Shared persistent memory across Claude Chat, Code, and Cowork.
┌───────────┐ ┌───────────┐ ┌───────────┐
│ Chat │ │ Code │ │ Cowork │
└─────┬─────┘ └─────┬─────┘ └─────┬─────┘
│ │ │
└────────┬────────┴────────┬─────────┘
│ │
┌─────▼─────────────────▼─────┐
│ Acheron MCP │
│ ┌───────────────────────┐ │
│ │ ~/.acheron/bridge.db │ │
│ └───────────────────────┘ │
└─────────────────────────────┘
Local · No cloudSave a decision in Chat. Retrieve it in Cowork. Search for it from Code. All local, all offline, zero configuration.
This connects Acheron to all surfaces — Chat, Code, Cowork, and Dispatch. This is the recommended setup for full cross-surface bridging.
Open Claude Desktop → Settings → Developer → Edit Config, then add:
{
"mcpServers": {
"acheron": {
"command": "npx",
"args": ["-y", "acheron-mcp-server"]
}
}
}Restart Claude Desktop.
If you only need Acheron in Claude Code (terminal / IDE):
claude mcp add acheron -- npx -y acheron-mcp-serverRequires Node.js 20+. Native build tools may be needed for better-sqlite3 (details).
Related MCP server: mcp-openmemory
Just talk naturally. Acheron's tool descriptions are written so Claude uses them automatically.
Save context — say "remember this", "save this decision", "note that we chose X":
"Remember: we're using Next.js App Router for the acme-site project."
Search context — say "what did I decide about...", "find my notes on...":
"What did we decide about the authentication approach?"
Browse context — say "show me my preferences", "list all decisions for this project":
"Show me everything saved for acme-site."
Acheron is an MCP server. It stores context in a local SQLite database (~/.acheron/bridge.db) with full-text search. No cloud, no network calls, no telemetry. Data never leaves your machine.
Six tools, all prefixed bridge_:
Tool | Purpose |
| Remember decisions, preferences, insights, notes |
| Retrieve full details of a saved context |
| Full-text search across all saved contexts |
| Browse and filter by project, surface, type, tags |
| Forget a saved context |
| Overview of what's stored |
better-sqlite3 install fails? You need native build tools:
macOS: xcode-select --install
Linux: sudo apt install build-essential
Windows: Visual Studio Build Tools
Database issues? Delete ~/.acheron/bridge.db — Acheron recreates it on next start.
MIT
Permanently delete a saved context. Use when the user says "forget this", "delete that", "remove that note", "I don't need that anymore", or "that's outdated, remove it". Requires the context ID — use search or list first to find it.
Inputs: id (required).
Retrieve the full details of a previously saved context by its ID. Use this after finding a context via search or list, when the user wants to see the complete content of a specific saved memory. Typically used as a follow-up: "show me that decision", "give me the full details on that one".
Inputs: id (required), response_format.
Browse and filter all saved contexts. Use when the user asks "what have I saved?", "show me my decisions", "what do I have for this project?", "list my preferences", "what did we do recently?", "show everything tagged with...", or "what happened in Cowork?". Unlike search (keyword-based), this tool browses by category — filter by project, surface, type, tags, or date. Returns newest entries first.
Inputs: tags, type, limit, since, +4 more.
Remember something for later. Use this when the user says things like "remember this", "save this", "note this", "keep this for later", "don't forget", or when an important decision, preference, or insight comes up that should persist across conversations. This saves context that will be available in ALL Claude surfaces (Chat, Code, Cowork) — even in future sessions. Use proactively when you recognize something worth remembering: a decision made, a user preference expressed, a lesson learned, a key file identified, or a workflow established.
Inputs: type (required), content (required), source_surface (required), tags, +2 more.
Search through everything that has been saved across conversations. Use when the user asks "what did I decide about...", "what do we know about...", "did I save anything about...", "find my notes on...", "what was that thing about...", or any question that might be answered by previously saved context. Also use proactively when the user asks a question that saved context might answer — check before saying "I don't have that information". Searches across all surfaces (Chat, Code, Cowork) and all projects.
Inputs: query (required), type, limit, offset, +3 more.
Show a summary of all saved knowledge: how many contexts are stored, broken down by surface (Chat/Code/Cowork) and type (decisions, preferences, insights, etc.), database size, and date range. Use when the user asks "how much have I saved?", "give me an overview", "what's in my memory?", or "how big is my context database?".
Inputs: response_format.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 6 tools
Each tool targets a distinct action (save, get, list, search, delete, status) on contexts with no overlap. The descriptions clearly differentiate when to use each.
All tool names follow a consistent pattern: bridge_verb_context (e.g., bridge_save_context, bridge_list_contexts). The verbs are clear and uniform.
Six tools cover the essential operations for a context management system (CRUD plus search and overview) without being excessive or sparse.
The tool set provides create, read, list/ browse, search, delete, and status. An update operation is missing, but contexts may be intended as immutable entries, making the set largely complete.
Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.
Persistent context for Claude. Your AI always knows your projects and next actions across sessions.
Your own memory inside ChatGPT and Claude, with the source of every note.
Long-term memory for Claude, ChatGPT, Cursor: search, save and organize notes, links, docs, videos.
