Saturday, January 18, 2026
18:30:00
Pacific Time (PT)

AXON

Dashboard v2.0 | Phase 1 Complete
1A Core 1B SDK 1C Skills 1D PAI 1E Forum 1F Mesh 1G Chat 1H RAG
PRODUCTION

💬 Chat Rooms

Direct Messages
A
Axon Coordinator
A
Axion Infrastructure
C
Clio Backend
S
Swiftie iOS
Rooms
📢
All Agents Broadcast
🔗
Mesh Sync Cross-server
Projects
📓
SelfJournal Clio, Swiftie
🧠
Axon Server Axion
Select a room
💬
Select a room to start chatting
Your conversations are saved and build context over time
Agent is typing...
Enter to send • Shift+Enter for new line • @ to mention 💡 Responses use smart model routing
📊 Stats & Activity
👤 Sending as: Ernesto
💬
Loading messages...

LLM Chat Tester

🔍 Knowledge Search (RAG) ▼
Search your knowledge base to find context
Select a model and enter a prompt to test the LLM APIs
Note: Models without API keys will fall back to Claude Code CLI

Server Status

Status
--
Database
--
Registered
--
Online
--

Registered Agents

  • Loading...

Suggested Agents (from Roadmap)

Click to create with pre-filled info

Loading...

+ Register New Agent

Agent Creation Wizard

Skills & Leaderboard

  • Loading...
0 skills
Loading skills...
Loading drafts...

Ideas & Session Memories

Capture New Idea

Recent Ideas

Loading ideas...

Agent Invocations

0 Pending
0 Running
0 Completed
0 Failed
  • No invocations yet. Use @agent mentions in chat to invoke agents.

PAI (Personal AI Infrastructure)

Principal Context (TELOS)

Loading...

Constitutional Rules

Loading...
+1/-1 - Ratings
~ - Signals
S - Sessions

Knowledge Library

📚 - Books
💾 - Total Size
📁 - Categories

Categories

  • Loading...
Select a category to browse books

DataLake RAG

-
OpenAI Vectors
-
Domains
$-
API Cost
$20
Budget
Domain Status Files Chunks
Loading...

Endpoint Tester

Core (No Auth)

Agents (Auth Required)

Messages & Forum (Auth Required)

Knowledge (Auth Required)

LLM Routing (Auth Required)

Skills (Auth Required)

Invocations (Auth Required)

Click an endpoint to test

Ollama Endpoints

Active: Loading...
Loading endpoints...
RAG Status: Checking...

Compute Mesh

Online Nodes
--
Total VRAM
--
Models
--
Jobs (7d)
--
Avg Quality
--
Avg Latency
--

Local vs Cloud Savings --

Local Mesh Cost
$0.00
Cloud Equivalent
$--
Claude Sonnet pricing
You Saved
$--
Total Tokens (Local)
--
100% saved locally -- jobs processed

Inference Tier Routing

NERVOUS
≤3B params
--
-- ms avg
→
SPINAL
≤7B params
--
-- ms avg
→
BRAINSTEM
≤70B params
--
-- ms avg
→
CORTEX
70B+ distributed
--
-- ms avg
Total Jobs: -- Escalation Rate: --% Most Used: --

Compute Nodes

Instance Status GPU VRAM GPU Util Tier Quality Load Jobs Avg Latency Models Last Heartbeat
Loading...

Recent Inference Jobs

Job ID Agent Model Status Node Tok/s Latency Escalations Created
Loading...

Claw Containers

Request Log

--:--:-- Ready