cd /news/ai-agents/persistent-memory-for-ai-agents-with… · home topics ai-agents article
[ARTICLE · art-121460] src=dev.to ↗ pub= topic=ai-agents verified=true sentiment=· neutral

Persistent Memory for AI Agents with Sutra MCP: Private, Portable, and Reusable

Developer Shivnath Tathe built Sutra MCP, a hosted Model Context Protocol service that gives AI agents a private, portable memory layer and reusable skill library. The service, published in the Official MCP Registry, lets users store durable project decisions and workflows that can be retrieved selectively across different AI clients, with explicit user authorization for memory writes.

read6 min views1 publishedSep 4, 2026

Your AI agent understands the project today. Tomorrow, you open another agent and explain the same architecture, preferences, and decisions again.

The model changed. The chat history stayed behind. Your context did not move with you.

I built Sutra MCP to make that handoff explicit: one private, portable memory layer and reusable skill library that can be accessed by supported AI agents through the Model Context Protocol.

This article shows what that means, how the pieces fit together, and how to connect an MCP client in a few minutes.

Sutra is a hosted MCP service for user-controlled AI agent memory and reusable skills.

Instead of treating every conversation as memory, Sutra exposes deliberate operations to:

SKILL.md

workflows separately from personal memoryThe same Streamable HTTP endpoint works across clients:

https://sutra-c3or.onrender.com/mcp

Sutra is published in the Official MCP Registry as io.github.shivnathtathe/sutra.

Agent memory and agent skills are often discussed as if they are interchangeable. They are not.

Layer Question it answers Example
Memory What should this agent know about me or this project? "This service uses UTC internally and displays local time at the UI boundary."
Skill How should an agent perform a repeatable task? A tested release checklist stored as a reusable SKILL.md workflow.

Memory carries durable facts, preferences, corrections, and decisions. Skills carry reusable operating knowledge.

Sutra keeps both available through MCP without permanently injecting everything into every prompt.

Here is a practical handoff you can try after connecting two supported clients.

In Agent A, ask:

Use Sutra to save this project decision in my payments cluster:
"All internal timestamps use UTC; localization happens only at the presentation boundary."
I authorize this memory write.

The explicit authorization matters. A normal conversation should not silently become permanent memory.

Open Agent B and ask:

Search my Sutra payments cluster for our timestamp convention.
Use only the context relevant to this question.

Agent B does not need Agent A's chat transcript. It retrieves the specific durable decision through Sutra.

In any connected agent, ask:

List my enabled Sutra skills. If there is a release checklist, show me its resource index before  any supporting files.

This keeps procedural knowledge discoverable without filling the context window with every workflow you have ever saved.

That is the core idea: store intentionally, retrieve selectively, and reuse across agents.

First, create a Sutra account. Then choose the authentication method supported by your client.

Authentication Best for Behavior
OAuth 2.1 Remote MCP clients with browser authorization The client requests consent and stores a revocable grant.
API key Clients that expect an Authorization header
Create a dedicated, revocable key and keep it in the client's secret storage.

Add this to ~/.cursor/mcp.json

:

{
  "mcpServers": {
    "sutra": {
      "url": "https://sutra-c3or.onrender.com/mcp"
    }
  }
}

Connect the server and complete Sutra's browser authorization flow.

Merge this into your global or project opencode.json

:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sutra": {
      "type": "remote",
      "url": "https://sutra-c3or.onrender.com/mcp",
      "oauth": {}
    }
  }
}

Authorize and inspect the connection:

opencode mcp auth sutra
opencode mcp list

Create .vscode/mcp.json

, or merge this into your user MCP configuration:

{
  "inputs": [
    {
      "id": "sutra-api-key",
      "type": "promptString",
      "description": "Sutra API key",
      "password": true
    }
  ],
  "servers": {
    "sutra": {
      "type": "http",
      "url": "https://sutra-c3or.onrender.com/mcp",
      "headers": {
        "Authorization": "Bearer ${input:sutra-api-key}"
      }
    }
  }
}

VS Code requests the key through a masked input instead of storing it in the configuration file.

npm install -g @shivnathtathe/sutra-cli
sutra connect claude-code

The CLI requests a dedicated key and writes the supported local configuration.

Current instructions for 22 clients are available in the Sutra integration catalog.

Sutra separates reads from deliberate writes, uploads, and exports.

Tool Access Purpose
read_context
Read Load the user's shared identity context.
search_memory
Read Find targeted memories by keyword.
list_clusters
Read Discover available project clusters.
get_cluster
Read Load one known project cluster.
write_observation
Write Save one durable preference, decision, correction, or fact.
export_all
Export Export all user memories for data portability.
list_skills
Read Discover skills explicitly enabled by the user.
get_skill
Read Load an enabled skill and its resource index.
get_skill_resource
Read Read one supporting resource from an enabled skill.
upload_skill
Write Upload a new immutable skill version after explicit authorization.

After authorization, use this connection check:

Use Sutra to list my project clusters, then ask before saving anything.

Your client should discover all ten tools.

Sutra is a hosted service, not a local-only database. Private means access-controlled, user-specific context with explicit data boundaries; it does not mean data never leaves your machine.

Sutra:

Sutra does not:

The connected AI client has its own data-handling policies. Review both the Sutra Privacy Policy and your client's policy before sending sensitive information.

Never commit a Sutra API key, OAuth token, password, or memory export to source control.

Approach Strength Tradeoff
Chat history Automatic and convenient Usually tied to one product or conversation.
Project instruction files Transparent and versionable Often project-specific and loaded as static context.
Local memory servers Maximum infrastructure control You operate the database, runtime, backups, and client connectivity.
Vendor-native memory Deep integration with one assistant Portability depends on that vendor.
Sutra MCP Hosted, selective memory plus reusable skills across supported agents Requires a Sutra account and network connection.

Sutra is not intended to replace every memory architecture. It is for people who want their useful context and repeatable workflows to outlast one chat window or one AI client.

The Sutra MCP integrations repository contains the open manifests, client configurations, documentation, and artwork needed to connect MCP clients. Those integration files are MIT licensed.

The hosted backend, dashboard, APIs, infrastructure, datasets, service implementation, and trademarks remain proprietary and are not included in that repository.

You can inspect Sutra through:

Connect Sutra to two agents you already use. Save one non-sensitive project decision with explicit authorization, retrieve it from the second agent, and see whether that small handoff removes a repeated explanation from your workflow.

If context should outlast the chat window, it should also remain under the user's control.

Create your private Sutra workspace or review the integration guide.

I would value feedback on three questions:

── more in #ai-agents 4 stories · sorted by recency
── more on @shivnath tathe 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/persistent-memory-fo…] indexed:0 read:6min 2026-09-04 ·