Omair's Hermes · Dashboard

Usage

Tokens & Sessions

Total Sessions

168

20.9M tokens processed

Input Tokens

19.2M

cache reads: 333.4M

Output Tokens

1.6M

4,478 tool calls · 4,687 API calls

Cron Jobs

13

13 active · 3,284 runs total

Token Usage — Last 30 Days

Sessions by Platform

Models

Brain Configuration

Model	Sessions	Tokens
glm-5.1	87 sessions	6.2M
glm-5.2	43 sessions	3.0M
glm-5-turbo	22 sessions	9.5M
gemini-2.5-flash	9 sessions	1.4M
glm-5	5 sessions	362.2K
glm-4.7	1 sessions	74.7K
gemma4:latest	1 sessions	355.4K

Activity

Recent Sessions ▼

Session	Source	When	Duration	Tokens	Tools
💬 Build the session-end capture review script at ~/.herme	whatsapp	1h ago	—	57.3K	16
💬 Build the memory staleness checker script at ~/.hermes/	whatsapp	1h ago	—	46.7K	17
💬 Build the memory deduplication script at ~/.hermes/scri	whatsapp	1h ago	—	92.8K	8
💬 Build the memory promotion scanner script at ~/.hermes/	whatsapp	1h ago	—	114.4K	19
⏰ TRG Watch — Regular (9AM + 6PM PKT) · Jun 28 13:03	cron	7h ago	3min	24.0K	11
💬 ChatGPT Reverse Engineers Education System	whatsapp	9h ago	—	1.1M	33
⏰ Content Pipeline Health Check · Jun 28 08:01	cron	12h ago	—	3.0K	1
⏰ TRG Watch — Regular (9AM + 6PM PKT) · Jun 28 04:03	cron	16h ago	3min	27.8K	12
⏰ Dojo Overnight Improvement (6am PKT) · Jun 28 01:10	cron	19h ago	9min	92.8K	34
⏰ Essay Backfill (Slow Retry) · Jun 28 01:17	cron	19h ago	16min	6.4K	8

Automation

Cron Job Health

Job	Description	Schedule	Type	Runs	Last Run
ok WhatsApp ensureJid Patch Watchdog	🔧 Fixes WhatsApp JID mapping bug automatically	`every 360m`	script	×65	5h ago
ok TRG Watch — Regular (9AM + 6PM PKT)	📊 Monitors TRG stock announcements twice daily	`0 4,13 * * *`	skill	×30	7h ago
new TRG Watch — Jul 1 Escalation (hourly 6-11 PM PKT)	📊 Monitors TRG stock announcements twice daily	`0 13-18 1 7 *`	skill	×0	—
ok Fallback Alert Watchdog	🚨 Alerts when model falls back from primary	`every 10m`	script	×1732	3m ago
ok SeggySaid Video Monitor	🎬 Downloads + transcribes new SeggySaid videos	`every 360m`	script	×33	4h ago
ok Yasar Ahmad Video Monitor	🎬 Downloads + transcribes new Yasar Ahmad videos	`every 360m`	script	×33	25m ago
ok Dashboard Refresh (hourly)	🔄 Regenerates this dashboard hourly	`every 60m`	script	×126	1h ago
ok Dojo Overnight Improvement (6am PKT)	🥋 Overnight skill analysis + improvement suggestions	`0 1 * * *`	LLM	×7	19h ago
ok Dashboard Uptime Monitor	—	`every 5m`	script	×1250	5m ago
ok Content Pipeline Health Check	—	`0 8 * * *`	LLM	×3	12h ago
ok Essay Backfill (Slow Retry)	—	`0 1 * * *`	LLM	×3	19h ago
new Memory Reconciliation	—	`0 5 * * 1`	script	×0	—
ok Session Capture Review	—	`/30 * * *`	script	×2	28m ago

Self-Improvement

🥋 Dojo Findings 🔵 6 ▼

Last analyzed: 2026-06-28 01:08 PKT

95.6%

Success Rate +0.2%

73

Sessions

2,935

Tool Calls

129

Total Errors

15

User Corrections

Trend: 11:39: 72.2% → 15:22: 79.5% → 01:03: 79.6% → 01:03: 80.1% → 11:19: 93.5% → 01:03: 95.4% → 01:07: 95.4% → 01:08: 95.6%

🔵6 Pending

Tool Performance Breakdown

skill_manage

60.0%5 calls, 2 errors

memory

62.5%8 calls, 3 errors

browser_navigate

72.6%62 calls, 17 errors

delegate_task

77.8%9 calls, 2 errors

patch

86.3%292 calls, 40 errors

write_file

91.8%73 calls, 6 errors

browser_vision

92.2%51 calls, 4 errors

terminal

93.2%1297 calls, 88 errors

search_files

94.0%83 calls, 5 errors

session_search

94.4%18 calls, 1 errors

process

94.4%18 calls, 1 errors

cronjob

95.7%69 calls, 3 errors

read_file

95.8%307 calls, 13 errors

execute_code

97.8%230 calls, 5 errors

web_search

100.0%159 calls, 0 errors

web_extract

100.0%80 calls, 0 errors

todo

100.0%59 calls, 0 errors

skill_view

100.0%34 calls, 0 errors

browser_console

100.0%32 calls, 0 errors

▶ INFO Monitor classifier improved: health check false positives eliminated hermes-dojo

The pipeline health check script exits with code 1 after successfully sending Discord alerts. The monitor classifier was counting these as terminal errors. Patched monitor.py to recognize [health-check] Alert sent patterns as intentional non-zero exits. 10 false positives eliminated per week.

Impact: Terminal error rate improved from 7.3% to 6.8%. Overall success rate 95.4% → 95.6%.

🔵 PENDING

Fix: Applied — monitor.py now has _INTENTIONAL_EXIT_PATTERNS for monitoring scripts.

Evidence

Content Pipeline Health Check · Jun 27 01:08 (cron)

exit_code=1 with '[health-check] Alert sent to Discord #alerts'

Content Pipeline Health Check · Jun 26 08:01 (cron)

exit_code=1 with '[health-check] Alert sent to Discord #alerts'

▶ INFO TRG Watch skill verified working — all recent sessions load it correctly trg-watch

Last run created the trg-watch skill. Verification confirms all 14 TRG Watch cron sessions in the last 7 days (Jun 21-27) now correctly invoke the skill. Sessions show 'The user has invoked the trg-watch skill' with full skill content loaded.

Impact: TRG Watch efficiency restored. No more 15+ tool calls per session discovering workflow from scratch.

🔵 PENDING

Fix: No action needed — monitoring confirmed.

Evidence

TRG Watch — Regular (9AM + 6PM PKT) · Jun 27 13:02 (cron)

Skill loaded successfully (verified from message content)

TRG Watch — Regular (9AM + 6PM PKT) · Jun 27 04:04 (cron)

Skill loaded successfully (verified from message content)

▶ WARNING memory tool — 62.5% success (3/8 failures, unchanged) memory

Still the weakest tool by rate (though low volume). 2/3 failures are from hermes_env threat pattern blocking legitimate memory writes. 1/3 is entry not found (exact match failed). This is a Hermes platform-level issue that cannot be fixed from skill/agent level.

Impact: Agent loses important cross-session context. Low volume (8 calls/week) limits practical impact.

🔵 PENDING

Fix: Platform-level fix needed: review hermes_env threat pattern to allow legitimate memory writes containing environment variable references.

Evidence

Various sessions (Jun 23-27) (cron+whatsapp)

Blocked: content matches threat pattern 'hermes_env'

▶ INFO Terminal error breakdown: 88 real failures out of 1297 calls (6.8%)

Breakdown: 45 Python tracebacks (script bugs in essay gen, audit tools), 18 timeouts (long-running commands), 7 exit-127 (bad commands), 10 health check false positives (now fixed), remaining are misc. The 45 tracebacks are the largest category — mostly from generate_yas_essays.py and one-off debug scripts.

Impact: Low — most errors are in background scripts, not interactive sessions.

🔵 PENDING

Fix: The generate_yas_essays.py tracebacks are from a KeyError on progress tracking. The Essay Backfill cron should handle these gracefully. No dojo-level fix needed.

▶ LOW Success rate stable at 95.6% — agent in steady state hermes-dojo

Third consecutive run near 95% (95.4, 95.4, 95.6). The classifier improvements from prior runs are holding. The remaining 4.4% is real tool failures (memory, skill_manage, write_file syntax errors) that require platform-level fixes or are edge cases.

Impact: Positive — agent stability is good. No new regressions detected.

🔵 PENDING

Fix: Accept 95.6% as current ceiling. Focus shifts to quality improvements (new skills, workflow optimization) rather than error rate reduction.

▶ LOW User corrections: 15 in 7 days, mostly resolved issues

Breakdown: 5× 'I got two morning updates' (already fixed — routing resolved), 3× 'wrong' (file path issues), 2× 'no, ' corrections. The morning updates issue is fully resolved but its correction signals persist in the 7-day window.

Impact: Low — all recurring issues have been addressed in prior runs.

🔵 PENDING

Fix: Monitor for new correction patterns. The morning updates corrections should naturally age out of the 7-day window.

Actionable Recommendations

→

Review hermes_env threat pattern at Hermes platform level (blocks memory writes) — #1 actionable item

→

Monitor TRG Watch for continued skill loading success

→

Consider writing more scripts with proper error handling (essay gen tracebacks = 45/88 terminal errors)

→

Success rate has plateaued — future dojo runs should focus on skill quality and new capabilities

External Services

Integrations

🔍active

Langfuse Observability

cloud.langfuse.com
Live tracing of every LLM call, tool invocation, latency, and token cost. Waterfall views per session.

🧠active

Mem0 Memory Provider

app.mem0.ai
Semantic memory — no char limits, automatic fact extraction, cross-session recall.

☁️active

Cloudflare Pages

omair.pages.dev
CDN hosting for dashboard, library, books, and transcripts. 0.07s TTFB via Dubai edge.

🔎active

Tavily Search

tavily.com
Real-time web search with answer synthesis. Returns structured results with snippets. Free tier, 1K searches/month.

🛡️active

Security Hardening

Bundled security-guidance plugin + custom security skill. File-write warnings, prompt injection defense, credential hygiene.

📋active

Kanban Task Board

SQLite-backed multi-agent task board with auto-decomposition. Access via:
  1. Through me: say "create a task" or "what's on the board?"
  2. Web UI: ssh -L 9119:localhost:9119 ubuntu@VPS then open localhost:9119
  Auth: omair / khaadim2026

🧩active

MCP Consolidated

13 servers → 5 (2 merged + 3 standalone). Google Suite (30 tools) + Local Services (11 tools). Saves ~500MB RAM.

🔗active

Composio Connect

dashboard.composio.dev
1,623 tools across 11 apps. Free tier: 20K calls/month.

Available apps: Gmail, GitHub, Notion, Slack, Linear, Jira, HubSpot, Twitter, Airtable, Firecrawl, Perplexity

To connect a new app:
  1. Go to dashboard.composio.dev → Connected Accounts
  2. Click the app you want → OAuth login → authorize
  3. Done! Say "send a Slack message" or "search my Notion" in WhatsApp

To add MORE apps (Slack, Notion, etc. not listed?):
  Say "add [app name] to Composio" in chat — I'll create a new MCP server config with that toolkit

Usage: 0 / 20,000 calls this month | Server ID: 244e9609

Content

Library Status

Scontent

SeggySaid

153 videos · 153 essays · 64.4K words
100.0% essay coverage
📕 Book · 📖 Transcripts

Ycontent

Yasar Ahmad

766 videos · 762 essays · 350.4K words
99.5% essay coverage
📕 Book · 📖 Transcripts

📚library

Master Landing

omair.pages.dev/library
Complete cross-linked library with book + transcript pages

Procedures

Skill Inventory — 61 Skills ▼

airtable (1)

productivity Airtable REST API via curl. Records CRUD, filters, upserts. 17d ago

api-integration (1)

software-development > 3d ago

architecture-diagram (1)

creative Dark-themed SVG architecture/cloud/infra diagrams as HTML. 3d ago

arxiv (1)

research Search arXiv papers by keyword, author, category, or ID. 17d ago

ascii-art (1)

creative ASCII art and video: text banners (pyfiglet), message art (cowsay), decorative borders (boxes), imag 2d ago

baoyu-infographic (1)

creative Infographics: 21 layouts x 21 styles (信息图, 可视化). 17d ago

blogwatcher (1)

research Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool. 17d ago

claude-design (1)

creative Design one-off HTML artifacts (landing, deck, prototype). 9d ago

coding-agent-delegation (1)

autonomous-ai-agents Delegate coding tasks to external CLI agents (Claude Code, Codex, OpenCode). Covers one-shot print m 2d ago

comfyui (1)

creative Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows 17d ago

content-pipeline-health (1)

devops Build, maintain, and health-check content pipelines (SeggySaid, Yasar Ahmad books) — essay generatio 2d ago

custom-mcp-servers (1)

autonomous-ai-agents Build in-house MCP servers using FastMCP + stdlib to replace broken, premium-locked, or missing thir 4d ago

database-operations (1)

software-development > 4d ago

deployment (1)

devops > 2d ago

design-md (1)

creative Author/validate/export Google's DESIGN.md token spec files. 17d ago

excalidraw (1)

creative Hand-drawn Excalidraw JSON diagrams (arch, flow, seq). 17d ago

gif-search (1)

media Search/download GIFs from Tenor via curl + jq. 17d ago

git-operations (1)

software-development > 4d ago

github-operations (1)

github Complete GitHub workflow: auth, repo management, PR lifecycle, issues, code review, and codebase ins 2d ago

google-workspace (1)

productivity Google Workspace operations via MCP and API: Calendar events, Drive file management, Docs/Sheets/Sli 2d ago

hermes-agent (1)

autonomous-ai-agents Configure, extend, or contribute to Hermes Agent. 3d ago

hermes-cron-jobs (1)

productivity Create, configure, and debug Hermes cron jobs — toolset/MCP integration, scheduling, delivery, and c 3d ago

hermes-model-config (1)

autonomous-ai-agents Switch, upgrade, and validate Hermes LLM models and providers. Manage fallback chains, add new provi 4d ago

hermes-operations-dashboard (1)

autonomous-ai-agents > 3d ago

himalaya (1)

email Himalaya CLI: IMAP/SMTP email from terminal. 17d ago

huggingface-hub (1)

mlops HuggingFace hf CLI: search/download/upload models, datasets. 17d ago

humanizer (1)

creative Humanize text: strip AI-isms and add real voice. 17d ago

jupyter-live-kernel (1)

data-science Iterative Python via live Jupyter kernel (hamelnb). 17d ago

kanban-orchestrator (1)

devops Decomposition playbook + anti-temptation rules for an orchestrator profile routing work through Kanb 17d ago

kanban-worker (1)

devops Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected 17d ago

llm-wiki (1)

research Karpathy's LLM Wiki: build/query interlinked markdown KB. 17d ago

manim-video (1)

creative Manim CE animations: 3Blue1Brown math/algo videos. 17d ago

maps (1)

productivity Geocode, POIs, routes, timezones via OpenStreetMap/OSRM. 17d ago

market-data (1)

productivity Look up stock prices, PSX/KSE market data, financial news, and company fundamentals for Pakistani an 4d ago

memory-management (1)

productivity > 37m ago

notion (1)

productivity Notion API + ntn CLI: pages, databases, markdown, Workers. 17d ago

obsidian (1)

note-taking Read, search, create, and edit notes in the Obsidian vault. 3d ago

ocr-and-documents (1)

productivity Extract text from PDFs/scans (pymupdf, marker-pdf). 9d ago

openhue (1)

smart-home Control Philips Hue lights, scenes, rooms via OpenHue CLI. 17d ago

p5js (1)

creative p5.js sketches: gen art, shaders, interactive, 3D. 17d ago

plan (1)

software-development Plan mode: write an actionable markdown plan to .hermes/plans/, no execution. Bite-sized tasks, exac 17d ago

polymarket (1)

research Query Polymarket: markets, prices, orderbooks, history. 17d ago

popular-web-designs (1)

creative 54 real design systems (Stripe, Linear, Vercel) as HTML/CSS. 17d ago

powerpoint (1)

productivity Create, read, edit .pptx decks, slides, notes, templates. 17d ago

pretext (1)

creative Use when building creative browser demos with @chenglou/pretext — DOM-free text layout for ASCII art 17d ago

requesting-code-review (1)

software-development Pre-commit review: security scan, quality gates, auto-fix. 9d ago

research-paper-writing (1)

research Write ML papers for NeurIPS/ICML/ICLR: design→submit. 17d ago

security-hardening (1)

software-development Security best practices and threat model for Omair's Hermes Agent setup on Oracle Cloud VPS with aut 4d ago

songsee (1)

media Audio spectrograms/features (mel, chroma, MFCC) via CLI. 17d ago

songwriting-and-ai-music (1)

creative Songwriting craft and Suno AI music prompts. 9d ago

spike (1)

software-development Throwaway experiments to validate an idea before build. 17d ago

systematic-debugging (1)

software-development 4-phase root cause debugging: understand bugs before fixing. 2d ago

systemd-ops (1)

devops Manage Hermes systemd services, gateway restarts, systemd units, and VPS operations on Oracle Cloud 4d ago

teams-meeting-pipeline (1)

productivity Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline sta 17d ago

test-driven-development (1)

software-development TDD: enforce RED-GREEN-REFACTOR, tests before code. 2d ago

touchdesigner-mcp (1)

creative Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire co 17d ago

trg-watch (1)

research > 1d ago

video-transcription (1)

media Download and transcribe videos from any platform (YouTube, Facebook, TikTok, Instagram, etc.) using 6h ago

web-retrieval (1)

research > 5d ago

whatsapp-messaging (1)

productivity Send WhatsApp messages to contacts and groups — direct bridge access, contact resolution, and outbou 3d ago

xurl (1)

social-media X/Twitter via xurl CLI: post, search, DM, media, v2 API. 17d ago

Memory

Persistent Stores

🧠 Mem0 Cloud unlimited · semantic

Mem0 Cloud (app.mem0.ai) — Semantic search, auto fact extraction, cross-session recall. No char limit.

Local MEMORY.md (prompt injection) 2,934/5,000 chars

58.7% used · injected into system prompt each turn

Local USER.md (prompt injection) 2,204/2,500 chars

88.2% used · injected into system prompt each turn

Connections

Platform Status

1connected

Whatsapp

Active and receiving messages

2connected

Discord

Active and receiving messages

Topology

System Architecture

Messages flow from WhatsApp/Discord/Email through the gateway to GLM-5.2, which reaches consolidated MCP servers, Composio, and cloud services — all self-hosted on Oracle VPS.

📱

💬

Discord

📧

Email

▼

Hermes Gateway

systemd · allowlisted · 3 platforms

▼

🧠 GLM-5.2

Persona · Tool-use · Reasoning · Vision (GLM-4.5v)

Fallback: 5.1→5-turbo→4.7→4.5-air→gemini→groq

▼ ▼ ▼

📦 Consolidated MCP (5 servers)

google_suite.py · 30 tools

local_services.py · 11 tools

clickup · docintel · context7

13→5 consolidation · -500MB RAM

🔗 Composio Connect

1,623 tools · 11 apps

Gmail · GitHub · Notion

Slack · Linear · Jira

HubSpot · Twitter · Airtable · Firecrawl · Perplexity

OAuth-based · no browser needed

☁️ Cloud Services

🧠 Mem0 · semantic memory

📊 Langfuse · observability

🔎 Tavily · AI search

☁️ Cloudflare Pages · hosting

All on free tiers

▼

Google APIs

Calendar · Drive · Docs · Sheets · Slides · Tasks · Contacts

1 OAuth client · 1 token · 0600 file

Oracle VPS

systemd services · ~/hermes · ARM64

● Teal = in-house · self-hosted ● Gold = third-party managed ● Red = brain & senses

Trust & Data

Security Posture

🏠 Data on your turf

Everything runs on your Oracle VPS. No third-party server sits between the agent and Google APIs. All adapter code is auditable in ~/.hermes/custom-mcp/

🔐 Minimal OAuth scopes

One Google OAuth client with only the scopes each feature needs — Calendar, Drive, Docs, Sheets, Slides, Tasks, Contacts. Nothing broader. No admin/Workspace powers.

🔑 One token, well guarded

A single refresh token in a 0600 file behind a shared auth helper. No secrets in config.yaml. API keys isolated in .env.

🔒 Allowlisted access

WhatsApp, Discord, and Email are allowlisted to your number and addresses only. No one else can talk to it. Password gate on dashboard (khaadim2026).

🛡️ Security hardening active

security-guidance plugin warns on dangerous file writes. Custom threat-model skill covers prompt injection, data exfiltration, and credential hygiene. ClickUp: no destructive actions.

⚠️ Known gaps

No host firewall (ufw) yet. No fail2ban. Leaked Vercel/Discord tokens need rotation. No offsite backups. Home dir has 1.4GB phone backup clutter.

What's Next

Roadmap & Limitations

✅ Recently Shipped (June 2026)

GLM-5.2 upgrade
From 5.1, with reasoning model

MCP consolidation
13→5 servers, -500MB RAM

Composio Connect
1,623 tools, 11 apps

Mem0 + Tavily
Semantic memory + AI search

Surge→CF migration
All 6 pages on Cloudflare

Dashboard v2
Charts, Dojo findings, architecture

💡 Ideas to Explore

Host firewall (ufw)
Block rpcbind/Syncthing exposure

Token rotation
Regen Vercel/Discord/Composio keys

Gmail API
Labels, threads, search, triage

Offsite backups
Encrypted, automated, remote

Dojo improvements
Fix cronjob + retry loop findings

Home dir cleanup
1.4GB phone backups to archive

▲ Current Limitations

Unverified OAuth app — Google shows a one-time consent warning and a 100-user cap (you're the only user)

Google Keep unavailable — API is Workspace-only, won't work with a personal account

Maps-lite is driving-only — OpenStreetMap routing covers car routes; walking/transit not wired

External tools (web_extract, browser_navigate) depend on target site availability — mitigated by Tavily + Composio

Composio apps need per-app OAuth — tools exist in schema but return "not authenticated" until connected

Hermes Dashboard

Tokens & Sessions

Brain Configuration

Recent Sessions ▼

Cron Job Health

🥋 Dojo Findings 🔵 6 ▼

Integrations

Langfuse Observability

Mem0 Memory Provider

Cloudflare Pages

Tavily Search

Security Hardening

Kanban Task Board

MCP Consolidated

Composio Connect

Library Status

SeggySaid

Yasar Ahmad

Master Landing

Skill Inventory — 61 Skills ▼

airtable (1)

api-integration (1)

architecture-diagram (1)

arxiv (1)

ascii-art (1)

baoyu-infographic (1)

blogwatcher (1)

claude-design (1)

coding-agent-delegation (1)

comfyui (1)

content-pipeline-health (1)

custom-mcp-servers (1)

database-operations (1)

deployment (1)

design-md (1)

excalidraw (1)

gif-search (1)

git-operations (1)

github-operations (1)

google-workspace (1)

hermes-agent (1)

hermes-cron-jobs (1)

hermes-model-config (1)

hermes-operations-dashboard (1)

himalaya (1)

huggingface-hub (1)

humanizer (1)

jupyter-live-kernel (1)

kanban-orchestrator (1)

kanban-worker (1)

llm-wiki (1)

manim-video (1)

maps (1)

market-data (1)

memory-management (1)

notion (1)

obsidian (1)

ocr-and-documents (1)

openhue (1)

p5js (1)

plan (1)

polymarket (1)

popular-web-designs (1)

powerpoint (1)

pretext (1)

requesting-code-review (1)

research-paper-writing (1)

security-hardening (1)

songsee (1)

songwriting-and-ai-music (1)

spike (1)

systematic-debugging (1)

systemd-ops (1)

teams-meeting-pipeline (1)

test-driven-development (1)

touchdesigner-mcp (1)

trg-watch (1)

video-transcription (1)

web-retrieval (1)

whatsapp-messaging (1)