Snipara Agents

Use Snipara to give AI agents shared Project Intelligence, reviewed memory inputs, shared team state, and explicit task coordination. This is not a separate product wedge; it is the agent capability layer on top of Snipara Workflow Continuity.

The Problem

AI agents today are stateless. Every conversation starts fresh. Past decisions, user preferences, learned patterns — all gone. This creates several challenges:

• No memory persistence — Agents forget everything between sessions
• No knowledge sharing— One agent's discovery stays siloed
• No coordination— Multiple agents can't work together effectively
• Repeated context loading — Same docs fetched over and over

The Solution

Snipara Agents is easiest to read as four product blocks: durable memory, multi-agent coordination, hierarchical tasks, and sandboxed proof. They are not all exposed through the same connection: the lean Hosted MCP surface covers the core agent path, Companion owns local workflow/memory helpers, and Orchestrator owns htasks, proof gates, and explicit coordination.

How It Works

Snipara Agents exposes tools that an authorized client can use to store, retrieve, and share memory. The LLM decides when to remember something important and when to recall relevant context, subject to the active plan and caller surface. Reviewed memory also adds lifecycle controls so agents can verify evidence, invalidate stale knowledge, and supersede old decisions safely.

// Agent remembers a user preference

snipara_remember({

  text: "User prefers TypeScript over JavaScript",

  type: "preference",

  ttl_days: 30

})

// Later, agent recalls relevant memories

snipara_recall({

  query: "What programming language does the user prefer?",

  limit: 5

})

Quick Start

1. Connect your existing project

Start from the repository or folder you already work in and use create-snipara to configure Hosted MCP and create or match the remote Snipara project boundary. Use the dashboard only when you do not have a local project folder yet.

2. Run the guided setup or get an API key

The recommended path is npx create-snipara@latestfrom the existing folder. If you configure MCP manually, navigate to your project's API Keys tab and create a key to authenticate MCP requests.

3. Add MCP Configuration and verify

Add Snipara to your MCP client configuration:

{

  "mcpServers": {

    "snipara": {

      "type": "http",

      "url": "https://api.snipara.com/mcp/YOUR_PROJECT_SLUG",

      "headers": {

        "X-API-Key": "YOUR_API_KEY"

      }

    }

  }

}

Restart your AI client or open a new session, then ask it to run snipara_help. If Snipara tools are missing, run npx create-snipara@latest doctor --client <client> from the same folder.

4. Start Using Agent Tools

Once configured, your LLM will have access to memory and coordination tools. Ask it to "remember this for next time" or "recall what we discussed about authentication".

MCP Tools

Highlighted rows are new Hierarchical Task tools. See all 17 htask tools →

Plans and availability

Agent memory, team memory, htasks, and coordination tools are plan-scoped capabilities inside Snipara. Use the pricing page for current plan packaging instead of treating Agents as a separate subscription.

Next Steps