Omair's Hermes · Dashboard

Usage

Tokens & Sessions

Total Sessions

129

17.2M tokens processed

Input Tokens

16.0M

cache reads: 280.0M

Output Tokens

1.2M

3,536 tool calls · 3,749 API calls

Cron Jobs

16

16 active · 1,763 runs total

Token Usage — Last 30 Days

Sessions by Platform

Models

Brain Configuration

Model	Sessions	Tokens
glm-5.1	86 sessions	6.2M
glm-5-turbo	19 sessions	8.9M
glm-5.2	13 sessions	355.2K
glm-5	5 sessions	362.2K
gemini-2.5-flash	4 sessions	1.0M
glm-4.7	1 sessions	74.7K
gemma4:latest	1 sessions	355.4K

Activity

Recent Sessions ▼

Session	Source	When	Duration	Tokens	Tools
💬 Explaining Conflicting Morning Updates #6	whatsapp	1h ago	—	67.7K	130
💬 Explaining Conflicting Morning Updates #5	whatsapp	1h ago	—	60.1K	115
💬 Explaining Conflicting Morning Updates #4	whatsapp	2h ago	35min	303.5K	96
💬 Explaining Conflicting Morning Updates #3	whatsapp	2h ago	21min	188.5K	91
⏰ Dojo Overnight Improvement (6am PKT) · Jun 25 01:05	cron	2h ago	5min	37.1K	32
⏰ Sehri Ends — 9th Muharram · Jun 24 23:15	cron	4h ago	1min	4.0K	3
⏰ Wake Up — Sehri (9th Muharram) · Jun 24 21:46	cron	6h ago	1min	17.4K	4
⏰ TRG Watch — Regular (9AM + 6PM PKT) · Jun 24 13:03	cron	14h ago	3min	33.8K	11
💬 Explaining Conflicting Morning Updates #2	whatsapp	18h ago	939min	1.1M	104
💬 Explaining Conflicting Morning Updates	whatsapp	20h ago	97min	415.2K	84

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	×51	1h ago
ok TRG Watch — Regular (9AM + 6PM PKT)	📊 Monitors TRG stock announcements twice daily	`0 4,13 * * *`	skill	×22	14h 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	×1247	8m ago
ok SeggySaid Video Monitor	🎬 Downloads + transcribes new SeggySaid videos	`every 360m`	script	×19	17m ago
ok Yasar Ahmad Video Monitor	🎬 Downloads + transcribes new Yasar Ahmad videos	`every 360m`	script	×18	2h ago
ok Dashboard Refresh (hourly)	🔄 Regenerates this dashboard hourly	`every 60m`	script	×39	1h ago
ok Dojo Overnight Improvement (6am PKT)	🥋 Overnight skill analysis + improvement suggestions	`0 1 * * *`	LLM	×3	2h ago
ok Dashboard Uptime Monitor	—	`every 5m`	script	×364	just now
new Iftari — 9th Muharram	—	`once at 2026-06-25 14:25`	LLM	×0	—
new Sehri Ends — 10th Muharram (Ashura)	—	`once at 2026-06-25 23:15`	LLM	×0	—
new Iftari — 10th Muharram (Ashura)	—	`once at 2026-06-26 14:25`	LLM	×0	—
new Wake Up — Sehri (10th Muharram)	—	`once at 2026-06-25 21:45`	LLM	×0	—
new Amazon Return — Send to Naveen	—	`once at 2026-06-25 05:00`	LLM	×0	—
new Amazon Return Reminder — Fintie Case to Nony	—	`once at 2026-06-26 05:00`	LLM	×0	—
new Reminder — Talk to Nony about 3 Amazon returns	—	`once at 2026-06-26 05:00`	LLM	×0	—

Self-Improvement

🥋 Dojo Findings 🔵 6 ▼

Last analyzed: 2026-06-25T01:03:00Z

80.1%

Success Rate +0.5%

48

Sessions

1,949

Tool Calls

388

Total Errors

26

User Corrections

Trend: 11:39: 72.2% → 15:22: 79.5% → 01:03: 79.6% → 01:03: 80.1%

🔵6 Pending

Tool Performance Breakdown

memory

13.0%23 calls, 20 errors

skill_view

30.8%13 calls, 9 errors

web_extract

53.1%64 calls, 30 errors

browser_navigate

58.5%41 calls, 17 errors

web_search

67.8%149 calls, 48 errors

send_message

71.4%7 calls, 2 errors

execute_code

80.6%134 calls, 26 errors

read_file

82.7%220 calls, 38 errors

patch

85.2%182 calls, 27 errors

delegate_task

87.5%8 calls, 1 errors

search_files

91.8%49 calls, 4 errors

browser_vision

92.3%39 calls, 3 errors

write_file

94.7%38 calls, 2 errors

▶ CRITICAL memory tool — 20 errors in 23 calls (13% success) memory-management

The #1 source of errors. 14/20 failures are memory-at-capacity errors (2,200 char limit). The agent repeatedly tries to add long entries without checking usage or consolidating first, creating 5-8 wasted retry loops per incident. 2 failures are injection-blocked content ('hermes_env' threat pattern). 4 failures are no-entry-match on search.

Impact: ~14 wasted tool calls per session that hits the limit. 20 errors in 7 days = significant token waste and user frustration.

🔵 PENDING

Fix: PATCHED: memory-management skill v1.0→1.1.0 — added explicit 2,200 char limit documentation, budget rule, aggressive consolidation instructions, and injection-block pitfall.

Evidence

Explaining Conflicting Morning Updates (whatsapp)

Memory at 2,065/2,200 chars. Adding this entry would exceed limit.

AI Reverse Engineers Education System #13 (whatsapp)

Blocked: content matches threat pattern 'hermes_env'.

Explaining Conflicting Morning Updates #2 (whatsapp)

No entry matched 'Naveen is Omair's brother...'

▶ WARNING web_extract — 30 errors in 64 calls (53% success) web-retrieval

Monitor counts wrappers as errors, inflating the count. Real failures are timeouts on large pages and paywall/JS-only sites. web-retrieval skill exists but many sessions still retry web_extract 3x instead of escalating.

Impact: ~15 wasted calls in 7 days from retry loops.

🔵 PENDING

Fix: Fix monitor.py to filter false positives. The web-retrieval skill already covers this.

Evidence

TRG Watch — Regular (cron)

wrapper counted as error (false positive)

Explaining Conflicting Morning Updates #2 (whatsapp)

web_extract truncated response / timeout

▶ WARNING skill_view — monitor reports 30.8% success (false positive) hermes-dojo

FALSE POSITIVE: all sampled 'errors' are actually {"success": true, ...} responses. Monitor regex matches 'error' substring even in successful responses.

Impact: Misleading metric inflating perceived failure rate. Not a real agent weakness — a monitoring bug.

🔵 PENDING

Fix: Fix monitor.py to parse JSON success field instead of regex-matching 'error' in content.

Evidence

Sehri Ends — 9th Muharram (cron)

False positive: response was {"success": true, ...}

Wake Up — Sehri (9th Muharram) (cron)

False positive: same issue

▶ INFO No api-integration skill (7 requests in 7 days) api-integration

Users repeatedly asked about REST API integrations, webhook setups, and third-party API connections. No skill existed to guide the agent.

Impact: Agent improvised each time, leading to inconsistent patterns.

🔵 PENDING

Fix: CREATED: api-integration skill with REST/GraphQL patterns, auth examples, pagination, retry logic, webhook templates.

Evidence

AI Reverse Engineers Education System #14 (whatsapp)

User asked about API integration approach

▶ INFO deployment skill exists but monitor reports gap deployment

Monitor detected 15 deployment requests as skill gap, but deployment skill exists at devops/deployment/SKILL.md. Gap detection doesn't scan all categories.

Impact: Deployment skill may not load automatically when needed.

🔵 PENDING

Fix: Fix monitor.py skill gap detection to recursively scan all skill subdirectories.

▶ INFO Retry loops remain high (166 in 7 days) web-retrieval

web_search called 3x in rapid succession on multiple occasions. Agent retries same tool instead of changing approach.

Impact: ~50 wasted tool calls from retry loops alone.

🔵 PENDING

Fix: Reinforce anti-retry-loop behavior in web-retrieval skill.

Evidence

TRG Watch — Regular (cron)

web_search called 3x in rapid succession

Actionable Recommendations

→

Fix monitor.py false positives: filter wrappers and parse JSON success field instead of regex-matching 'error' substring.

→

Patch monitor.py skill gap detection to recursively scan all skill subdirectories — it missed the existing deployment skill.

→

Reinforce anti-retry-loop behavior in web-retrieval skill — add explicit 'escalate after 1 failure' rule.

→

Track memory consolidation success rate as a new metric — measure whether the patched memory-management skill reduces capacity errors over the next 7 days.

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 · 90 essays · 41.9K words
58.8% essay coverage
📕 Book · 📖 Transcripts

Ycontent

Yasar Ahmad

758 videos · 671 essays · 317.1K words
88.5% essay coverage
📕 Book · 📖 Transcripts

📚library

Master Landing

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

Procedures

Skill Inventory — 75 Skills ▼

airtable (1)

productivity Airtable REST API via curl. Records CRUD, filters, upserts. 13d ago

api-integration (1)

software-development > 2h ago

architecture-diagram (1)

creative Dark-themed SVG architecture/cloud/infra diagrams as HTML. 2h ago

arxiv (1)

research Search arXiv papers by keyword, author, category, or ID. 13d ago

ascii-art (1)

creative ASCII art: pyfiglet, cowsay, boxes, image-to-ascii. 13d ago

ascii-video (1)

creative ASCII video: convert video/audio to colored ASCII MP4/GIF. 13d ago

baoyu-infographic (1)

creative Infographics: 21 layouts x 21 styles (信息图, 可视化). 13d ago

blogwatcher (1)

research Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool. 13d ago

claude-code (1)

autonomous-ai-agents Delegate coding to Claude Code CLI (features, PRs). 13d ago

claude-design (1)

creative Design one-off HTML artifacts (landing, deck, prototype). 6d ago

cloudflare-pages-deploy (1)

devops Deploy static sites to Cloudflare Pages via wrangler CLI. Project "omair" under Omair's Cloudflare a 10h ago

codebase-inspection (1)

github Inspect codebases w/ pygount: LOC, languages, ratios. 13d ago

codex (1)

autonomous-ai-agents Delegate coding to OpenAI Codex CLI (features, PRs). 13d ago

comfyui (1)

creative Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows 13d ago

custom-mcp-servers (1)

autonomous-ai-agents Build in-house MCP servers using FastMCP + stdlib to replace broken, premium-locked, or missing thir 1d ago

database-operations (1)

software-development > 1d ago

deployment (1)

devops > 15h ago

design-md (1)

creative Author/validate/export Google's DESIGN.md token spec files. 13d ago

excalidraw (1)

creative Hand-drawn Excalidraw JSON diagrams (arch, flow, seq). 13d ago

gif-search (1)

media Search/download GIFs from Tenor via curl + jq. 13d ago

git-operations (1)

software-development > 1d ago

github-auth (1)

github GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login. 13d ago

github-code-review (1)

github Review PRs: diffs, inline comments via gh or REST. 13d ago

github-issues (1)

github Create, triage, label, assign GitHub issues via gh or REST. 13d ago

github-pr-workflow (1)

github GitHub PR lifecycle: branch, commit, open, CI, merge. 13d ago

github-repo-management (1)

github Clone/create/fork repos; manage remotes, releases. 13d ago

google-calendar (1)

productivity Manage Google Calendar via MCP gcal tools — list, create, search events. 3h ago

google-docs-formatting (1)

productivity Create well-formatted Google Docs programmatically — HTML→Drive conversion (primary), plain text upl 5d ago

google-drive (1)

productivity Manage Google Drive, Docs, Sheets, and Slides via MCP gdrive tools — full file CRUD, document editin 5d ago

hermes-agent (1)

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

hermes-agent-skill-authoring (1)

software-development Author in-repo SKILL.md: frontmatter, validator, structure. 13d ago

hermes-cron-jobs (1)

productivity Create, configure, and debug Hermes cron jobs — toolset/MCP integration, scheduling, delivery, and c 1h ago

hermes-model-config (1)

autonomous-ai-agents Switch, upgrade, and validate Hermes LLM models and providers. Manage fallback chains, add new provi 1d ago

hermes-operations-dashboard (1)

autonomous-ai-agents > 2h ago

himalaya (1)

email Himalaya CLI: IMAP/SMTP email from terminal. 13d ago

huggingface-hub (1)

mlops HuggingFace hf CLI: search/download/upload models, datasets. 13d ago

humanizer (1)

creative Humanize text: strip AI-isms and add real voice. 13d ago

jupyter-live-kernel (1)

data-science Iterative Python via live Jupyter kernel (hamelnb). 13d ago

kanban-orchestrator (1)

devops Decomposition playbook + anti-temptation rules for an orchestrator profile routing work through Kanb 13d ago

kanban-worker (1)

devops Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected 13d ago

llm-wiki (1)

research Karpathy's LLM Wiki: build/query interlinked markdown KB. 13d ago

manim-video (1)

creative Manim CE animations: 3Blue1Brown math/algo videos. 13d ago

maps (1)

productivity Geocode, POIs, routes, timezones via OpenStreetMap/OSRM. 13d ago

market-data (1)

productivity Look up stock prices, PSX/KSE market data, financial news, and company fundamentals for Pakistani an 1d ago

memory-management (1)

productivity > 2h ago

node-inspect-debugger (1)

software-development Debug Node.js via --inspect + Chrome DevTools Protocol CLI. 13d ago

notion (1)

productivity Notion API + ntn CLI: pages, databases, markdown, Workers. 13d ago

obsidian (1)

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

ocr-and-documents (1)

productivity Extract text from PDFs/scans (pymupdf, marker-pdf). 6d ago

omair-transcription-treatment (1)

media Full transcription pipeline triggered by 'Omair Transcription treatment' — download, transcribe, AI- 7h ago

opencode (1)

autonomous-ai-agents Delegate coding to OpenCode CLI (features, PR review). 13d ago

openhue (1)

smart-home Control Philips Hue lights, scenes, rooms via OpenHue CLI. 13d ago

p5js (1)

creative p5.js sketches: gen art, shaders, interactive, 3D. 13d ago

plan (1)

software-development Plan mode: write an actionable markdown plan to .hermes/plans/, no execution. Bite-sized tasks, exac 13d ago

polymarket (1)

research Query Polymarket: markets, prices, orderbooks, history. 13d ago

popular-web-designs (1)

creative 54 real design systems (Stripe, Linear, Vercel) as HTML/CSS. 13d ago

powerpoint (1)

productivity Create, read, edit .pptx decks, slides, notes, templates. 13d ago

pretext (1)

creative Use when building creative browser demos with @chenglou/pretext — DOM-free text layout for ASCII art 13d ago

python-debugpy (1)

software-development Debug Python: pdb REPL + debugpy remote (DAP). 13d ago

requesting-code-review (1)

software-development Pre-commit review: security scan, quality gates, auto-fix. 6d ago

research-paper-writing (1)

research Write ML papers for NeurIPS/ICML/ICLR: design→submit. 13d ago

security-hardening (1)

software-development Security best practices and threat model for Omair's Hermes Agent setup on Oracle Cloud VPS with aut 1d ago

songsee (1)

media Audio spectrograms/features (mel, chroma, MFCC) via CLI. 13d ago

songwriting-and-ai-music (1)

creative Songwriting craft and Suno AI music prompts. 6d ago

spike (1)

software-development Throwaway experiments to validate an idea before build. 13d ago

systematic-debugging (1)

software-development 4-phase root cause debugging: understand bugs before fixing. 1d ago

systemd-ops (1)

devops Manage Hermes systemd services, gateway restarts, systemd units, and VPS operations on Oracle Cloud 15h ago

teams-meeting-pipeline (1)

productivity Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline sta 13d ago

test-driven-development (1)

software-development TDD: enforce RED-GREEN-REFACTOR, tests before code. 13d ago

touchdesigner-mcp (1)

creative Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire co 13d ago

video-transcription (1)

media Download and transcribe videos from social media platforms (Facebook, TikTok, Instagram, etc.) using 3d ago

web-retrieval (1)

research > 1d ago

whatsapp-messaging (1)

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

xurl (1)

social-media X/Twitter via xurl CLI: post, search, DM, media, v2 API. 13d ago

youtube-content (1)

media YouTube transcripts to summaries, threads, blogs. 5d 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) 4,957/5,000 chars

99.1% used · injected into system prompt each turn

Local USER.md (prompt injection) 2,489/2,500 chars

99.6% used · injected into system prompt each turn

Connections

Platform Status

1connected

Whatsapp

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 — 75 Skills ▼

airtable (1)

api-integration (1)

architecture-diagram (1)

arxiv (1)

ascii-art (1)

ascii-video (1)

baoyu-infographic (1)

blogwatcher (1)

claude-code (1)

claude-design (1)

cloudflare-pages-deploy (1)

codebase-inspection (1)

codex (1)

comfyui (1)

custom-mcp-servers (1)

database-operations (1)

deployment (1)

design-md (1)

excalidraw (1)

gif-search (1)

git-operations (1)

github-auth (1)

github-code-review (1)

github-issues (1)

github-pr-workflow (1)

github-repo-management (1)

google-calendar (1)

google-docs-formatting (1)

google-drive (1)

hermes-agent (1)

hermes-agent-skill-authoring (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)

node-inspect-debugger (1)

notion (1)

obsidian (1)

ocr-and-documents (1)

omair-transcription-treatment (1)

opencode (1)

openhue (1)

p5js (1)

plan (1)

polymarket (1)

popular-web-designs (1)

powerpoint (1)

pretext (1)

python-debugpy (1)

requesting-code-review (1)