Destrayon/Connapse

> *Your AI agents forget everything between sessions. Connapse fixes that.*
Every time you start a new conversation, your AI agent starts from zero — no memory of past research, no access to your documents, no accumulated knowledge. Connapse is an open-source knowledge backend that gives agents persistent, searchable memory. Upload documents or point it at your existing Amazon S3 buckets or local filesystems. Agents query and build their own research corpus via 11 MCP tools, REST API, or CLI. Container-isolated, hybrid search (vector + keyword), self-hosted and private. Deploy in 60 seconds with Docker. Built on .NET 10.
🤖 AI Agent Integration — Claude queries and builds your knowledge base via MCP
> *AI agents query your knowledge base through the MCP server, receiving structured answers with source citations from your documents.*
🎛️ Your Knowledge, Your Rules — Runtime configuration without restarting
> *Switch embedding providers, tune chunking parameters, and configure search — all at runtime, without restarting.*
---
📦 Quick Start
Prerequisites
- Docker & Docker Compose
- .NET 10 SDK (for development)
- (Optional) Ollama for local embeddings
Run with Docker Compose
The first run will:
1. Pull Docker images (~2-5 minutes)
2. Initialize PostgreSQL with pgvector extension and run EF Core migrations
3. Create MinIO buckets
4. Seed the admin account (from env vars) and start the web application
Development Setup
Command-line client
The connapse CLI is published separately at Destrayon/connapse-cli.
Install:
Get started:
Using with Claude (MCP)
Connapse includes a Model Context Protocol (MCP) server for integration with Claude and any MCP client.
**Setup**: Create an agent API key via the web UI (Settings → Agent API Keys), then add the config snippet for your client:
Claude Code (CLI)
Claude Desktop
Add to your claude_desktop_config.json:
VS Code / Cursor
Add to your .vscode/settings.json (VS Code) or Cursor MCP config:
VS Code will prompt for the API key on first use.
The MCP server exposes:
| Tool | Description |
|------|-------------|
| container_create | Create a new container for organizing files |
| container_list | List all containers with document counts |
| container_delete | Delete a container |
| container_stats | Get container statistics (documents, chunks, storage, embeddings) |
| upload_file | Upload a single file to a container |
| bulk_upload | Upload up to 100 files in one operation |
| list_files | List files and folders at a path |
| get_document | Retrieve full parsed text content of a document |
| delete_file | Delete a single file from a container |
| bulk_delete | Delete up to 100 files in one operation |
| search_knowledge | Semantic, keyword, or hybrid search within a container |
> **Full reference:** See docs/mcp-tools.md for parameter tables, return formats, error cases, and usage examples.
> **Containers and sources**: container_list tags each scope managed or source. A **source** is an external system Connapse mirrors read-only — searchable, but never browsable and never writable. list_files and every write tool resolve containers only; pass a source id and they report it as not found. See docs/connectors.md.
Example prompts — what to ask your agent
- *"Create a container called 'project-research' for my architecture notes"*
- *"Upload all the PDFs in my downloads folder to the project-research container"*
- *"Search my project-research container for information about rate limiting strategies"*
- *"List all files in the /notes/ folder of my project-research container"*
- *"Get the full text of distributed-systems-notes.md from project-research"*
- *"Delete meeting-2026-03-14.md from project-research and upload this updated version"*
- *"Delete all files in the /drafts/ folder of project-research"*
- *"How many documents and chunks are in my project-research container?"*
Troubleshooting
**Connection refused on localhost:5001** — Docker not running or port conflict. Check docker compose ps and docker compose logs web.