airi

A self-hosted (and client-distributed) virtual character/AI companion platform that supports multimodal interaction (chat, voice input/output, and client integrations like Telegram/Discord) and in-game automation/play for titles like Minecraft and Factorio, with VRM and Live2D rendering/animation support. Primarily described as an application rather than an API service.

Evaluated Mar 29, 2026 (0d ago)
Homepage ↗ Repo ↗ Ai Ml ai-companion vtuber digital-human multimodal voice-chat vrm live2d games self-hosted
⚙ Agent Friendliness
12
/ 100
Can an agent use this?
🔒 Security
28
/ 100
Is it safe for agents?
⚡ Reliability
26
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
35
Error Messages
0
Auth Simplicity
30
Rate Limits
0

🔒 Security

TLS Enforcement
40
Auth Strength
25
Scope Granularity
20
Dep. Hygiene
35
Secret Handling
25

Based on provided data only: TLS/auth/error handling/rate limiting for any service endpoints are not documented. The project integrates with third-party services (Discord/Telegram, potentially ElevenLabs/LLM providers), which typically requires handling secrets (API keys/webhooks). Without explicit documentation, scores are conservative.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
40
Error Recovery
20
AF Security Reliability

Best When

You want a self-hosted interactive desktop/web client experience for an AI character (including media/voice and avatar rendering) rather than a developer API.

Avoid When

You need a well-specified REST/GraphQL/SDK interface, predictable API error semantics, or documented auth/rate limiting for programmatic agent workflows.

Use Cases

  • Run an owner-controlled AI “digital companion/waifu” experience with chat and voice
  • Integrate a virtual character into Discord/Telegram chats
  • Use as a companion for game “co-play”/automation (e.g., Minecraft/Factorio)
  • Render/animate VRM and Live2D avatars with automated expressions/movement
  • Prototype an on-prem AI character stack using web/desktop clients

Not For

  • Providing a stable, documented machine-to-machine API for agents (no API contract shown in provided data)
  • Strict compliance-oriented deployments without reviewing data handling and model provider usage
  • Highly reliable production service usage without further operational evidence

Interface

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

Authentication

Methods: Not specified in provided content; likely integration tokens/credentials for third-party platforms (e.g., Discord/Telegram) and model/voice provider keys
OAuth: No Scopes: No

The provided README content describes capabilities and distribution but does not document API authentication flows, tokens, or scopes for a first-class service API.

Pricing

Free tier: No
Requires CC: No

No pricing tiers/free tier information for the project itself were found in the provided README/manifest excerpt.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Not a clearly specified tool/API surface for agents; agent integration would likely require scraping UI behavior or reverse-engineering internal endpoints rather than using a documented contract.
  • Potential heavy local-resource usage (GPU/CUDA/Metal) and complex multimodal pipelines; agent workflows may fail due to runtime environment differences rather than API semantics.

Alternatives

Full Evaluation Report

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

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 2026-03-29.

5347
Packages Evaluated
21056
Need Evaluation
586
Need Re-evaluation
Community Powered