engram

by NickCirv · TypeScript · ★ 108

EngramX — the cached context spine for AI coding agents. 9 built-in providers + any MCP server as a 10-line plugin, pre-mortem mistake-guard, bi-temporal memory, Anthropic Auto-Memory bridge, SSE streaming packets, dual-emit AGENTS.md+CLAUDE.md. 89.1% measured real-world token savings, local SQLite, zero cloud.

#agent-memory#agent-tools#agents-md#ai#claude-code#claude-code-hooks#context-engineering#context-spine#cursor#developer-tools#engramx#hooks#knowledge-graph#llm#mcp#token-optimization#tree-sitter#typescript

Install

npx -y github:NickCirv/engram

Claude Desktop config

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "engram": {
      "command": "npx",
      "args": [
        "-y",
        "github:NickCirv/engram"
      ]
    }
  }
}

From the README

Install Page · Live Demo · Scene Table · rendered with Hyperframes Install · Quickstart · Dashboard · Benchmark · IDE Integrations · HTTP API · ECP Spec · Contributing Your AI coding agent keeps re-reading the same files. Every , every , every re-pays for context you've already paid for. **EngramX is the spine.** It intercepts every file read at the tool boundary, answers from a pre-assembled context packet held in **three layers of cache** — a knowledge graph the agent has already "paid" to build, a per-provider SQLite cache of ex…

Read full README on GitHub →