Stele

dev.stele-aiv1.0.0Updated Sep 30, 2026

Shared project memory for AI coding agents: decisions, lessons, risks and tasks in one graph.

VerifiedStreamable HTTPWeb executableKnowledge & Memory Productivity & Workflow

Overview

AI-generated overview

Gives AI coding agents a shared project knowledge graph to recall decisions, capture lessons and risks, and coordinate tasks across sessions.

What it does: Stele is a hosted shared project memory for AI agents and their teammates. Through the connector an agent can recall what a project already knows, trace why a decision was made and what it replaced, capture decisions, lessons, risks and gaps as they happen, and create, claim and complete tasks so two agents do not duplicate work. It also supports handing off cleanly to the next agent, session or teammate. Tools are split into read-only, write, and a single destructive tier that always prompts before acting.
When to use it: Worth adding when several agents or people work on the same project over time and context is being lost between sessions. It suits teams that want prior decisions, risks and open tasks to surface automatically instead of being re-explained each time.
Requirements: A Stele account and at least one project; signing in through the connector creates the account if needed, and no paid plan is required to connect. It is a remote hosted MCP server reached over Streamable HTTP at the provider's endpoint, with OAuth 2.1 and dynamic client registration; the client registers itself on first connection and opens Stele's sign-in page. No credentials or secrets are stored in the plugin repository. An optional command-line tool exists for local repositories but is not…

Before you install

The connector writes to a shared project graph: capturing decisions, lessons and risks, and creating, claiming or completing tasks changes data other agents and teammates see. A single destructive tool covers consequential operations such as cancelling, force-claiming, unlinking, retiring and merging, and always prompts before acting. Access is limited to projects you own or belong to, and project content is stored in the hosted service rather than locally.

Installation

In SourceWeft

Open Stele in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "stele": {
      "type": "http",
      "url": "https://app.stele-ai.dev/api/mcp"
    }
  }
}

README

Stele — MCP connector plugin

Stele is shared project memory and work tracking for AI agents and the people who work with them. It keeps decisions, lessons, risks, documents, components, and tasks in one durable knowledge graph, so work can continue across agent clients without losing the project's history.

This repository is the plugin that connects an agent client to Stele. It follows the Agent Plugins open standard and contains configuration and documentation only.

What's in here

plugin.json          Agent Plugins manifestmcp.json             Stele's hosted MCP server, over Streamable HTTPskills/stele/        Guidance on when and how an agent should use Stele

plugin.json          Agent Plugins manifestmcp.json             Stele's hosted MCP server, over Streamable HTTPskills/stele/        Guidance on when and how an agent should use Stele

There is no build step, no bundled binary, and no executable code. Stele itself runs as a hosted service; this plugin only points at it.

What the connector does

Once connected, an agent can:

Recall what a project already knows before it acts, instead of starting cold.
Trace why a decision was made, what caused it, and what it replaced.
Capture decisions, lessons, risks, and gaps as they happen, so they survive the conversation that produced them.
Coordinate tasks — create, claim, and complete them — so two agents don't duplicate each other's work.
Hand off cleanly to the next agent, session, or teammate.

The bundled skill tells the agent when reaching for these tools is appropriate and when it isn't, which matters on a surface where the agent chooses for itself.

Working locally

This connector is the whole product on a chat or IDE surface. If you also work in a local repository, Stele's command-line tool adds automatic recall — relevant prior decisions, risks, and open work surface as you go, rather than only when someone thinks to ask. See the documentation.

The tool is optional. Nothing in this plugin requires it, downloads it, or runs it for you.

Requirements

A Stele account and at least one project. Signing in through the connector creates the account if you don't already have one, and no paid plan is required to connect.

Authentication

OAuth 2.1 with dynamic client registration (RFC 7591). Your client registers itself on first connection and opens Stele's sign-in page. Access is limited to the projects you own or belong to.

No credentials, tokens, or secrets are stored in this repository, and none are needed to install it.

Tool safety

Stele's tools are split so a client can tell safe operations from unsafe ones. Read-only tools are annotated as such and never modify data. Write tools are separate. Every consequential operation — cancelling, force-claiming, unlinking, retiring, merging — lives in a single destructive tool that always prompts before acting. No tool mixes these tiers.

License

MIT — see LICENSE.

Source: README.md at commit 7d6a9f4

Tools

Tool metadata has not been indexed yet.

Version history

v1.0.0LatestSep 30, 2026