nexu

nexu is an open-source desktop client that runs an OpenClaw agent inside IM apps (WeChat, Feishu, Slack, Discord, etc.), providing a GUI to connect, chat, and manage model/provider access for the agent.

Evaluated Mar 30, 2026 (0d ago)
Homepage ↗ Repo ↗ Communication ai-agent desktop im-integration openclaw wewechat feishu slack discord byok oauth local-first electron typescript
⚙ Agent Friendliness
24
/ 100
Can an agent use this?
🔒 Security
47
/ 100
Is it safe for agents?
⚡ Reliability
25
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
40
Error Messages
0
Auth Simplicity
70
Rate Limits
0

🔒 Security

TLS Enforcement
70
Auth Strength
60
Scope Granularity
20
Dep. Hygiene
40
Secret Handling
40

From the provided README only: the app is claimed to be local-first and data stays on the machine (not a verifiable guarantee here). OAuth support is claimed for some providers and a BYO API key option exists, but there is no provided detail on OAuth scope granularity, token storage, TLS enforcement, secret redaction, or dependency/security practices.

⚡ Reliability

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

Best When

You want a GUI desktop integration to connect an OpenClaw-style agent into common IM channels and you’re comfortable with a client-side (local) deployment model.

Avoid When

You require a fully specified developer API (OpenAPI/SDK/webhooks/MCP) with documented rate limits and machine-consumable error codes.

Use Cases

  • Connect an OpenClaw agent to WeChat/Feishu/Slack/Discord and chat with it from IM
  • Use model providers (e.g., Gemini) via built-in selection or BYO API keys
  • OAuth-based login for some model providers (as described in README)
  • Operate agent workflows in-team via the connected IM channels
  • Local-first usage posture (as claimed in README) for keeping data on the machine

Not For

  • Headless/server-only deployments where a REST/GraphQL API is required
  • Use cases that require a clearly documented public API contract for programmatic agent control
  • Organizations needing audited, explicitly documented security/privacy guarantees beyond README claims

Interface

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

Authentication

Methods: OAuth login (for certain model providers, as described) Bring your own API key (no account/login)
OAuth: Yes Scopes: No

README claims OAuth for some providers (e.g., MiniMax, OpenAI Codex, GLM) and a BYO API key mode with no account. No explicit mention of fine-grained OAuth scopes or token handling details.

Pricing

Free tier: Yes
Requires CC: No

Client is described as free; model costs are implied to be handled via user-provided API keys or providers' own billing. No detailed pricing table or rate/usage plan is provided in the supplied content.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • No machine-consumable API contract (OpenAPI/MCP/SDK) is shown in provided content; agent integrations likely depend on internal behavior or UI-based workflows
  • Rate limiting and structured error formats are not documented in supplied README
  • OAuth/BYO key flows are described at a high level; token lifecycle and failure modes are not documented

Alternatives

Full Evaluation Report

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

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.

6465
Packages Evaluated
19938
Need Evaluation
586
Need Re-evaluation
Community Powered