Quoroom Room

Open-source swarm intelligence engine enabling self-governing AI agent collectives with queen/worker architecture, quorum voting, and local-first execution via MCP. Supports local models (Ollama), Claude Code CLI, Codex CLI, and paid APIs. Features include EVM wallet integration (USDC/USDT across multiple chains), semantic memory with vector embeddings, skill versioning, self-modification with audit trails, task scheduling (cron/webhook), and ERC-8004 on-chain identity.

Evaluated Mar 08, 2026 (0d ago) vcurrent
Homepage ↗ Repo ↗ AI & Machine Learning swarm agents mcp governance quorum-voting crypto-wallet autonomous-agents claude-code codex ollama
⚙ Agent Friendliness
70
/ 100
Can an agent use this?
🔒 Security
65
/ 100
Is it safe for agents?
⚡ Reliability
49
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
72
Documentation
78
Error Messages
60
Auth Simplicity
62
Rate Limits
72

🔒 Security

TLS Enforcement
55
Auth Strength
65
Scope Granularity
70
Dep. Hygiene
65
Secret Handling
70

Dual-token auth. AES-256-GCM for wallet keys. Runtime credential retrieval prevents log exposure. But: very new project (Feb 2026), crypto wallets with real money, self-modification capabilities, and auto-update from quoroom.io — significant trust surface.

⚡ Reliability

Uptime/SLA
45
Version Stability
50
Breaking Changes
45
Error Recovery
55
AF Security Reliability

Best When

You want to experiment with autonomous AI agent collectives that can govern themselves, earn money via crypto wallets, and run locally with full transparency.

Avoid When

You need a simple agent framework, are uncomfortable with crypto wallet integration, or need enterprise-grade multi-tenant scaling.

Use Cases

  • Running autonomous AI agent swarms locally with governance (voting, goal decomposition, progress tracking)
  • Building earning-focused agent collectives with integrated EVM crypto wallets
  • Scheduling recurring agent tasks with cron, webhooks, and external service triggers
  • Creating self-modifying agent systems with full audit trails and one-click revert

Not For

  • Simple single-agent tasks where swarm overhead is unnecessary
  • Production financial operations without thorough security review
  • Environments without Node.js v20 support
  • Teams needing distributed horizontal scaling (one execution host per room)

Interface

REST API
Yes
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
Yes

Authentication

Methods: api_key
OAuth: No Scopes: Yes

Dual-token system: agent tokens (room-level operations), user tokens (full keeper access), member tokens (read-only + limited collaboration). Webhook security via per-task and per-room tokens with 30 req/min rate limit.

Pricing

Model: freemium
Free tier: Yes
Requires CC: No

Free local-first operation. Paid model APIs optional. Cloud runtime at quoroom.io for hosted swarms.

Agent Metadata

Idempotent
Unknown
Retry Guidance
Not documented

Known Gotchas

  • Very new project (Feb 2026) — expect breaking changes and incomplete features
  • Free local model (Ollama qwen3-coder:30b) is fail-closed with no paid fallback
  • Cloud swarm provisions one execution host per room — no distributed scaling
  • EVM wallet integration means real money at risk — AES-256-GCM encrypted but still high stakes
  • Self-modification audit history persists indefinitely with no automatic cleanup
  • Public rooms send heartbeats every 5 minutes — disclosure is opt-in but easy to enable accidentally
  • 30MB+ repo size suggests significant bundled assets
  • macOS auto-update checks every 4 hours from quoroom.io servers

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for Quoroom Room.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-08.

6961
Packages Evaluated
25669
Need Evaluation
173
Need Re-evaluation
Community Powered