Add it to Claude Code
claude mcp add -e "CONNAPSE_ADMIN_EMAIL=${CONNAPSE_ADMIN_EMAIL}" -e "CONNAPSE_ADMIN_PASSWORD=${CONNAPSE_ADMIN_PASSWORD}" -e "Identity__Jwt__Secret=${Identity__Jwt__Secret}" connapse -- docker run -i --rm connapse-mcpCONNAPSE_ADMIN_EMAILCONNAPSE_ADMIN_PASSWORDIdentity__Jwt__SecretMake your agent remember this setup
connapse's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.
npx conare@latestFree · one command · indexes the sessions already on disk. Set up in the browser instead →
What it does
- Hybrid vector and keyword search for accurate retrieval
- Persistent memory for AI agents across different sessions
- Support for multiple storage backends including S3, Azure Blob, and MinIO
- Container-isolated knowledge bases for privacy
- Runtime configuration of embedding providers and chunking parameters
Tools 2
search_knowledgePerform hybrid vector and keyword search across the knowledge base.upload_documentUpload a document to the knowledge base for indexing.Environment Variables
CONNAPSE_ADMIN_EMAILrequiredEmail address for the admin accountCONNAPSE_ADMIN_PASSWORDrequiredPassword for the admin accountIdentity__Jwt__SecretrequiredSecret key for JWT authenticationTry it
Original README from Destrayon/Connapse
<em>Stop losing context between AI sessions. Give your agents persistent, searchable memory.</em>
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, Azure Blob Storage containers, 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.
<details> <summary><strong>🤖 AI Agent Integration</strong> — Claude queries and builds your knowledge base via MCP</summary></details> <details> <summary><strong>🎛️ Your Knowledge, Your Rules</strong> — Runtime configuration without restarting</summary>AI agents query your knowledge base through the MCP server, receiving structured answers with source citations from your documents.
</details>Switch embedding providers, tune chunking parameters, and configure search — all at runtime, without restarting.
📦 Quick Start
git clone https://github.com/Destrayon/Connapse.git && cd Connapse && docker-compose up -d
# Open http://localhost:5001
Prerequisites
- Docker & Docker Compose
- .NET 10 SDK (for development)
- (Optional) Ollama for local embeddings
Run with Docker Compose
# Clone the repository
git clone https://github.com/Destrayon/Connapse.git
cd Connapse
# Set required auth environment variables (or use a .env file)
export [email protected]
export CONNAPSE_ADMIN_PASSWORD=YourSecurePassword123!
export Identity__Jwt__Secret=$(openssl rand -base64 64)
# Start all services (PostgreSQL, MinIO, Web App)
docker-compose up -d
# Open http://localhost:5001 — log in with the admin credentials above
The first run will:
- Pull Docker images (~2-5 minutes)
- Initialize PostgreSQL with pgvector extension and run EF Core migrations
- Create MinIO buckets
- Seed the admin account (from env vars) and start the web application
Development Setup
# Start infrastructure only (database + object storage)
docker-compose up -d postgres minio
# Run the web app locally
dotnet run --project src/Connapse.Web
# Run all tests
dotnet test
# Run just unit tests
dotnet test --filter "Category=Unit"