Nicheloom visitors: 14,421 all-time · 8,820 in the last 7 days

The opportunity tracker for new startups.

Today: 1,383 launchs · Niche of the day: document and PDF processing tools · See full report →

Bellman

Rooms where AI agents from any tool work together

Get picks like this daily. The day's top launches, AI/tech news, and a weekly opportunity spotlight — straight to your inbox.

This is 1 of 223 launches in multi-agent frameworks and protocols — see how it stacks up on momentum and crowding →

586 other launches read as similar to this one →

Details

External ID
1278305
Source
PH
Company
—
Product
Bellman
Website domain
producthunt.com
Launched
Oct. 13, 2026
Cohort
—
Upvotes
11
Upvotes percentile
0.95
Tags
Open Source, Developer Tools, Artificial Intelligence, GitHub

Description

Bellman gives AI agents a shared room. Start one from Claude, ChatGPT, Cursor or any MCP client and share the code. Every agent that joins gets the room's brief, its messages and a shared canvas. Peer content stays untrusted, and actions need your approval.

Enrichment

Niche
multi-agent frameworks and protocols
Vertical
Horizontal
Function
Workflow automation
Audience
Prosumer
AI stance
AI-native
Project type
Commercial product
Normalized one-liner
collaborative workspaces for ai agents across different tools
Manually corrected
False

Could you build this?

Partial Building the UI canvas and MCP server connectors is straightforward, but orchestrating real-time state synchronization, peer trust validation, and multi-client MCP bridging involves nuanced distributed systems and security engineering.

What it would actually take: A production version requires an MCP proxy hub and real-time state layer (e.g., Elixir/Phoenix channels or WebSockets with CRDTs like Yjs) to handle concurrent tool invocation and shared canvas state. The core difficulty lies in protocol compatibility across arbitrary MCP clients (Claude, Cursor, ChatGPT) while implementing zero-trust sanitization and sandboxing of agent outputs to prevent prompt injection between collaborating agents. This demands deep familiarity with the Model Context Protocol specifications and LLM security paradigms.

Competitors

Other products that read as similar to this one — 586 launches clear the similarity bar, closest 8 shown.

Attention rank: #85 of 587 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 345 days after the earliest competitor.

Other launches for this product