Claude-Zeroclaw
ZeroClaw Claude is a lightweight daemon that integrates with Claude Code to run scheduled jobs (cron), send/receive messages via a Telegram bot (text/voice), and provide a local web dashboard for monitoring, chat, logs, and memory. It claims “zero API overhead” by operating within the existing Claude Code/Anthropic workflow and spawning a Claude CLI subprocess via @anthropic-ai/claude-agent-sdk.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Strengths (from README): dashboard is intended for localhost only; README claims the OAuth token is not read/transmitted by ZeroClaw and that the Claude CLI subprocess manages OAuth from ~/.claude/. Concerns: Telegram bot token and optional Groq API key are stored in a local JSON config; the README does not describe secure secret storage/redaction, logging behavior for secrets, CSRF/auth for the dashboard, or transport security for any external-facing components (beyond implied local dashboard). Dependency hygiene and vulnerability posture are not verifiable from the provided manifest/README (manifest shows no deps, but that conflicts with README architecture claims like Express/grammy, so dependency details are unclear).
⚡ Reliability
Best When
You want local, on-machine automation and monitoring around Claude Code, with personal messaging via Telegram, and you’re comfortable running a background daemon and providing Telegram (and optionally Groq) credentials.
Avoid When
You need a documented public API contract, fine-grained enterprise security posture, or guaranteed reliability/SLA with observable operational metrics and rollback/change management.
Use Cases
- • Run recurring automations (e.g., weekly summaries, status checks)
- • Receive prompts and deliver outputs through Telegram, including voice transcription
- • Provide a local operations console: job management, run history, logs, and memory inspection
- • Maintain conversational/session continuity and structured memory for Claude Code workflows
Not For
- • Exposing an internet-facing control plane (dashboard is stated to be localhost-only)
- • Strict environments requiring formal enterprise compliance/audits (not evidenced in the provided README)
- • Use cases needing a standards-based public REST/GraphQL API or webhooks for external systems
Interface
Authentication
Auth details for the Claude side are described as handled by the spawned claude CLI using ~/.claude/. The README does not document explicit OAuth scopes or scope granularity for this project itself.
Pricing
No pricing model for the tool itself is provided in the README; it depends on your Claude Code subscription and optionally Groq for transcription.
Agent Metadata
Known Gotchas
- ⚠ Dashboard is stated as localhost-only; remote agent access may fail without SSH tunneling/reverse proxy (not documented).
- ⚠ Cron job execution and Telegram delivery semantics are not specified; agent-driven retries may duplicate actions if operations are not idempotent.
- ⚠ No explicit API/interface for programmatic job creation from an external agent is documented; integration appears to be via Claude Code commands/hooks and the local dashboard.
- ⚠ Local-only web UI port (3742) may conflict with existing services.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for Claude-Zeroclaw.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.