selene

Selene is a desktop app that runs AI agents locally (optionally with cloud) and can connect agents to messaging channels like WhatsApp, Telegram, Slack, and Discord. It supports voice (STT/TTS), images/video generation, retrieval/memory, scheduling, and extensibility via plugins and MCP tools; it also provides a developer/internal API reference and Electron-based build system.

Evaluated Mar 30, 2026 (0d ago)
Homepage ↗ Repo ↗ Ai Ml ai-ml agents desktop electron mcp retrieval memory messaging voice images plugins local-llm
⚙ Agent Friendliness
45
/ 100
Can an agent use this?
🔒 Security
50
/ 100
Is it safe for agents?
⚡ Reliability
30
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
35
Documentation
55
Error Messages
0
Auth Simplicity
55
Rate Limits
20

🔒 Security

TLS Enforcement
70
Auth Strength
55
Scope Granularity
20
Dep. Hygiene
45
Secret Handling
55

Strengths inferred from README: app is distributed as signed installer/DMG, supports offline/local-first operation (reducing data exposure to third parties), and mentions an INTERNAL_API_SECRET env var for internal API auth. Gaps from provided content: no explicit description of TLS requirements for internal endpoints, no documented scope-based authorization, no clear secret handling/logging guarantees, and no security threat model or compliance posture. Dependency hygiene cannot be verified from provided data.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
40
Error Recovery
35
AF Security Reliability

Best When

You want on-device agent execution with optional cloud providers, and you’ll integrate through native desktop capabilities (chat channels, local model runtimes, MCP tools).

Avoid When

You need a well-specified, third-party-callable API (OpenAPI/SDK) with strong documented auth/rate-limit/error semantics for automated agent integration; you also may want to avoid deploying without reviewing the internal API/MCP docs and permission model.

Use Cases

  • Running personal or team-like AI agent workflows locally on a desktop
  • Connecting agent actions to chat channels (WhatsApp/Telegram/Slack/Discord) including attachments and voice notes
  • Building assistants that use retrieval/memory and scheduled tasks
  • Developing agent-capable tooling using hooks/plugins and MCP as an integration mechanism
  • Generating images and turning images into video with agent-controlled workflows

Not For

  • Environments that require a purely server-hosted API service (it’s a desktop app)
  • Use cases that need strict, formally documented public REST/GraphQL contracts for automation
  • Security-sensitive deployments that require clearly specified threat model, audited auth flows, and detailed operational guarantees from documentation alone

Interface

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

Authentication

Methods: WhatsApp QR-based pairing (native) Telegram bot token Slack Socket Mode (auth via app/bot configuration implied) Discord bot token Provider API keys or local-only (no API keys)
OAuth: Yes Scopes: No

README mentions one provider using Google OAuth (Antigravity free tier via Google OAuth) and developer runtime secrets via an INTERNAL_API_SECRET env var. Public API auth details, scopes, and token lifecycles are not specified in the provided content.

Pricing

Model: Mixed: local models (no direct per-use cost) plus
Free tier: Yes
Requires CC: No

No pricing page or explicit tiers/limits are provided in the provided content.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Desktop/mobile integration quality may vary by channel auth/pairing (QR tokens, bot tokens, Socket Mode).
  • MCP integration exists, but provided docs don’t describe tool contracts, error formats, or retry/idempotency semantics.
  • Internal API/auth details are not fully visible here; agents should not assume documented guarantees without checking docs/API.md and runtime behavior.
  • Offline vs cloud mode mixing may change latency/cost and permissions; ensure the agent knows which components run locally.

Alternatives

Full Evaluation Report

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

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.

6495
Packages Evaluated
19908
Need Evaluation
586
Need Re-evaluation
Community Powered