AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Multi-Agent/
TecAdRiseBot
TecAdRiseBot logo

TecAdRiseBot

Active·★ 0·MIT·Updated 2026-10-20

TecAdRiseBot is a local desktop multi-agent chat built with Electron, React, TypeScript and the Cursor TypeScript SDK. The README presents it as a free, open-source alternative to Grok Bot, adds that it is not a clone and not an official Grok or xAI product, and says agents run on your PC through the SDK. It is MIT licensed.

The feature list covers a multi-agent sidebar with colours and search, a per-agent Soul of sticky instructions, one customisable SYSTEM.md for all agents, a long-term wiki-style memory (an Obsidian-like index, notes and a log), messages between agents, shared skills, common MCP servers plus per-agent MCP JSON (Playwright runs through local npx and AgentMail is hosted HTTP), a scheduler with loop, interval, daily, weekly, once and cron routines, a local token usage table and attachments. An external local HTTP API listens on 127.0.0.1:8787, and the README says agents can read a snapshot of their own configuration and may patch themselves.

It needs Node.js 22.13+ and npm 10+ and targets Windows 10 and 11, with Mac possible later; the quick start is `git clone`, `npm install` and `npm run dev`, then paste a Cursor API key into Settings. The key is stored with Electron safeStorage rather than in the chat database, and the usage table is not an invoice because Cursor bills the API key. The README states the control plane is localhost-only with no authentication. This is a new project with 0 stars at the time we checked. This review is based on the README and repository data; we have not run it ourselves.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#cursor#desktop#electron#mcp#multi-agent#react#typescript#Multi-Agent
$ Install
$ git clone https://github.com/tecadrise-ai/TecAdRiseBot.git && cd TecAdRiseBot && npm install && npm run dev
↗ Visit site★ GitHub
01

Features

01Multi-agent sidebar with per-agent model, instructions and sticky rules (Soul)
02Global and per-agent MCP configuration, with Playwright and AgentMail bundled
03Routines on interval, daily, weekly, once or cron schedules
04Inter-agent messaging and a shared memory wiki
05Localhost-only control API and API key kept in Electron safeStorage
02

Why choose it

+Multi-agent chat with per-agent Soul, shared memory, shared skills and messages between agents
+Routines with loop, interval, daily, weekly, once and cron schedules, plus a local token usage table
+Common and per-agent MCP configuration; API key kept in Electron safeStorage; MIT licensed
+Localhost HTTP API so external tools can control the agents
03

Trade-offs

!It needs a Cursor API key, and Cursor bills that key; the local usage table is not an invoice
!The localhost control API has no authentication, so other local processes could reach it
!Targets Windows 10 and 11; Mac is only mentioned as possible later
!Brand new with 0 stars at the time we checked, and agents that can patch their own configuration need watching
05

Maintenance check

ActiveChecked: 2026-10-22
Last commit
2026-10-20
Commits, last 90 days
38
Releases, last 90 days
1
Latest release
demo-video (2026-10-19)
Open issues
0
Recent issues with at least one comment
—
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 0, 0, 0, 0, 0, 0, 6, 21, 0, 0, 5, 6

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

04

Who it fits

Pick it if
  • You already use the Cursor SDK and want several named agents with shared memory and routines on your PC.
  • You want agents that run on a schedule and can be controlled by a local HTTP API.
  • You want an MIT-licensed desktop app you can read and modify.
Look elsewhere if
  • You do not use Cursor or do not want a Cursor API key to be the model backend.
  • You are on macOS or Linux and want a supported build today.
  • You need authenticated access to the control API.
06

Compatibility

Windows
Windows 10/11
Verified via docs
Cursor SDK
Requires Cursor API key
Verified via docs
MCP
Global and per-agent
Verified via docs
Node.js
Node 22.13+
Verified via docs
07

Quick start

1
$ git clone https://github.com/tecadrise-ai/TecAdRiseBot.git
2
$ cd TecAdRiseBot
3
$ npm install
4
$ npm run dev
08

Use cases

↳Run several specialised agents on a desktop and let them hand work to each other
↳Schedule recurring agent tasks such as status updates or checklists
↳Script the agents through the local HTTP control API
09

Alternatives

⚡Top VS:
VSeigent★15.6k→VSharness-sdk★8.9k→VSask-user-questions-mcp★147→VSkeryx★36→
eigent logo
eigent★ 15.6k
Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex
VSCompare→
harness-sdk logo
harness-sdk★ 8.9k
Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
VSCompare→
ask-user-questions-mcp logo
ask-user-questions-mcp★ 147
Better 'AskUserQuestion' - A lightweight MCP server/OpenCode plugin/Agent Skills + CLI tool that allows your LLMs ask questions to you. Be the human in the human-in-the-loop!
VSCompare→
keryx logo
keryx★ 36
Keryx: The Fullstack TypeScript Framework for MCP and APIs
VSCompare→
hive logo
hive★ 11.1k
Multi-Agent Harness for Production AI
VSCompare→
commonly logo
commonly★ 1.4k
Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and workstation. Any runtime, your infra — no per-agent fees.
VSCompare→
mcp-app-typescript-template logo
mcp-app-typescript-template★ 21
ChatGPT app template using Pomerium, OpenAI Apps SDK and Model Context Protocol (MCP), with a Node.js server and React widgets.
VSCompare→
gitwarren-app logo
gitwarren-app★ 18
A cross-platform desktop app for doing local code reviews of your own git repositories. Single user, single machine, no server, no account.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs05Maintenance check04Who it fits06Compatibility07Quick start08Use cases09Alternatives
tecadrise-ai /
TecAdRiseBot
↗

MIT Electron desktop app for chatting with several Cursor SDK agents, with shared memory, routines, MCP and a localhost control API

0MIT
Last commit3d ago
StatusActive
CategoryMulti-Agent
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.