TokST Documentation

TokST provides durable shared context for people and Agents. Cloud MCP is the recommended entry point for Memory, context, knowledge bases, files, and workspace governance.

Recommended: Cloud MCP

Connect your Agent to https://api.tokst.com/mcp, approve access once, and let it search before work and save confirmed long-term knowledge as structured Markdown. This path works across compatible clients without installing a local binary.

Read Getting Started for the connection flow, MCP Server Reference for the complete tool contract, and Skill Guide for the recommended Agent behavior.

Why TokST Exists

AI sessions are temporary, while projects continue for weeks or years. Important context often lives across chat histories, local notes, repositories, and individual tools. TokST turns that context into a managed knowledge layer with stable ownership, explicit scope, searchable records, and a reviewable lifecycle.

TokST is designed for workflows such as:

• preserving product and architecture decisions with their rationale
• carrying coding conventions and user preferences across agents
• preparing a focused context snapshot before an agent starts work
• handing completed work, open tasks, and known risks to another agent
• keeping reference documents and files next to the memories they support
• separating personal, project, and team knowledge with clear boundaries

How Data Is Organized

TokST uses a simple hierarchy so every memory has a clear home.

A workspace can contain multiple atlases. Each atlas can define routing keywords, allowing TokST to place new memories in the most relevant knowledge base when an explicit atlas is not supplied.

Sessions capture normal Agent activity. Memories retain durable information that remains useful across later work. A Task is created only when a user explicitly assigns work to one or more connected Agents.

What You Can Remember

Every memory has one of six types. Types make context snapshots and filtered searches easier to understand.

Memories can also include a title, tags, source metadata, timestamps, and attachments. Files uploaded through the web dashboard can be up to 500 MB; remote MCP uploads can be up to 50 MB per file.

The Memory Workflow

1. Authenticate with browser setup, the dashboard, or a tk_live_... API key for automation.
2. Select a workspace and atlas to define ownership and subject scope.
3. Remember a fact, decision, preference, task, architecture record, or note.
4. Retrieve relevant knowledge with search or a grouped context snapshot.
5. Maintain the record by updating, appending, archiving, or restoring it. The Dashboard archived view provides permanent cleanup.
6. Continue in another agent or tool through the same shared state.

The basic Agent loop uses Cloud MCP: search or load context before work, save only a confirmed durable conclusion, then retain its ID for later review. The corresponding tools are tokst_search, tokst_context, and tokst_remember.

Search and Context

TokST uses keyword-first search with semantic fallback. Direct text matches return immediately. When the configured embedding service is available and keywords do not produce a result, TokST searches 1536-dimensional vectors within the authenticated user's accessible scope.

Use search for a specific question. Use a context snapshot to give an agent a compact, grouped view of recent facts, decisions, preferences, tasks, architecture records, and notes before work begins.

Choose an Interface

All interfaces operate on the same workspaces, atlases, memories, and access rules.

Advanced Runtime Workflows

The standalone CLI connects supported local Agent endpoints to the Dashboard. It enables automatic Session capture, explicitly assigned Task execution, Agent communication, endpoint health, and local diagnostics. These device-side workflows complement Cloud MCP and use their own records.

Sessions capture normal Agent work and create reviewable compilations with optional long-term memory extraction. Tasks are user-created work orders that route a defined action to one or more connected Agents. The two records link through source context while preserving their separate histories.

Read the Sessions guide for automatic capture, compilation, privacy, diagnostics, and memory extraction. Read the Tasks guide for assignment, execution, results, and recovery.

Security and Data Boundaries

• API keys inherit the account and workspace access available to their owner.
• Memory searches and resource lookups stay within the authenticated user's accessible workspaces.
• API keys should live in environment variables, secret managers, or client configuration.
• Signed attachment download links expire after 15 minutes.
• Archiving keeps a memory recoverable. The Dashboard archived view provides user-confirmed permanent cleanup.

Start Here