Decay-weighted vector memory for AI agents — 83 MCP tools: store, recall, search, knowledge graphs.
Decay-weighted vector memory for AI agents — 83 MCP tools: store, recall, search, knowledge graphs.
MCP server for Dakera AI. Gives any MCP-compatible AI agent persistent, queryable memory — with smart token management built in.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"dakera": {
"command": "dakera-mcp",
"env": {
"DAKERA_API_URL": "http://localhost:3000",
"DAKERA_API_KEY": "YOUR_DAKERA_API_KEY"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| DAKERA_API_URL | Declared in the maintainer’s client configuration. | Check documentation |
| DAKERA_API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Connect your AI assistant to Forgejo repositories. Manage issues, pull requests, files, and more through natural language.
Generate beautiful Excalidraw architecture diagrams with auto-layout and component styling
Persistent memory for AI agents — local JSON, zero config, no server required.
An MCP (Model Context Protocol) server providing hybrid semantic search over code across a set of GitHub repositories that you list in `config.yaml`.