io.github.HBarefoot/engram MCP Server
io.github.HBarefoot/engram
What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the io.github.HBarefoot/engram MCP server?
Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.
How to install io.github.HBarefoot/engram
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"engram": {
"command": "npx",
"args": [
"-y",
"@hbarefoot/engram",
"start",
"--mcp-only"
]
}
}
}Related MCP servers
Venture intelligence for autonomous agents with discovery, scoring, and workspace automation.
View repository →Let Claude and other LLMs watch videos locally with intelligent frame extraction and audio transcription.

RAGScore
Generate QA datasets and evaluate RAG systems with failure diagnosis using any LLM.

Haiku DeFi MCP
DeFi execution for AI agents — swap, lend, bridge, and yield across 22 chains.
Emite CFDIs 4.0 y resuelve claves del SAT para agentes de IA (México), con permisos por API key.

io.github.HMAKT99/akf
Trust metadata for AI agents — check files before building on them, stamp verified work.

