/answer-check-answered.png" alt="Answer Check: the on-device model judges that the memories answer the question, with its confidence and timing"> |
+
+Recorded on a test install with fictional memories. [The four-minute product film](https://www.youtube.com/watch?v=pyAu_vaIYZQ) walks through every pane.
+
+## Architecture
+
+<img src="https://raw.githubusercontent.com/qualixar/superlocalmemory/main/docs/assets/slm-architecture.png" alt="SuperLocalMemory architecture: local harnesses, web bots and your code reach one SLM service on your computer through four doors (MCP, CLI, REST and dashboard, Web access); SLM-Mesh lets local agents and web bots talk to each other; inside, recall runs hybrid channels, fusion, the answer gate with three tiers, the Laya or Jev answer check and layered output; saves pass admission, redaction and understanding; the living brain runs Memory health, consolidation, daily learning and bounded loops; storage is SQLite with verified LanceDB and CozoDB copies, pictures and documents, the knowledge graph, the audit chain and encrypted backup; governance applies to every call" width="900">
+
+The free local core is complete on its own; Web access is optional. [Architecture in detail](https://github.com/qualixar/superlocalmemory/blob/main/docs/ARCHITECTURE.md)
+
+## Privacy
+
+<img align="right" width="110" src="https://raw.githubusercontent.com/qualixar/superlocalmemory/main/assets/mascot/slm-mascot-shield.png" alt="SuperLocalMemory mascot holding a shield: privacy and governance">
+
+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](https://github.com/qualixar/superlocalmemory/blob/main/SECURITY.md)
+
+## Benchmarks
+
+These numbers come from the published architecture paper ([arXiv:2603.14588](https://arxiv.org/abs/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](https://github.com/qualixar/superlocalmemory/blob/main/docs/benchmarks.md)
+
+## Research
+
+Four arXiv preprints by Varun Pratap Bhardwaj describe SLM:
+
+1. [SuperLocalMemory 4.0: The Governed Memory Operating System for AI Agents](https://arxiv.org/abs/2608.08253), with Garima Singh and Arun Pratap Bhardwaj. arXiv:2608.08253
+2. [SuperLocalMemory V3.3: The Living Brain](https://arxiv.org/abs/2604.04514), arXiv:2604.04514
+3. [SuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory](https://arxiv.org/abs/2603.14588), arXiv:2603.14588
+4. [Privacy-Preserving Multi-Agent Memory with Bayesian Trust Defense Against Memory Poisoning](https://arxiv.org/abs/2603.02240), arXiv:2603.02240
+
+Cite with [CITATION.cff](https://github.com/qualixar/superlocalmemory/blob/main/CITATION.cff) or GitHub's "Cite this repository".
+
+## Documentation
+
+**Start:** [Getting started](https://github.com/qualixar/superlocalmemory/blob/main/docs/getting-started.md) · [IDE setup](https://github.com/qualixar/superlocalmemory/blob/main/docs/ide-setup.md) · [Plugins](https://github.com/qualixar/superlocalmemory/blob/main/docs/plugins.md) · [Quick proof](https://github.com/qualixar/superlocalmemory/blob/main/docs/QUICK_PROOF.md)
+**Use:** [Recall](https://github.com/qualixar/superlocalmemory/blob/main/docs/recall.md) · [Memory health](https://github.com/qualixar/superlocalmemory/blob/main/docs/memory-health.md) · [Answer check](https://github.com/qualixar/superlocalmemory/blob/main/docs/answer-check.md) · [Pictures and documents](https://github.com/qualixar/superlocalmemory/blob/main/docs/pictures-and-documents.md) · [Auto-memory](https://github.com/qualixar/superlocalmemory/blob/main/docs/auto-memory.md) · [Web access](https://github.com/qualixar/superlocalmemory/blob/main/docs/remote-access/README.md) · [Optimize](https://github.com/qualixar/superlocalmemory/blob/main/docs/optimize-overview.md)
+**Reference:** [CLI](https://github.com/qualixar/superlocalmemory/blob/main/docs/cli-reference.md) · [MCP tools](https://github.com/qualixar/superlocalmemory/blob/main/docs/mcp-tools.md) · [Configuration](https://github.com/qualixar/superlocalmemory/blob/main/docs/configuration.md) · [Troubleshooting](https://github.com/qualixar/superlocalmemory/blob/main/docs/troubleshooting.md) · [Compliance](https://github.com/qualixar/superlocalmemory/blob/main/docs/compliance.md) · [Wiki](https://github.com/qualixar/superlocalmemory/wiki) · [Release notes](https://github.com/qualixar/superlocalmemory/blob/main/CHANGELOG.md)
+
+## Upgrade
+
+```bash
+npm update -g superlocalmemory    # or: pipx upgrade superlocalmemory
+slm restart && slm doctor
+slm upgrade-hosts                 # preview plugin and IDE updates; nothing changes until you --apply
+```
+
+Upgrades never move or delete memory, and a store update takes a restore point first. [Host upgrades](https://github.com/qualixar/superlocalmemory/blob/main/docs/host-upgrades.md)
+
+## Platform support
+
+| | SuperLocalMemory | Laya (on-device answer check) |
+|---|---|---|
+| Apple Silicon macOS | Yes | Yes, installed by default |
+| 64-bit Windows | Yes | No (Jev, the online check, works) |
+| 64-bit Linux (x86-64, ARM64) | Yes | No (Jev works) |
+| Intel Mac, 32-bit Windows | No prebuilt install | — |
+
+Python 3.12+, Node 18+ for npm. Pictures and documents need 16 GB of memory.
+
+## Contributing and license
+
+Issues and pull requests are welcome: [CONTRIBUTING.md](https://github.com/qualixar/superlocalmemory/blob/main/CONTRIBUTING.md). Security reports: [SECURITY.md](https://github.com/qualixar/superlocalmemory/blob/main/SECURITY.md). Licensed under [AGPL-3.0-or-later](https://github.com/qualixar/superlocalmemory/blob/main/LICENSE); for a commercial license see [COMMERCIAL-LICENSE.md](https://github.com/qualixar/superlocalmemory/blob/main/COMMERCIAL-LICENSE.md).
+
+---
+
+<div align="center">
+
+<img src="https://raw.githubusercontent.com/qualixar/superlocalmemory/main/assets/mascot/slm-mascot-pointing.png" width="120" alt="SuperLocalMemory mascot pointing to the repository star button">
+
+### Built by Qualixar
+
+**SuperLocalMemory** is made by [Varun Pratap Bhardwaj](https://varunpratap.com) at [Qualixar](https://qualixar.com): 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](https://github.com/qualixar/jev-decision-layer)** makes your agent's bounded choices typed and checked. **[Bounded Loops](https://github.com/qualixar/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](https://github.com/qualixar/superlocalmemory)**. It's how other developers find it.
+
+[![GitHub stars](https://img.shields.io/github/stars/qualixar/superlocalmemory?style=social)](https://github.com/qualixar/superlocalmemory/stargazers)
+[![Follow on X](https://img.shields.io/badge/follow-%40varunPbhardwaj-000000?logo=x)](https://x.com/varunPbhardwaj)
+
+**More from Qualixar:** [Qualixar OS](https://github.com/qualixar/qualixar-os) · [SkillFortify](https://github.com/qualixar/skillfortify) · [SLM Mesh](https://github.com/qualixar/slm-mesh) · [AgentAssert](https://github.com/qualixar/agentassert-abc) · [AgentAssay](https://github.com/qualixar/agentassay) · [Bounded Loops](https://github.com/qualixar/bounded-loops) · [Jev Decision Layer](https://github.com/qualixar/jev-decision-layer) · [SLM MCP Hub](https://github.com/qualixar/slm-mcp-hub)
+
+</div>