人工智能记忆工具

Install in one prompt (any AI tool)

Paste this into Claude Desktop, Cursor, Codex, Claude Code, or Windsurf — the agent reads our setup guide, installs the SDK, configures the MCP server, and verifies the round-trip end-to-end. No terminal context-switching.

Install Mengram for me. Fetch the canonical install guide at
https://mengram.io/agent-install.txt and follow it precisely.
My email is YOUR_EMAIL_HERE.

Works in any agent with shell + file-edit + web-fetch tools. Prefer doing it manually? See the plain-text guide — it's structured for human eyes too.

---

→ ["Uses Python 3.12", "Deploys to Railway", "PostgreSQL with pgvector"]

```

→ Episode created → linked to "Deploy" procedure → failure detected → v3 created

```

and Railway. Recently debugged pgvector deployment. Prefers direct

Claude Code — Zero-Config Memory

Two commands. Claude Code remembers everything across sessions automatically.

pip install mengram-ai
mengram setup              # Sign up + install hooks (interactive)

Or manually: export MENGRAM_API_KEY=om-... → mengram hook install

What happens:

Session Start  →  Loads your cognitive profile (who you are, preferences, tech stack)
Every Prompt   →  Searches past sessions for relevant context (auto-recall)
After Response →  Saves new knowledge in background (auto-save)

No manual saves. No tool calls. Claude just knows what you worked on yesterday.

mengram hook status     # check what's installed
mengram hook uninstall  # remove all hooks

---

REST API

curl -X POST https://mengram.io/v1/add_file \ -H "Authorization: Bearer om-..." \ -F "file=@meeting-notes.pdf" \ -F "user_id=default"

</details>

<details>
<summary><b>JavaScript / TypeScript</b></summary>

await m.add([{ role: 'user', content: 'Fixed OOM by adding Redis cache layer' }]); const results = await m.searchAll('database issues'); // → { semantic: [...], episodic: [...], procedural: [...] }

</details>

<details>
<summary><b>REST API (curl)</b></summary>

Semantic — facts, preferences, knowledge

```python m.search("tech stack")

API Reference

Full interactive docs: mengram.io/docs

Add a conversation — auto-extracts facts, events, and workflows

m.add([ {"role": "user", "content": "Deployed to Railway today. Build passed but forgot migrations — DB crashed. Fixed by adding a pre-deploy check."}, ])

Procedural — workflows that evolve

Week 1:  "Deploy" → build → push → deploy
                                         ↓ FAILURE: forgot migrations
Week 2:  "Deploy" v2 → build → run migrations → push → deploy
                                                          ↓ FAILURE: OOM
Week 3:  "Deploy" v3 → build → run migrations → check memory → push → deploy ✅

This happens automatically when you report failures:

```python m.procedure_feedback(proc_id, success=False, context="OOM error on step 3", failed_at_step=3)

Integrations

mengram hook install

{
  "mcpServers": {
    "mengram": {
      "command": "mengram",
      "args": ["server", "--cloud"],
      "env": { "MENGRAM_API_KEY": "om-..." }
    }
  }
}

from langchain_mengram import (
    MengramRetriever,
    MengramChatMessageHistory,
)

retriever = MengramRetriever(api_key="om-...")
docs = retriever.invoke("deployment issues")

</td>
</tr>
<tr>
<td width="50%">

**OpenClaw**

Auto-recall before every turn, auto-capture after. 12 tools, slash commands, Graph RAG.

[GitHub](https://github.com/alibaizhanov/openclaw-mengram) · [npm](https://www.npmjs.com/package/openclaw-mengram)

</td>
<td width="50%">

**CLI** — Full command-line interface

[Docs](https://mengram.io/docs/cli)

</td>
</tr>
<tr>
<td width="50%">

**Claude Managed Agents** — MCP memory for hosted agents

30 memory tools via MCP. [Docs](https://mengram.io/docs/managed-agents)

</td>
<td width="50%">

**n8n** — HTTP nodes for any workflow