Agents Index

Engram

Online

Memory for AI agent teams across tools, sessions, repositories, and teammates.

Visit publisherConnectJSON

What it can do: 17 tools

  • engram_startBegin meaningful work in a repository with a Markdown briefing: session id, ranked private/public memory, workspace guidance and optional checklists. Unlike engram_smarter, this includes workspace onboarding/activation g
  • engram_rehydrateRecover interrupted work after compaction, resume or lost context. Returns Markdown checkpoints, decisions, gotchas, open loops and recent events. Unlike engram_start, this restores the prior journal when available; unli
  • engram_recall read-onlyAnswer one concrete question from authenticated workspace/public memory before deciding or debugging. Unlike engram_smarter, this retrieves question-specific evidence without task checklists; unlike engram_get_context, i
  • engram_storeSave independently maintained knowledge privately. Use type+content for one claim, optionally with claim metadata; use claims for 1–32 separate units committed together, each with its own id, lifecycle and outcomes. Neve
  • engram_report_outcomeRecord whether a recalled memory helped; returns a confirmation. Use its exact memory_id and evidence in detail. success=false may include failure_reason; outdated marks obsolete knowledge, while success raises confidenc
  • engram_cross_pollinate read-onlyReuse a lesson solved in another repository before rebuilding a shared pattern. Unlike engram_recall or engram_smarter, this explicitly excludes target_repo from source searches and adds transfer lessons and quality gate
  • engram_smarter read-onlyBrief a materially different task within the same session. Unlike engram_recall, this combines goal-focused memories with optional procedural checklists; unlike engram_get_context, it ranks evidence for the task instead
  • engram_reflectCheckpoint a milestone or handoff for later recovery with engram_rehydrate. Supply at least one of summary, learnings, used_memories or feedback. Returns Markdown with stored/skipped counts, outcomes and next actions. Us
  • engram_skill read-onlyFind a procedural checklist before a repeatable task. Omit skill or pass an empty string to list available names; otherwise load a name such as code-review or skill:code-review. Returns JSON with available_skills/usage
  • engram_get_context read-onlyAudit repository knowledge by category: conventions, gotchas, patterns, solutions and architecture. Unlike engram_recall or engram_smarter, this searches each category separately and returns five sample arrays for covera
  • engram_setup read-onlyExplain onboarding and inspect the authenticated workspace when an agent needs setup guidance. Returns one JSON response with plan/counts/limits, tool groups, activation checklist and suggested calls; no pagination or in
  • engram_proof read-onlyAudit adoption before a rollout or when checking whether the workspace is using memory and reporting outcomes. Takes no arguments. Returns JSON with memory-bank breakdowns, learning-loop activity, proof points and a benc
  • engram_list_sessions read-onlyFind an exact session_id before recovery, closing or a handoff. Unlike engram_rehydrate, this lists bounded metadata without replaying journal content or changing a session. Returns JSON sessions with member/client attri
  • engram_close_sessionFinish an exact journal at a real completion or handoff. Unlike engram_reflect, this atomically closes the session after saving a supplied final summary or confirming an existing checkpoint. Durable memories and journal
  • engram_retract_memoryWithdraw an exact private memory that should no longer guide agents. Unlike engram_store with supersedes_memory_ids, this needs no replacement and keeps the content for explicit restoration. Unlike engram_delete_memory,
  • engram_restore_memoryMake an explicitly retracted private memory available again. Unlike engram_store, this restores the original ID/content; storing matching retired content returns 409 rather than silently reviving it. Returns JSON memory_
  • engram_delete_memoryPreview or permanently erase one private memory and its explicit derived patterns from the live database. Unlike engram_retract_memory, execution cannot be undone. Requires a human workspace OWNER API key; OAuth agents a

Connect it

Claude Code
claude mcp add --transport http engram https://api.engram.tools/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://api.engram.tools/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "engram": {
      "url": "https://api.engram.tools/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "engram": {
      "type": "http",
      "url": "https://api.engram.tools/mcp"
    }
  }
}

Questions

What does Engram do?

Memory for AI agent teams across tools, sessions, repositories, and teammates. It exposes 17 tools to AI assistants.

What tools does Engram provide?

17 tools, including engram_start, engram_rehydrate, engram_recall, engram_store, engram_report_outcome, engram_cross_pollinate, engram_smarter, engram_reflect, engram_skill, engram_get_context, engram_setup, engram_proof….

How do I connect Engram to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://api.engram.tools/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does Engram require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Engram online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes Engram?

engram.tools. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Memory & RAG