← Chat Archive

{"success": true, "name": "hermes-agent", "description": "Configure, extend, or contribute to Hermes Agent.", "tags": ["hermes", "setup", "configuration", "multi-agent", "spawning", "cli", "gateway", "development"], "related_skills": ["claude-code", "codex", "opencode"], "content": "---\nname: hermes-agent\ndescription: \"Configure, extend, or contribute to Hermes Agent.\"\nversion: 2.0.0\nauthor: Hermes Agent + Teknium\nlicense: MIT\nmetadata:\n hermes:\n tags: [hermes, setup, configuration, multi-agent, spawning, cli, gateway, development]\n homepage: https://github.com/NousResearch/hermes-agent\n related_skills: [claude-code, codex, opencode]\n---\n\n# Hermes Agent\n\nHermes Agent is an open-source AI agent framework by Nous Research that runs in your terminal, messaging platforms, and IDEs. It belongs to the same category as Claude Code (Anthropic), Codex (OpenAI), and OpenClaw — autonomous coding and task-execution agents that use tool calling to interact with your system. Hermes works with any LLM provider (OpenRouter, Anthropic, OpenAI, DeepSeek, local models, and 15+ others) and runs on Linux, macOS, and WSL.\n\nWhat makes Hermes different:\n\n- **Self-improving through skills** — Hermes learns from experience by saving reusable procedures as skills. When it solves a complex problem, discovers a workflow, or gets corrected, it can persist that knowledge as a skill document that loads into future sessions. Skills accumulate over time, making the agent better at your specific tasks and environment.\n- **Persistent memory across sessions** — remembers who you are, your preferences, environment details, and lessons learned. Pluggable memory backends (built-in, Honcho, Mem0, and more) let you choose how memory works.\n- **Multi-platform gateway** — the same agent runs on Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Email, and 10+ other platforms with full tool access, not just chat.\n- **Provider-agnostic** — swap models and providers mid-workflow without changing anything else. Credential pools rotate across multiple API keys automatically.\n- **Profiles** — run multiple independent Hermes instances with isolated configs, sessions, skills, and memory.\n- **Extensible** — plugins, MCP servers, custom tools, webhook triggers, cron scheduling, and the full Python ecosystem.\n\nPeople use Hermes for software development, research, system administration, data analysis, content creation, home automation, and anything else that benefits from an AI agent with persistent context and full system access.\n\n**This skill helps you work with Hermes Agent effectively** — setting it up, configuring features, spawning additional agent instances, troubleshooting issues, finding the right commands and settings, and understanding how the system works when you need to extend or contribute to it.\n\n**Docs:** https://hermes-agent.nousresearch.com/docs/\n\n## Quick Start\n\n```bash\n# Install\ncurl -fsSL https://raw.githubusercontent.com/NousResea ... [32098 chars total, truncated]

{"output": "", "exit_code": -1, "error": "BLOCKED: User denied. Do NOT retry.", "status": "blocked"}

{"output": "Saved working directory and index state On main: hermes-update-autostash-20260429-120207\n⚕ Updating Hermes Agent...\n\n→ Fetching updates...\n→ Local changes detected — stashing before update...\n→ Found 56 new commit(s)\n ✓ Pre-update snapshot: 20260429-120207-pre-update\n→ Pulling updates...\n→ Restoring local changes...\n⚠ Local changes were restored on top of the updated codebase.\n Review `git diff` / `git status` if Hermes behaves unexpectedly.\n ✓ Cleared 18 stale __pycache__ directories\n→ Updating Python dependencies...\n→ Updating Node.js dependencies...\n ✓ repo root\n ✓ ui-tui\n→ Building web UI...\n ✓ Web UI built\n\n✓ Code updated!\n\n→ Syncing bundled skills...\n ~ 1 user-modified (kept)\n ✓ Skills are up to date\n\n→ Checking configuration for new options...\n ✓ Configuration is up to date\n\n✓ Update complete!\n\nTip: You can now select a provider and model:\n hermes model # Select provider and model", "exit_code": 0, "error": null, "approval": "Command required approval (hermes update (restarts gateway, kills running agents)) and was approved by the user."}

{"output": "Model: {'default': 'deepseek-v4-pro', 'provider': 'ollama-cloud', 'base_url': 'https://ollama.com/v1'}\n Max turns: 60\n\n◆ Display\n Personality: kawaii\n Reasoning: off", "exit_code": 0, "error": null}

{"output": "┌─────────────────────────────────────────────────────────┐\n│ ⚕ Hermes Configuration │\n└─────────────────────────────────────────────────────────┘\n\n◆ Paths\n Config: /home/ubuntu/.hermes/config.yaml\n Secrets: /home/ubuntu/.hermes/.env\n Install: /home/ubuntu/.hermes/hermes-agent\n\n◆ API Keys\n OpenRouter (not set)\n OpenAI (STT/TTS) (not set)\n Exa (not set)\n Parallel (not set)\n Firecrawl (not set)\n Tavily (not set)\n Browserbase (not set)\n Browser Use (not set)\n FAL (not set)\n Anthropic (not set)\n\n◆ Model\n Model: {'default': 'deepseek-v4-pro', 'provider': 'ollama-cloud', 'base_url': 'https://ollama.com/v1'}\n Max turns: 60\n\n◆ Display\n Personality: kawaii\n Reasoning: off\n Bell: off\n User preview: first 2 line(s), last 2 line(s)\n\n◆ Terminal\n Backend: local\n Working dir: .\n Timeout: 180s\n\n◆ Timezone\n Timezone: (server-local)\n\n◆ Context Compression\n Enabled: yes\n Threshold: 50%\n Target ratio: 20% of threshold preserved\n Protect last: 20 messages\n Model: (auto)\n\n◆ Messaging Platforms\n Telegram: not configured\n Discord: not configured\n\n────────────────────────────────────────────────────────────\n hermes config edit # Edit config file\n hermes config set <key> <value>\n hermes setup # Run setup wizard", "exit_code": 0, "error": null}

{"output": "Connect: 0.002928s | TTFB: 0.054508s | Total: 0.054714s", "exit_code": 0, "error": null}

{"output": "Connect: 0.092167s | TTFB: 0.426186s | Total: 0.426302s", "exit_code": 0, "error": null}

{"error": "Error searching web: Payment Required: Failed to search. {'code': 'BILLING_ERROR', 'message': 'Charge authorization failed', 'details': {'upstreamStatusCode': 402, 'upstreamPayload': {'error': 'Insufficient available balance for requested reservation', 'code': 'insufficient_funds', 'data': {'requestedReserveAmount': '0.000966', 'orgId': 'cmo7hy3oc001kjp07sl05jcau', 'subscriptionAllowance': {'allowanceId': 'cmoa7aw32019rjo04olbrhyt0', 'allowanceType': 'SUBSCRIPTION', 'balance': '-0.952795488', 'availableBalance': '-0.952795488', 'outstandingReservations': '0'}, 'purchasedAllowance': {'allowanceId': 'cmo7hy3oc001ljp07w9wc8hh8', 'allowanceType': 'PURCHASED', 'balance': '-0.7559', 'availableBalance': '-0.7559', 'outstandingReservations': '0'}}}, 'method': 'POST', 'targetUrl': 'https://portal.nousresearch.com/api/nous/charge-intents/authorize'}} - No additional error details provided."}

{"output": "TTFB: 0.000000s | Total: 0.017837s | HTTP: 000\n\nreal\t0m0.032s\nuser\t0m0.021s\nsys\t0m0.009s", "exit_code": 43, "error": null}

{ "results": [ { "url": "https://status.deepseek.com", "title": "", "content": "", "error": "Payment Required: Failed to scrape. {'code': 'BILLING_ERROR', 'message': 'Charge authorization failed', 'details': {'upstreamStatusCode': 402, 'upstreamPayload': {'error': 'Insufficient available balance for requested reservation', 'code': 'insufficient_funds', 'data': {'requestedReserveAmount': '0.000483', 'orgId': 'cmo7hy3oc001kjp07sl05jcau', 'subscriptionAllowance': {'allowanceId': 'cmoa7aw32019rjo04olbrhyt0', 'allowanceType': 'SUBSCRIPTION', 'balance': '-0.952795488', 'availableBalance': '-0.952795488', 'outstandingReservations': '0'}, 'purchasedAllowance': {'allowanceId': 'cmo7hy3oc001ljp07w9wc8hh8', 'allowanceType': 'PURCHASED', 'balance': '-0.7559', 'availableBalance': '-0.7559', 'outstandingReservations': '0'}}}, 'method': 'POST', 'targetUrl': 'https://portal.nousresearch.com/api/nous/charge-intents/authorize'}} - No additional error details provided." }, { "url": "https://ollama.com/blog", "title": "", "content": "", "error": "Payment Required: Failed to scrape. {'code': 'BILLING_ERROR', 'message': 'Charge authorization failed', 'details': {'upstreamStatusCode': 402, 'upstreamPayload': {'error': 'Insufficient available balance for requested reservation', 'code': 'insufficient_funds', 'data': {'requestedReserveAmount': '0.000483', 'orgId': 'cmo7hy3oc001kjp07sl05jcau', 'subscriptionAllowance': {'allowanceId': 'cmoa7aw32019rjo04olbrhyt0', 'allowanceType': 'SUBSCRIPTION', 'balance': '-0.952795488', 'availableBalance': '-0.952795488', 'outstandingReservations': '0'}, 'purchasedAllowance': {'allowanceId': 'cmo7hy3oc001ljp07w9wc8hh8', 'allowanceType': 'PURCHASED', 'balance': '-0.7559', 'availableBalance': '-0.7559', 'outstandingReservations': '0'}}}, 'method': 'POST', 'targetUrl': 'https://portal.nousresearch.com/api/nous/charge-intents/authorize'}} - No additional error details provided." } ] }

{"output": "● hermes-gateway.service - Hermes Agent Gateway - Messaging Platform Integration\n Loaded: loaded (/home/ubuntu/.config/systemd/user/hermes-gateway.service; enabled; preset: enabled)\n Active: active (running) since Wed 2026-04-29 14:32:50 IST; 3h 2min ago\n Invocation: dc69400ea0814a1d862a736d4dc6f7fc\n Main PID: 2284178 (python)\n Tasks: 4 (limit: 13960)\n Memory: 99.9M (peak: 102.7M)\n CPU: 7.785s\n CGroup: /user.slice/user-1000.slice/user@1000.service/app.slice/hermes-gateway.service\n └─2284178 /home/ubuntu/.hermes/hermes-agent/venv/bin/python -m hermes_cli.main gateway run --replace\n\nApr 29 14:32:50 vps-2c5ca245 systemd[1139]: Started hermes-gateway.service - Hermes Agent Gateway - Messaging Platform Integration.\n✓ User gateway service is running\n✓ Systemd linger is enabled (service survives logout)", "exit_code": 0, "error": null}

{"output": "# LLM PROVIDER (Ollama Cloud)\n# Cloud-hosted open models via Ollama's OpenAI-compatible endpoint.\n# Get your key at: https://ollama.com/settings\n# OLLAMA_API_KEY=your_o...here\n# Optional base URL override (default: https://ollama.com/v1)\n# OLLAMA_BASE_URL=https://ollama.com/v1\nOLLAMA_API_KEY=dd18d6...Pqc_", "exit_code": 0, "error": null}

{"output": "} [1 bytes data]\n* TLSv1.3 (OUT), TLS handshake, Finished (20):\n} [52 bytes data]\n* SSL connection using TLSv1.3 / TLS_AES_256_GCM_SHA384 / x25519 / RSASSA-PSS\n* ALPN: server accepted h2\n* Server certificate:\n* subject: CN=ollama.com\n* start date: Apr 25 21:18:19 2026 GMT\n* expire date: Jul 24 22:11:53 2026 GMT\n* subjectAltName: host \"ollama.com\" matched cert's \"ollama.com\"\n* issuer: C=US; O=Google Trust Services; CN=WR3\n* SSL certificate verify ok.\n* Certificate level 0: Public key type RSA (2048/112 Bits/secBits), signed using sha256WithRSAEncryption\n* Certificate level 1: Public key type RSA (2048/112 Bits/secBits), signed using sha256WithRSAEncryption\n* Certificate level 2: Public key type RSA (4096/152 Bits/secBits), signed using sha384WithRSAEncryption\n* Connected to ollama.com (34.36.133.15) port 443\n* using HTTP/2\n\r 0 86 0 0 0 0 0 0 --:--:-- --:--:-- --:--:-- 0\n* Connection #0 to host ollama.com left intact\ncurl: (43) A libcurl function was given a bad argument", "exit_code": 0, "error": null}

{"output": "2026-04-29 14:21:18,853 INFO gateway.run: Exiting with code 1 (signal-initiated shutdown without restart request) so systemd Restart=on-failure can revive the gateway.\n2026-04-29 14:26:23,809 INFO gateway.run: Exiting with code 1 (signal-initiated shutdown without restart request) so systemd Restart=on-failure can revive the gateway.", "exit_code": 0, "error": null}

{"output": "{\n \"object\": \"list\",\n \"data\": [\n {\n \"id\": \"mistral-large-3:675b\",\n \"object\": \"model\",\n \"created\": 1764633600,\n \"owned_by\": \"ollama\"\n },\n {\n \"id\": \"gemini-3-flash-preview\",\n \"object\": \"model\",\n \"created\": 1765929600,\n \"owned_by\": \"ollama\"\n },\n {\n \"id\": \"gemma3:4b\",\n \"object\": \"model\",\n \"created\": 1741737600,\n \"owned_by\": \"ollama\"\n },\n {\n \"id\": \"gemma3:27b\",\n \"object\": \"model\",\n \"created\": 1741737600,\n \"owned_by\": \"ollama\"\n },\n {\n \"id\": \"qwen3-next:80b\",\n \"object\": \"model\",", "exit_code": 0, "error": null, "approval": "Command required approval (Security scan — [MEDIUM] Schemeless URL in sink context: URL without explicit scheme passed to a command that downloads/executes content; [HIGH] Pipe to interpreter: curl | python3: Command pipes output from 'curl' directly to interpreter 'python3'. Downloaded content will be executed without inspection.\n Safer: tirith run https://ollama.com/v1/models — or: vet https://ollama.com/v1/models (https://getvet.sh)) and was approved by the user."}

{"output": "Total models: 39\ndeepseek-v3.1:671b\ndeepseek-v4-pro\ndeepseek-v3.2\ndeepseek-v4-flash", "exit_code": 0, "error": null, "approval": "Command required approval (Security scan — [HIGH] Pipe to interpreter: curl | python3: Command pipes output from 'curl' directly to interpreter 'python3'. Downloaded content will be executed without inspection.\n Safer: tirith run https://ollama.com/v1/models — or: vet https://ollama.com/v1/models (https://getvet.sh); script execution via -e/-c flag) and was approved by the user."}

{"output": "Key length: 57\n\n[Command timed out after 30s]", "exit_code": 124, "error": null}

{"output": "total 13400\n-rw------- 1 ubuntu ubuntu 143687 Apr 29 17:36 session_20260429_170552_d653fc.json\n-rw------- 1 ubuntu ubuntu 78609 Apr 29 14:40 session_api-4f5e8b4251daa2fe.json\n-rw------- 1 ubuntu ubuntu 78609 Apr 29 14:35 session_api-7c3d512c99c0ccb5.json\n-rw------- 1 ubuntu ubuntu 82769 Apr 29 14:25 session_api-a8927237dd14b24c.json", "exit_code": 0, "error": null}

{"output": "HTTP: 200 | TTFB: 0.928512s | Total: 0.928639s\n\nreal\t0m0.943s\nuser\t0m0.028s\nsys\t0m0.011s", "exit_code": 0, "error": null}

{"output": "HTTP: 200 | TTFB: 0.706734s | Total: 0.706921s\n\nreal\t0m0.720s\nuser\t0m0.017s\nsys\t0m0.014s", "exit_code": 0, "error": null}

{"output": "HTTP: 200 | TTFB: 1.560553s | Total: 1.560642s\n\nreal\t0m1.573s\nuser\t0m0.025s\nsys\t0m0.008s", "exit_code": 0, "error": null}

{"output": "{\"id\":\"chatcmpl-455\",\"object\":\"chat.completion\",\"created\":1777464729,\"model\":\"deepseek-v4-pro\",\"system_fingerprint\":\"fp_ollama\",\"choices\":[{\"index\":0,\"message\":{\"role\":\"assistant\",\"content\":\"\",\"reasoning\":\"We are asked: \\\"\"},\"finish_reason\":\"length\"}],\"usage\":{\"prompt_tokens\":7,\"completion_tokens\":5,\"total_tokens\":12}}\n\nreal\t0m3.584s\nuser\t0m0.020s\nsys\t0m0.008s", "exit_code": 0, "error": null}

{"output": "", "exit_code": 0, "error": null}

{"question": "Want me to switch your model from deepseek-v4-pro to deepseek-v4-flash? It's 5x faster and still a capable model. Or would you prefer deepseek-v3.2 (2x faster, more stable)?", "choices_offered": ["Switch to deepseek-v4-flash (5x faster)", "Switch to deepseek-v3.2 (2x faster, more stable)", "Keep v4-pro, I'll deal with the latency", "Show me all available models on ollama.com first"], "user_response": "Switch to deepseek-v4-flash (5x faster)"}

{"output": "✓ Set model.default = deepseek-v4-flash in /home/ubuntu/.hermes/config.yaml", "exit_code": 0, "error": null}

{"output": "✓ User service restarted", "exit_code": 0, "error": null, "approval": "Command required approval (stop/restart hermes gateway (kills running agents)) and was approved by the user."}

{"output": "/home/ubuntu/.hermes/config.yaml\n\nreal\t0m0.436s\nuser\t0m0.371s\nsys\t0m0.061s", "exit_code": 0, "error": null}

{"output": "ok\n\nreal\t0m0.026s\nuser\t0m0.021s\nsys\t0m0.005s", "exit_code": 0, "error": null, "approval": "Command required approval (script execution via -e/-c flag) and was approved by the user."}

{"output": "/home/ubuntu/.local/bin/hermes\n/home/ubuntu/.local/bin/hermes: symbolic link to /home/ubuntu/.hermes/hermes-agent/venv/bin/hermes\n#!/home/ubuntu/.hermes/hermes-agent/venv/bin/python3\n# -*- coding: utf-8 -*-\nimport sys\nfrom hermes_cli.main import main\nif __name__ == \"__main__\":", "exit_code": 0, "error": null}

{"output": "Run 1: HTTP 200 | TTFB 1.087889s | Total 1.088027s\nRun 2: HTTP 200 | TTFB 1.311063s | Total 1.311174s\nRun 3: HTTP 200 | TTFB 1.132627s | Total 1.132736s", "exit_code": 0, "error": null}