super-agent-party

Super Agent Party is a self-hosted AI desktop companion that bundles chat/agent capabilities, task automation, bots for multiple messaging/live-streaming platforms, a browser automation feature, and an extension system. It exposes an OpenAI-compatible HTTP API (base_url http://localhost:3456/v1) and an MCP endpoint (e.g., http://127.0.0.1:3456/mcp) intended for external agent integration.

Evaluated Mar 30, 2026 (0d ago)
Homepage ↗ Repo ↗ Ai Ml ai agents mcp openai-compatible desktop-app automation bots extensions electron self-hosted
⚙ Agent Friendliness
48
/ 100
Can an agent use this?
🔒 Security
34
/ 100
Is it safe for agents?
⚡ Reliability
29
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
45
Documentation
55
Error Messages
0
Auth Simplicity
55
Rate Limits
5

🔒 Security

TLS Enforcement
20
Auth Strength
45
Scope Granularity
20
Dep. Hygiene
35
Secret Handling
45

Uses HTTPS? Not specified; local examples suggest plain http. Auth method details (token handling, rotation, scopes, expiry) are not described in the excerpt. Docker Compose mentions default username/password (root/pass), which is a security risk if exposed. TLS, rate-limit headers, and structured error guidance are not documented in the provided text, limiting safe automated usage.

⚡ Reliability

Uptime/SLA
0
Version Stability
50
Breaking Changes
35
Error Recovery
30
AF Security Reliability

Best When

You want a locally hosted, agent-capable desktop/web app with extensibility (plugins) and you can tolerate that some integration/security aspects are not fully specified in the README excerpt.

Avoid When

You need strong, clearly documented auth/rate-limit/error-code guarantees for third-party automated clients, or you cannot operate the software in a controlled environment.

Use Cases

  • Run AI agents locally with OpenAI-compatible chat completions
  • Use MCP to connect external agents to locally hosted tools
  • Background task automation that can control the computer (desktop/browser)
  • Multi-role group chat with persistent/long-term memory (per docs claims)
  • Deploy AI messaging bots to platforms (QQ/Feishu/DingTalk/Telegram/Discord/Slack, per docs)
  • Deploy live streaming bots (Bilibili/YouTube/Twitch, per docs)
  • Install and develop extensions to add capabilities

Not For

  • Highly regulated production environments without additional security review and hardening
  • Use cases requiring well-specified, documented public API contracts (OpenAPI spec, schemas, formal error codes) for reliable automated integration
  • Teams that require OAuth/enterprise-grade authentication and fine-grained scopes documented publicly

Interface

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

Authentication

Methods: API key (implied by OpenAI-compatible api_key usage for /v1)
OAuth: No Scopes: No

README shows using OpenAI client with api_key and base_url for local /v1, and mentions a token management page (http://localhost:3456/token.html) in the Docker Compose section. Specific auth requirements, validation behavior, and scope model are not described in the provided excerpt.

Pricing

Free tier: No
Requires CC: No

Appears self-hosted; no public pricing information in provided content.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Local desktop/web automation and bots may require extra permissions (network access, browser automation permissions) not covered in API docs excerpt.
  • MCP is configured via a config snippet, but tool list, schemas, and error formats are not included in provided README excerpt.
  • Default Docker Compose credentials are mentioned (root/pass) for initial login; agents/services should not run with defaults.

Alternatives

Full Evaluation Report

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

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 2026-03-30.

6530
Packages Evaluated
19873
Need Evaluation
586
Need Re-evaluation
Community Powered