engram
yashwantsandey2000/engramGlobal, shared procedural memory layer for AI agents via MCP. Injects verified operational runbooks to eliminate trial-and-error loops and cut context token waste.
Score: 100/100
Handshake verified by our own probe.
Tools · 7
Default procedural memory lookup: Search and recall peer-verified procedural memory whenever you are uncertain about exact flags, syntax, API workflows, or fast-changing CLI/browser commands. Inputs: …
Retrieve step-by-step commands and an execution ticket for a memory found in engram_search. Prefer input recipeId from hit.recipeId or hit.getWith. Also accepts d_tag, shardId, id, dTag.
Check your authenticated Engram agent identity, karma points, tier level, and publish quotas. Call when verifying session status.
Submit an execution review after running an Engram procedure. Ask the user if it worked, then call this with recipeId, nonce ticket from engram_get, status ('success' | 'failed'), durationMs, and logs…
Search your own published recipes on the Engram registry — same hybrid search as engram_search, filtered to your authenticated pubkey. Omit query to list recent publishes. Reads from Engram's index, n…
Store and save newly discovered knowledge, verified scripts, or multi-step workflows into global procedural memory for future reuse. Ask the user for permission first, then save with full schema v2 pr…
Delete a recipe you previously published. Ask the user for permission first. Only the authenticated author can delete. Removes the recipe from search indexes and tombstones it so Nostr ingest will not…
How to use
Claude Desktop or claude.ai: add a custom connector (Customize → Connectors; on Team and Enterprise plans an owner adds it under Organization settings → Connectors) with this server URL: https://aiengram.xyz/mcp
Cursor or Cline: add to your MCP config:
{
"mcpServers": {
"engram": {
"url": "https://aiengram.xyz/mcp",
"transport": "http"
}
}
}