ScalyClaw — The AI That Scales With You

Dashboard

Real-time system health at a glance — node status, models, budget, channels, and workers, all auto-refreshing.

ScalyClaw Dashboard

Overview

Mind

Usage

Channels

Models

Agents

Skills

Memory

Vault

MCP

Scheduler

Engagement

Security

Logs

Workers

Jobs

Overview

↻ Refresh

Node

Hostnamemac-studio

Addresslocalhost:3000

Uptime6h 32m

Version1.4.2

Memory128 MB

Models

Chat3

Embedding1

Usage

Messages312

Input Tokens271,300

Output Tokens16,700

Total Calls594

Budget

Month Cost$12.4832

Limit$50.00

ModeHard

of $50.00

Agents

Count3

Skills

Count5

Memory

Stored847

Channels

telegramdiscordslack

MCP

Servers2

Tools17

Workers

Count2

Scheduler

Active Jobs4

Jobs

Active12

Mind

Save

IDENTITY.mdSOUL.mdUSER.md

Usage

⚙ Settings ↻

Today7d30dThis MonthAll Time From To

Today's Cost

$2.48

of $5.00/day

Month Cost

$12.48

of $50.00/mo

Total Cost

$12.48

Input Tokens

271,300

Output Tokens

16,700

API Calls

594

By ModelBy Type

Model	Provider	In Tokens	Out Tokens	In Cost	Out Cost	Total	Calls
claude-sonnet-4-6	Anthropic	98,400	34,300	$0.30	$0.20	$0.50	312
gpt-4o	OpenAI	71,200	23,300	$0.18	$0.10	$0.28	187
gemini-2.0-flash	Google	38,700	5,400	$0.02	$0.01	$0.03	95

Daily Cost

Daily Tokens

Channels

Save

TelegramDiscordSlackWhatsAppSignalTeams

Enabled

Bot Token

Allowlist (User IDs)

DM Policy

Group Policy

Text Chunk Limit

Media Max MB

Models

+ Add Model + Add Embedding ↻

Chat ModelsEmbedding Models

ID	Name	Provider	Temp	Max Tok	Context	Pri	Wt	In $/M	Out $/M	Capabilities
cs46	claude-sonnet-4-6	Anthropic	0.7	4096	200K	1	1	$3	$15	tool image	✎ 🗑 Test
gpt4o	gpt-4o	OpenAI	0.7	4096	128K	2	1	$2.5	$10	tool image	✎ 🗑 Test
gf20	gemini-2.0-flash	Google	0.5	8192	1M	3	1	$0.1	$0.4	tool	✎ 🗑 Test

Agents

+ New Agent ↻

ID	Name	Description	Models	Skills	Tools	MCPs
research	research-agent	Web research & summarize	auto	web-search	8	filesystem	✎ 🗑
code	code-agent	Write & review code	claude-sonnet	exec-js exec-py	12	—	✎ 🗑
skill-creator	skill-creator	Creates new skills	auto	—	5	—	locked

Skills

⬆ Upload ↻

ID	Name	Description	Lang
web-search	Web Search	Search using Brave API	js	📄 🗑
summarize	Summarizer	Condenses text to bullets	python	📄 🗑
exec-code	Code Runner	Execute arbitrary code	js	📄 🗑

Memory

+ Store ⚙

	Subject	Type	Tags	Confidence	Updated
▸	User prefers dark mode UI	fact	preference	High	Feb 24	🗑
▸	Project uses Bun runtime	fact	project	High	Feb 23	🗑
▸	Alice's deadline is March 1	analysis	person	Low	Feb 22	🗑

Vault

+ Add Secret ↻

Name	Value	Actions
OPENAI_API_KEY	••••••••	Reveal Copy Delete
ANTHROPIC_API_KEY	••••••••	Reveal Copy Delete
TELEGRAM_BOT_TOKEN	••••••••	Reveal Copy Delete

MCP Servers

+ Add Server Import JSON ↻

	ID	Transport	Status	Tools
▸	filesystem	stdio	connected	12	✎ ↻ 🗑
▸	web-search	http	error	0	✎ ↻ 🗑
▸	code-runner	sse	disconnected	5	✎ ↻ 🗑

Scheduler

+ Reminder + Recurrent ↻

RemindersTasks

ActiveAllCompletedCancelledFailed

ID	Type	Description	Cron	Next Run	State	Created
r-001	one-time	Check in with team	—	Feb 24 14:00	Active	Feb 24	✓ 🗑
r-002	recurrent	Daily standup reminder	0 9 * * *	Feb 25 09:00	Active	Feb 20	✓ 🗑
r-003	one-time	Pay rent	—	—	Cancelled	Feb 18	🗑

Engagement

Trigger Now Discard Save

GeneralQuiet HoursTriggers

Enabled

Model

Cron Pattern

Idle Threshold (min)

Cooldown (sec)

Max Per Day

Security

Discard Save

Message GuardSkill GuardAgent GuardCommand Shield

Enabled

Model

Layer 1 — Echo Guard

Similarity Threshold

Layer 2 — Content Guard

Checks for injection, social engineering, and harmful content

Logs

↻

NodeWorkers

1m5m10m30m1hRange

allinfowarnerrordebug

10:32:14.521 INFO [orchestrator] message received channelId=telegram:12345

10:32:14.892 INFO [tool] exec_code started jobId=98

10:32:15.103 ERROR [worker] connection timeout after 5000ms

10:32:15.440 WARN [guard] echo similarity 0.91 — blocked repeated message

10:32:16.001 INFO [orchestrator] tool result received jobId=98

10:32:16.312 INFO [channel] sending reply channelId=telegram:12345 chunks=2

10:32:17.891 INFO [memory] stored 3 new facts from conversation

10:32:18.440 WARN [budget] daily spend $2.48 approaching threshold (80%)

Workers

↻ Refresh

mac-studio.local

localhost:4001

StartedFeb 24 08:00

Uptime6h 32m

Concurrency4

Version1.4.2

web-server-01

192.168.1.10:4001

StartedFeb 24 07:30

Uptime7h 02m

Concurrency8

Version1.4.2

Jobs

⚙ ↻ Auto-refresh

AllMessagesAgentsToolsProactiveSchedulerSystem

activewaitingcompletedfailed (2)delayed

ID	Name	Queue	Created	Processed
48291	process-message	messages	14:01:22	14:01:23	👁 ✓ ✗
48290	exec-code	tools	14:01:10	14:01:11	👁 ✓ ✗
48285	delegate-agent	agents	13:58:44	13:58:45	👁 ✓ ✗

Pending Messages

Channel	Messages	Types	Oldest
telegram:12345	2	text	14:01:20

1 / 16

Features

Persistent Memory

Hybrid vector + full-text search. Your AI automatically extracts and recalls facts from every conversation. It truly learns you.

Every Channel

Discord, Telegram, Slack, WhatsApp, Signal, Teams, or the built-in gateway. One assistant, one memory, all your conversations.

Autonomous Agents

Delegate complex work to specialized sub-agents with their own models, tools, and skill access. They think so you don't have to.

Extensible Skills

Write skills in JavaScript, Python, Rust, or Bash. Auto-dependency install, hot-reload, and zip deployment. Your AI can even write its own.

Multi-Layer Security

LLM-powered guards validate every message, skill, and agent. Echo guard, content guard, command shield, and code validation. Fail-closed by default.

MCP Integration

Connect any Model Context Protocol server. Tools are discovered automatically and become first-class citizens. Zero glue code required.

Scalable Workers

Deploy workers anywhere. Same machine or remote, they auto-connect via Redis and BullMQ. Scale execution without touching the core.

Zero-Downtime Reload

Skills, agents, config, and MCP servers reload live via Redis pub/sub. Update anything without restarting. No interruptions, ever.

Budget Control

Monthly and daily limits with hard/soft enforcement. Per-model tracking, configurable alert thresholds. Never get a surprise bill again.

Security

Security by Default

Three LLM-powered guards, an encrypted vault, and container-ready workers. Every layer is designed to fail closed — if anything looks wrong, it gets blocked.

Echo Guard detects prompt injection attacks
Content Guard blocks harmful requests
Skill & Agent Guards validate code and definitions
Command Shield blocks dangerous shell commands with pattern matching
Vault stores secrets in Redis — never exposed in messages, memory, or logs
You can run Workers in containers for full execution sandboxing

Echo Guard

LLM repeats the message; if similarity < 0.7, injection detected. Blocked.

Content Guard

Analyzes for social engineering, harmful content, jailbreak attempts.

Skill & Agent Guard

Validates code for malicious payloads and excessive permission requests.

Command Shield

Deterministic pattern matching blocks dangerous shell commands before execution. No LLM needed.

Vault

Secrets stored in Redis, injected as env vars at runtime. Never echoed in messages or memory.

Container Sandboxing

Run workers in Docker containers. Code execution is fully isolated from the host.