mnemon
starsforks
How to install mnemon?
mnemon-dev/mnemon
$git clone https://github.com/mnemon-dev/mnemonEnglish | 中文
README.md
| 1 | <p align="center"> |
| 2 | <img src="docs/logo/logo.svg" width="160" height="160" alt="Mnemon Logo" /> |
| 3 | </p> |
| 4 | |
| 5 | # Mnemon |
| 6 | |
| 7 | **English** | [中文](docs/zh/README.md) |
| 8 | |
| 9 | **LLM-supervised persistent memory for AI agents.** |
| 10 | |
| 11 | [](https://go.dev/) |
| 12 | [](https://github.com/mnemon-dev/mnemon/actions/workflows/ci.yml) |
| 13 | [](https://goreportcard.com/report/github.com/mnemon-dev/mnemon) |
| 14 | [](LICENSE) |
| 15 | |
| 16 | --- |
| 17 | |
| 18 | LLM agents forget everything between sessions. Context compaction drops critical decisions, cross-session knowledge vanishes, and long conversations push early information out of the window. |
| 19 | |
| 20 | Mnemon gives your agent persistent, cross-session memory — a four-graph knowledge store with intent-aware recall, importance decay, and automatic deduplication. Single binary, zero API keys, one setup command. |
| 21 | |
| 22 | > **Experimental beta:** this repository also includes `mnemon-harness`, a |
| 23 | > source-built beta for project-local host-agent lifecycle state. It is separate |
| 24 | > from the stable `mnemon` CLI, not production-ready, and may make breaking |
| 25 | > changes at any time. See [harness/README.md](harness/README.md). |
| 26 | |
| 27 | > **Claude Max / Pro subscriber?** Mnemon works entirely through your existing subscription — no separate API key required. Your LLM subscription *is* the intelligence layer. Two commands and you're done. |
| 28 | |
| 29 | ### Why Mnemon? |
| 30 | |
| 31 | Most memory tools embed their own LLM inside the pipeline. Mnemon takes a different approach: **your host LLM is the supervisor.** The binary handles deterministic computation (storage, graph indexing, search, decay); the LLM makes judgment calls (what to remember, how to link, when to forget). No middleman, no extra inference cost. |
| 32 | |
| 33 | | Pattern | LLM Role | Representative | |
| 34 | |---|---|---| |
| 35 | | **LLM-Embedded** | Executor inside the pipeline | Mem0, Letta | |
| 36 | | **File Injection** | None — reads file at session start | Claude Code Memory | |
| 37 | | **MCP Server** | Tool provider via MCP protocol | claude-mem | |
| 38 | | **LLM-Supervised** | External supervisor of a standalone binary | **Mnemon** | |
| 39 | |
| 40 | Mnemon also addresses a gap in the protocol stack. MCP standardizes how LLMs discover and invoke tools. ODBC/JDBC standardizes how applications access databases. But how LLMs interact with databases using memory semantics — this layer has no protocol. Mnemon's three primitives — `remember`, `link`, `recall` — form an intent-native protocol: command names map to the LLM's cognitive vocabulary (`remember` not INSERT, `recall` not SELECT), and output is structured JSON with signal transparency rather than raw database rows. |
| 41 | |
| 42 | <p align="center"> |
| 43 | <img src="docs/diagrams/llm-supervised-concept.jpg" width="720" alt="LLM-Supervised Architecture — three patterns compared, with Mnemon hooks, protocol boundary, and deterministic memory engine" /> |
| 44 | <br /> |
| 45 | <sub>The LLM-Supervised pattern: hooks drive the lifecycle, the host LLM makes judgment calls, the binary handles deterministic computation.</sub> |
| 46 | </p> |
| 47 | |
| 48 | Memory has a **compound interest effect** — the longer it accumulates, the greater its value. LLM engines iterate constantly, skill files cost nearly nothing to write, but memory is a private asset that grows with the user. It is the only component in the agent ecosystem worth deep investment. |
| 49 | |
| 50 | <p align="center"> |
| 51 | <img src="docs/diagrams/10-knowledge-graph.jpg" width="720" alt="Knowledge Graph — 87 insights connected by temporal, entity, semantic, and causal edges" /> |
| 52 | <br /> |
| 53 | <sub>A real knowledge graph built by Mnemon — 87 insights, 2150 edges across four graph types.</sub> |
| 54 | </p> |
| 55 | |
| 56 | See [Design & Architecture](docs/DESIGN.md) for details. |
| 57 | |
| 58 | ## Quick Start |
| 59 | |
| 60 | ### Install |
| 61 | |
| 62 | **Homebrew** (macOS / Linux): |
| 63 | |
| 64 | ```bash |
| 65 | brew install mnemon-dev/tap/mnemon |
| 66 | ``` |
| 67 | |
| 68 | **Go install**: |
| 69 | |
| 70 | ```bash |
| 71 | go |
People who liked this also viewed
6 picksType
- excel-mcpA Model Context Protocol (MCP) server for working with Excel (.xlsx) files without requiring Microsoft Excel. Enables AI assistants to create, read, modify, and format spreadsheets using openpyxl, fully in Python and cross-platform.MCP ServersOct 2025
- memories-with-lessons-mcp-serverI enhance the existing memory mcp server from the official mcp github, so big thanks and credits for creating thisMCP ServersFeb 2025
- anytype-mcpAn MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.MCP ServersJul 2026
- mcp-server-kubernetesMCP Server for kubernetes management commandsMCP ServersJul 2026
- thoughtboxThoughtbox is an intention ledger for agents. Evaluate AI's decisions against its decision-making.MCP ServersJul 2026
- google-drive-mcpA Model Context Protocol (MCP) server that provides secure integration with Google Drive, Docs, Sheets, Slides and Calendar. It allows Claude Desktop and other MCP clients to manage files in Google Drive through a standardized interface.MCP ServersJul 2026
