saya

v0.1.0

Connect agents to Saya's live, trust-graded team brain over remote MCP.

CodexClaude Code1 Skill

By creative-intLicense: MIT0 GitHub starsUpdated 2 weeks ago

Directory evidence

Runtimes: Codex and Claude Code
Parsed components: 1 skill or MCP entry
Source updated: Oct 3, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install saya for Codex and Claude Code

Installs for the current user

codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add saya@agent-plugin-marketplace

Paste and run these commands in a terminal with Codex. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/creative-int/saya-plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

saya/

├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
└── skills/saya-team-brain/SKILL.md

Included Skills1

saya-team-brainskills/saya-team-brain/SKILL.md

Usage guidance for querying a team's live Saya brain through MCP before answering from guesswork. Use when a task depends on team memory, captured workspace context, prior decisions, workspace norms, known skills, or whether a fact is verified, candidate, or deprecated. Also answers to "ask-team" and "team-context". The MCP connection is the product surface; this skill teaches when and how to use it well.

Plugin manifests2

.codex-plugin/plugin.json

{
  "name": "saya",
  "version": "0.1.0",
  "description": "Connect agents to Saya's live, trust-graded team brain over remote MCP.",
  "author": {
    "name": "creative-int",
    "email": "[email protected]"
  },
  "homepage": "https://saya.computer",
  "repository": "https://github.com/creative-int/saya-plugins.git",
  "license": "MIT",
  "keywords": [
    "saya",
    "mcp",
    "team-memory",
    "slack",
    "agent-context",
    "workspace-context",
    "team-brain"
  ],
  "skills": "./skills",
  "mcpServers": "./.mcp.json",
  "interface": {
    "displayName": "Saya",
    "shortDescription": "Connect agents to Saya's live, trust-graded team brain over remote MCP.",
    "longDescription": "Saya lets an external agent ask the team brain before it guesses. The production MCP exposes a deliberately small live surface: `saya_context` returns workspace-scoped, provenance- and trust-graded team knowledge from Saya's Convex brain; `saya_act` provides the approval-first `save_memory` action path; and `saya_status` reports live MCP and Convex health. Access is per-team OAuth bearer auth plus workspace membership. The MCP origin is `https://mcp.saya.computer/mcp`.",
    "developerName": "creative-int",
    "category": "Productivity",
    "logo": "./assets/logo.png",
    "metadata": {
      "tools": [
        {
          "name": "saya_context",
          "scope": "saya.context",
          "description": "Read bounded, workspace-scoped Saya context: provenance-graded team knowledge, lifecycle status, trust grade, decisions, skills, and captured workspace memory."
        },
        {
          "name": "saya_act",
          "scope": "saya.act",
          "description": "Save approved team memory through Saya's curated, idempotent, approval-first action path."
        },
        {
          "name": "saya_status",
          "scope": "saya.status",
          "description": "Check live Saya MCP readiness, tool availability, auth posture, and Convex bridge health."
        }
      ],
      "scopes": [
        "saya.context",
        "saya.act",
        "saya.status"
      ],
      "readiness": "Live prod: the MCP origin serves the real Convex-backed team brain. Authenticated saya_context queries return trust-graded workspace knowledge; saya_act is approval-first save_memory; saya_status reports live bridge health. It is served at the mcp.saya.computer custom domain.",
      "mcp": {
        "id": "saya",
        "url": "https://mcp.saya.computer/mcp",
        "transport": "streamable-http"
      }
    }
  }
}

.claude-plugin/plugin.json

{
  "name": "saya",
  "version": "0.1.0",
  "description": "Connect agents to Saya's live, trust-graded team brain over remote MCP.",
  "author": {
    "name": "creative-int",
    "email": "[email protected]"
  },
  "homepage": "https://saya.computer",
  "repository": "https://github.com/creative-int/saya-plugins.git",
  "license": "MIT",
  "keywords": [
    "saya",
    "mcp",
    "team-memory",
    "slack",
    "agent-context",
    "workspace-context",
    "team-brain"
  ],
  "displayName": "Saya",
  "skills": "./skills",
  "mcpServers": "./.mcp.json",
  "metadata": {
    "tools": [
      {
        "name": "saya_context",
        "scope": "saya.context",
        "description": "Read bounded, workspace-scoped Saya context: provenance-graded team knowledge, lifecycle status, trust grade, decisions, skills, and captured workspace memory."
      },
      {
        "name": "saya_act",
        "scope": "saya.act",
        "description": "Save approved team memory through Saya's curated, idempotent, approval-first action path."
      },
      {
        "name": "saya_status",
        "scope": "saya.status",
        "description": "Check live Saya MCP readiness, tool availability, auth posture, and Convex bridge health."
      }
    ],
    "scopes": [
      "saya.context",
      "saya.act",
      "saya.status"
    ],
    "readiness": "Live prod: the MCP origin serves the real Convex-backed team brain. Authenticated saya_context queries return trust-graded workspace knowledge; saya_act is approval-first save_memory; saya_status reports live bridge health. It is served at the mcp.saya.computer custom domain.",
    "mcp": {
      "id": "saya",
      "url": "https://mcp.saya.computer/mcp",
      "transport": "streamable-http"
    }
  }
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[saya on Agent Plugins Marketplace](https://pluginsmp.com/plugins/saya)