# MegaMemory > Persistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer. - **Type:** MCP server - **Install:** `agentstack add mcp-0xk3vin-megamemory` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [0xK3vin](https://agentstack.voostack.com/s/0xk3vin) - **Installs:** 0 - **Category:** [Databases](https://agentstack.voostack.com/c/databases) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [0xK3vin](https://github.com/0xK3vin) - **Source:** https://github.com/0xK3vin/MegaMemory ## Install ```sh agentstack add mcp-0xk3vin-megamemory ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About MegaMemory Persistent project knowledge graph for coding agents. --- An [MCP](https://modelcontextprotocol.io/) server that lets your coding agent build and query a graph of concepts, architecture, and decisions — so it **remembers across sessions**. The LLM is the indexer. No AST parsing. No static analysis. Your agent reads code, writes concepts in its own words, and queries them before future tasks. The graph stores **concepts** — features, modules, patterns, decisions — not code symbols. ### The Loop `understand → work → update` 1. **Session start** — agent calls `list_roots` to orient itself 2. **Before a task** — agent calls `understand` with a natural language query (or `get_concept` for exact ID lookup) 3. **After a task** — agent calls `create_concept` or `update_concept` to record what it built Everything persists in a per-project SQLite database at `.megamemory/knowledge.db`. --- ### Installation ```bash npm install -g megamemory ``` > [!NOTE] > Requires Node.js >= 18. The embedding model (~23MB) downloads automatically on first use. ### Quick Start ```bash megamemory install ``` Run the interactive installer and choose your editor: > [!NOTE] > The installer only updates config files after a successful read/merge, and it will not overwrite existing plugin/command files unless they are already marked as MegaMemory-managed. #### With [opencode](https://opencode.ai) ```bash megamemory install --target opencode ``` One command configures: - MCP server in `~/.config/opencode/opencode.json` - Workflow instructions in `~/.config/opencode/AGENTS.md` - Skill tool plugin at `~/.config/opencode/tool/megamemory.ts` - Bootstrap command `/user:bootstrap-memory` for initial graph population - Save command `/user:save-memory` to persist session knowledge Restart opencode after running install. #### With [Claude Code](https://code.claude.com) ```bash megamemory install --target claudecode ``` Configures: - MCP server in `~/.claude.json` - Workflow instructions in `~/.claude/CLAUDE.md` - Commands in `~/.claude/commands/` #### With [Antigravity](https://idx.google.com) ```bash megamemory install --target antigravity ``` Configures: - MCP server in `./mcp_config.json` (workspace-level) #### With [Codex](https://openai.com/codex) ```bash megamemory install --target codex ``` Configures: - MCP server in `~/.codex/config.toml` - Workflow instructions in `~/.codex/AGENTS.md` #### With other MCP clients Add megamemory as a stdio MCP server. The command is just `megamemory` (no arguments). It reads/writes `.megamemory/knowledge.db` relative to the working directory, or set `MEGAMEMORY_DB_PATH` to override. ```json { "megamemory": { "type": "local", "command": ["megamemory"], "enabled": true } } ``` --- ### MCP Tools | Tool | Description | |------|-------------| | `understand` | Semantic search over the knowledge graph. Returns matched concepts with children, edges, and parent context. | | `get_concept` | Look up a concept by its exact ID. Returns full context including children, edges, incoming edges, and parent. | | `create_concept` | Add a new concept with optional edges and file references. | | `update_concept` | Update fields on an existing concept. Regenerates embeddings automatically. | | `link` | Create a typed relationship between two concepts. | | `remove_concept` | Soft-delete a concept with a reason. History preserved. | | `list_roots` | List all top-level concepts with direct children. | | `list_conflicts` | List unresolved merge conflicts grouped by merge group. | | `resolve_conflict` | Resolve a merge conflict by providing verified, correct content based on the current codebase. | **Concept kinds:** `feature` · `module` · `pattern` · `config` · `decision` · `component` **Relationship types:** `connects_to` · `depends_on` · `implements` · `calls` · `configured_by` ### Knowledge Graph --- ### Web Explorer Visualize the knowledge graph in your browser: ```bash megamemory serve ``` - Nodes are colored by kind and sized by edge count - Dashed edges show parent-child links; solid edges show relationships - Click any node to inspect summary, files, and edges - Search supports highlight/dim filtering - If port `4321` is taken, you'll be prompted to pick another ```bash megamemory serve --port 8080 # custom port ``` --- ### How It Works ``` src/ index.ts CLI entry + MCP server (9 tools) tools.ts Tool handlers (understand, get_concept, create, update, link, remove, list_conflicts, resolve_conflict) db.ts SQLite persistence (libsql, WAL mode, schema v3) embeddings.ts In-process embeddings (all-MiniLM-L6-v2, 384 dims) merge.ts Two-way merge engine for knowledge.db files merge-cli.ts CLI handlers for merge, conflicts, resolve commands types.ts TypeScript types cli-utils.ts Colored output + interactive prompts install.ts multi-target installer (opencode, Claude Code, Antigravity, Codex) web.ts HTTP server for graph explorer plugin/ megamemory.ts Opencode skill tool plugin commands/ bootstrap-memory.md /user command for initial population save-memory.md /user command to save session knowledge web/ index.html Single-file graph visualization (d3-force + Canvas) ``` - **Embeddings** — In-process via [Xenova/all-MiniLM-L6-v2](https://huggingface.co/Xenova/all-MiniLM-L6-v2) (ONNX, quantized). No API keys, and no network calls after the first model download. - **Storage** — SQLite with WAL mode, soft-delete history, and schema migrations (currently v3). - **Search** — Brute-force cosine similarity over node embeddings; fast enough for graphs with --keep left # keep the left version megamemory resolve --keep right # keep the right version megamemory resolve --keep both # keep both as separate concepts ``` #### AI-assisted resolution When an AI agent runs `/merge`, it calls `list_conflicts`, verifies both versions against current source files, then calls `resolve_conflict` with `resolved: {summary, why?, file_refs?}` plus a verification `reason`. It does not pick a side blindly; it resolves to what the codebase currently reflects. --- ### License [MIT](./LICENSE) ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [0xK3vin](https://github.com/0xK3vin) - **Source:** [0xK3vin/MegaMemory](https://github.com/0xK3vin/MegaMemory) - **License:** MIT Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-0xk3vin-megamemory - Seller: https://agentstack.voostack.com/s/0xk3vin - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.