Is Hermes Agent v0.17.0 stable?
-232/100Fact score: -232/100 · evidence-based, not a YES/NO verdict
“v0.17.0 picked up fresh receipts: tool loading can collapse to cronjob-only, QQBot can fail on gateway startup, Matrix/table formatting still bites, and desktop/file-tool/SimpleX regressions joined the stack. The pager has started using footnotes.”
Stability Score
-232Base
80
Evidence
-232
Votes
-0
Survived
ignored
Curated
ignored
-232 evidence debt=-232
Affected components
approval-boundaryauthbrowsercompactionconfig-profilesdashboarddesktop-linuxdesktop-macosdesktop-uidesktop-windowsdiscordemailfeishufile-toolsgateway-serviceimessageinstallermatrixmcpmemorymessage-deliverymodel-routingopencodeprovider-routingqqbotruntimesecuritysimplextelegramtool-loaderupdate-systemvoiceweb-toolswhatsappwindows-runtimewindows-update
Install this version
npm install hermes-agent@0.17.0Score Evidence
| Issue | Area | Type | Penalty | Reason |
|---|---|---|---|---|
| NousResearch/hermes-agent issue 51405 → | feishu | runtime | -5 | v0.17.0 gateway startup can crash on fresh Feishu installs because cron.scheduler_provider is missing. |
| NousResearch/hermes-agent issue 50734 → | approval-boundary | kernel | -5 | v0.17.0 read_file/tool path can ignore safety directives and exfiltrate full .env credentials to LLM providers. |
| NousResearch/hermes-agent issue 49578 → | approval-boundary | kernel | -5 | v0.17.0 execute_code can bypass agent file edit restrictions and write outside the allowed edit path. |
| NousResearch/hermes-agent issue 51447 → | auth | runtime | -4 | v0.17.0 Bitwarden profile-suffixed secrets may not reach platform plugins, silently breaking non-default Telegram bot profiles. |
| NousResearch/hermes-agent issue 51029 → | telegram | runtime | -4 | v0.17.0 multiplexer env override handling can leak a default profile platform token into a secondary Telegram profile. |
| NousResearch/hermes-agent issue 50806 → | runtime | runtime | -4 | v0.17.0 CLI can hang after a shell tool starts a detached child process, repeatedly submitting tool results instead of returning control. |
| NousResearch/hermes-agent issue 50765 → | runtime | runtime | -4 | Hermes ACP session/prompt hangs after conversation turn on Windows v0.17.0 while v0.16.0 works, blocking ACP apps. |
| NousResearch/hermes-agent issue 50394 → | mcp | runtime | -4 | v0.17.0 MCP bridge can churn after one failing stdio server, leaving healthy servers' tools as unknown at runtime. |
| NousResearch/hermes-agent issue 49627 → | runtime | runtime | -4 | v0.17.0 setup can fail during agent initialization with init_agent() receiving an unexpected event_callback argument. |
| NousResearch/hermes-agent issue 49305 → | message-delivery | runtime | -4 | Hermes Desktop/TUI on v0.17.0 can lose a user message and persist no assistant response when an additional profile uses codex_app_server. |
| NousResearch/hermes-agent issue 51448 → | provider-routing | runtime | -3 | Hermes Desktop v0.17.0 on native Windows can return empty LM Studio streams while the same config works under WSL. |
| NousResearch/hermes-agent issue 51381 → | provider-routing | runtime | -3 | v0.17.0 can send malformed tools[] schemas without function names to OpenCode/DeepSeek backends, causing provider deserialization failure. |
| NousResearch/hermes-agent issue 51316 → | mcp | tool-specific | -3 | v0.17.0 MCP single-query snapshots can miss slow-start stdio servers, producing incomplete tool lists until reload. |
| NousResearch/hermes-agent issue 51290 → | runtime | runtime | -3 | v0.17.0 background skill review can block ACP multi-turn IDE sessions after the first turn. |
| NousResearch/hermes-agent issue 51030 → | telegram | runtime | -3 | v0.17.0 Telegram multiplexer token-collision detection can miss duplicate tokens in profile adapter config. |
| NousResearch/hermes-agent issue 50959 → | provider-routing | runtime | -3 | v0.17.0 can send invalid Unicode in tools[].function.description, producing HTTP 400s across providers. |
| NousResearch/hermes-agent issue 50807 → | runtime | runtime | -3 | v0.17.0 forwards very large shell tool output to providers without bounding the payload. |
| NousResearch/hermes-agent issue 50794 → | desktop-macos | runtime | -3 | Hermes Desktop v0.17.0 can crash on launch on macOS 26.5 with EXC_BREAKPOINT in fontations_ffi. |
| NousResearch/hermes-agent issue 50252 → | provider-routing | runtime | -3 | v0.17.0 GitHub Copilot provider can return an empty base URL on every inference despite a valid token and detected models. |
| NousResearch/hermes-agent issue 50209 → | desktop-ui | runtime | -3 | v0.17.0 Desktop boot can hang around the backend status probe even while the CLI itself is healthy. |
| NousResearch/hermes-agent issue 50199 → | provider-routing | runtime | -3 | v0.17.0 delegation.base_url can be ignored at runtime, forcing incorrect provider endpoint resolution. |
| NousResearch/hermes-agent issue 49976 → | update-system | runtime | -3 | v0.17.0 Windows ZIP-fallback update path can drop gateway resume state and make restarts fail on stale gateway_state.json. |
| NousResearch/hermes-agent issue 49961 → | provider-routing | runtime | -3 | v0.17.0 reports configured tools not being invoked across NVIDIA NIM and OpenRouter conversation flows. |
| NousResearch/hermes-agent issue 49903 → | desktop-ui | runtime | -3 | v0.17.0 Desktop can throw Composer is not available after upgrade, making the composer input unresponsive. |
| NousResearch/hermes-agent issue 49590 → | auth | runtime | -3 | v0.17.0 gateway startup can prefer literal op:// secret references over resolved cached values, breaking secret-backed channels. |
| NousResearch/hermes-agent issue 49490 → | opencode | runtime | -3 | OpenCode Zen provider calls fail after updating to v0.17.0, breaking that provider path. |
| NousResearch/hermes-agent issue 49445 → | web-tools | tool-specific | -3 | Since v0.17.0 the official Docker image can ship with search.exa/web_search/web_extract unusable. |
| NousResearch/hermes-agent issue 49283 → | approval-boundary | kernel | -3 | v0.17.0 desktop execute_code consent gate still rejects an explicitly consented code execution request. |
| NousResearch/hermes-agent issue 47917 → | desktop-windows | runtime | -3 | Desktop builds can continue failing after v0.17.0 updates because electronDist disappears from the build path. |
| NousResearch/hermes-agent issue 47868 → | provider-routing | runtime | -3 | Strict chat-completions providers on v0.17.0 reject leaked messages[].timestamp metadata with HTTP 400s. |
| NousResearch/hermes-agent issue 36718 → | compaction | kernel | -3 | After updating to v0.17.0, context compression can repeatedly trigger because last_prompt_tokens stays stale until the next API call. |
| NousResearch/hermes-agent issue 51278 → | provider-routing | runtime | -2 | v0.17.0 title generation can route the main model name to the fallback provider endpoint. |
| NousResearch/hermes-agent issue 51263 → | channel-specific | -2 | v0.17.0 email STARTTLS setup can fail with OpenSSL WRONG_VERSION_NUMBER on OpenSSL 3.5+ systems. | |
| NousResearch/hermes-agent issue 51155 → | runtime | runtime | -2 | v0.17.0 user personalities can fail to change and persist across sessions. |
| NousResearch/hermes-agent issue 51099 → | memory | runtime | -2 | v0.17.0 can activate the Honcho memory provider even when honcho-ai is not installed. |
| NousResearch/hermes-agent issue 50966 → | browser | tool-specific | -2 | Desktop GUI on v0.17.0 routes browser_vision calls to browser_scroll instead of the requested vision tool. |
| NousResearch/hermes-agent issue 50823 → | installer | runtime | -2 | Desktop build for v0.17.0 hard fails on Windows native non-git checkouts because build-stamp cannot determine a git commit. |
| NousResearch/hermes-agent issue 50769 → | installer | runtime | -2 | Windows installer for v0.17.0 detects a Python 3.12 fallback but still tries Python 3.11 for venv creation, failing install. |
| NousResearch/hermes-agent issue 50737 → | gateway-service | runtime | -2 | v0.17.0 desktop profile-scoped OpenRouter setup can leave gateway inference not ready. |
| NousResearch/hermes-agent issue 50713 → | message-delivery | runtime | -2 | v0.17.0 can lose chat text after reopening sessions across multiple deployments. |
| NousResearch/hermes-agent issue 50675 → | gateway-service | runtime | -2 | v0.17.0 gateway agent cache can reset /usage API-call and token counters during follow-up turns. |
| NousResearch/hermes-agent issue 50404 → | discord | channel-specific | -2 | v0.17.0 Discord config is not profile-isolated, allowing channel state to bleed across profiles. |
| NousResearch/hermes-agent issue 50395 → | mcp | tool-specific | -2 | v0.17.0 hermes mcp test can report a server healthy under a different PATH than the gateway MCP spawn actually uses. |
| NousResearch/hermes-agent issue 50229 → | model-routing | runtime | -2 | v0.17.0 silent fallback failover can run the agent as the wrong model without notifying the user. |
| NousResearch/hermes-agent issue 50210 → | installer | runtime | -2 | v0.17.0 Windows bootstrap can produce an unsigned Hermes.exe blocked by Smart App Control. |
| NousResearch/hermes-agent issue 50205 → | feishu | channel-specific | -2 | v0.17.0 Docker image can miss lark-oapi, causing the Feishu channel to fail at connect time. |
| NousResearch/hermes-agent issue 50175 → | config-profiles | runtime | -2 | v0.17.0 profile deletion can fail while dashboard/gateway child processes are alive, making profiles reappear until reboot. |
| NousResearch/hermes-agent issue 49982 → | desktop-ui | runtime | -2 | v0.17.0 Windows Desktop can time out connecting to the backend while the CLI still works. |
| NousResearch/hermes-agent issue 49870 → | dashboard | tool-specific | -2 | v0.17.0 task Done/ready flow can trigger a false diagnostic and then get blocked by the respawn guard. |
| NousResearch/hermes-agent issue 49606 → | update-system | runtime | -2 | Windows Desktop v0.17.0 update flow can leave users with a mismatched backend/desktop state after silent GUI update failure. |
| NousResearch/hermes-agent issue 49561 → | channel-specific | -2 | v0.17.0 regression can prevent installing the WhatsApp bridge in Docker environments. | |
| NousResearch/hermes-agent issue 49529 → | installer | tool-specific | -2 | The v0.17.0 PyPI wheel install has a doctor false-positive and omits optional-skills from the wheel package. |
| NousResearch/hermes-agent issue 49297 → | provider-routing | tool-specific | -2 | Gemma4 through the Ollama backend still hits near-immediate finish_reason=length truncation on v0.17.0. |
| NousResearch/hermes-agent issue 49242 → | windows-runtime | runtime | -2 | Windows WhatsApp gateway and updater paths on v0.17.0 can use system Node/npm instead of Hermes-managed tooling. |
| NousResearch/hermes-agent issue 50775 → | telegram | channel-specific | -1 | Telegram macOS app streaming on v0.17.0 can show ghosting/double-text during edited-message updates. |
| NousResearch/hermes-agent issue 49955 → | dashboard | tool-specific | -1 | v0.17.0 Kanban inline create form truncates field labels in the dashboard. |
| NousResearch/hermes-agent issue 49908 → | dashboard | tool-specific | -1 | v0.17.0 drag-and-drop to Done can show a completion prompt and then silently revert the task. |
| NousResearch/hermes-agent issue 49745 → | desktop-ui | tool-specific | -1 | Desktop v0.17.0 composer undo skips pasted content because paste operations lack a contentEditable undo entry. |
| NousResearch/hermes-agent issue 49732 → | model-routing | tool-specific | -1 | v0.17.0 dashboard model-switch dialog can fire with no active chat and flip the badge before the user decides. |
| NousResearch/hermes-agent issue 49600 → | desktop-ui | tool-specific | -1 | v0.17.0 desktop UI can clip the audio icon on Windows. |
| NousResearch/hermes-agent issue 49536 → | telegram | channel-specific | -1 | Telegram finalize messages on v0.17.0 can overlap text because parse_mode mutation falls back incorrectly. |
| NousResearch/hermes-agent issue 49294 → | gateway-service | tool-specific | -1 | Windows Desktop restart gateway action on v0.17.0 opens a persistent CMD window instead of restarting the installed headless service. |
| NousResearch/hermes-agent issue 49253 → | imessage | channel-specific | -1 | Photon iMessage on v0.17.0 corrupts Unicode when Markdown bold formatting is present. |
| NousResearch/hermes-agent issue 52023 → | provider-routing | runtime | -3 | Hermes Desktop v0.17.0 on Windows returns OpenAI 400 errors for GPT-4o-mini, GPT-4.1 and related models because encrypted content is sent to models that do not support it. |
| NousResearch/hermes-agent issue 51864 → | dashboard | runtime | -3 | Hermes v0.17.0 self-hosted kanban can route task workspaces and board filters through global active-board state instead of task tenant, mixing tenants. |
| NousResearch/hermes-agent issue 52013 → | desktop-ui | channel-specific | -1 | Hermes Desktop v0.17.0 on Chinese Windows can render Chinese TUI/desktop text as mojibake, making non-ASCII output unreadable. |
| NousResearch/hermes-agent issue 51646 → | memory | runtime | -4 | Hermes v0.17.0 gateway memory writes can omit the active column, causing INSERT failures and lost persisted state. |
| NousResearch/hermes-agent issue 51873 → | auth | runtime | -3 | Hermes Desktop v0.17.0 can loop on 401s and never show the documented sign-in UI when connecting to a remote backend with basic auth. |
| NousResearch/hermes-agent issue 51871 → | approval-boundary | runtime | -4 | Hermes v0.17.0 legacy chat-completions streaming can omit approval events, so apps see text deltas but no tool-approval boundary. |
| NousResearch/hermes-agent issue 52753 → | desktop-windows | runtime | -5 | v0.17.0 packaged Windows desktop can fail to launch after update because simple-git is missing from the Electron bundle. |
| NousResearch/hermes-agent issue 52378 → | update-system | runtime | -4 | v0.17.0 Windows desktop auto-update can loop indefinitely, repeatedly spawning elevated updater processes even when behind=0. |
| NousResearch/hermes-agent issue 52428 → | browser | tool-specific | -3 | v0.17.0 browser_navigate fails with missing _hermes_read_browser_output, breaking browser tool navigation on Windows. |
| NousResearch/hermes-agent issue 52496 → | model-routing | runtime | -3 | v0.17.0 dashboard model switcher can rewrite named custom providers to openrouter/bare custom, breaking local proxy routing. |
| NousResearch/hermes-agent issue 52492 → | provider-routing | runtime | -2 | v0.17.0 Codex model selection can persist an unsupported gpt-5.3-codex custom model and then fail prompts with HTTP 400. |
| NousResearch/hermes-agent issue 52363 → | telegram | channel-specific | -2 | v0.17.0 Telegram outbound messages can be stored as incoming unread items, making inbox badges grow on the agent's own replies. |
| NousResearch/hermes-agent issue 52573 → | voice | tool-specific | -2 | v0.17.0 TUI continuous voice mode can fail to reopen the microphone after TTS playback on macOS. |
| NousResearch/hermes-agent issue 51882 → | desktop-ui | runtime | -2 | v0.17.0 Desktop Chat→Personality setting writes display.personality but not agent.system_prompt, so the persona is silently ignored. |
| NousResearch/hermes-agent issue 51684 → | feishu | channel-specific | -2 | v0.17.0 Feishu approval-card clicks reject FEISHU_ALLOWED_USERS=* wildcard even though normal inbound messages are allowed. |
| NousResearch/hermes-agent issue 52235 → | desktop-ui | tool-specific | -1 | v0.17.0 Windows desktop composer can visually corrupt after PageDown while draft text is present. |
| NousResearch/hermes-agent issue 52566 → | voice | tool-specific | -1 | v0.17.0 desktop TTS playback can time out through the hermes-media:// protocol even when generated audio files are valid. |
| NousResearch/hermes-agent issue 51321 → | desktop-ui | tool-specific | -1 | v0.17.0 Windows Artifacts view can display file/session timestamps months off from actual file and database times. |
| NousResearch/hermes-agent issue 53514 → | desktop-linux | runtime | -1 | Linux desktop v0.17.0 hides the close button when titleBarStyle is hidden, leaving Alt+F4 as the exit path |
| NousResearch/hermes-agent issue 53667 → | tool-loader | runtime | -5 | Fresh v0.17.0 install can collapse runtime tools to cronjob-only despite doctor reporting tools available |
| NousResearch/hermes-agent issue 50928 → | desktop-ui | runtime | -2 | v0.17.0 desktop deleted sessions can reappear after Load more/refresh due to state race |
| NousResearch/hermes-agent issue 53173 → | windows-update | runtime | -3 | Machines updated to v0.17.0 can retain stale Windows gateway .cmd autostart launchers that respawn console windows |
| NousResearch/hermes-agent issue 53026 → | matrix | channel-specific | -1 | v0.17.0 Matrix adapter splits messages at 4000 chars, breaking Markdown tables despite Matrix allowing larger events |
| NousResearch/hermes-agent issue 52823 → | file-tools | tool-specific | -3 | v0.17.0 write_file with non-local terminal backend resolves remote absolute paths on the macOS host |
| NousResearch/hermes-agent issue 53659 → | desktop-ui | runtime | -2 | Hermes Desktop v0.17.0 Ctrl/Cmd+Enter can miss freshly typed steer text before state flushes |
| NousResearch/hermes-agent issue 53443 → | qqbot | channel-specific | -3 | v0.17.0 QQBot adapter connect signature rejects is_reconnect and fails every gateway startup |
| NousResearch/hermes-agent issue 54077 → | voice | tool-specific | -1 | Hermes Desktop v0.17.0 generates Windows SAPI TTS audio but opens it in Windows Media Player instead of inline playback |
| NousResearch/hermes-agent issue 55180 → | simplex | channel-specific | -2 | v0.17.0 SimpleX adapter silently drops non-audio XFTP attachments before completed downloads reach the agent |
| NousResearch/hermes-agent issue 55917 → | dashboard | runtime | -2 | v0.17.0 dashboard PTY WebSocket Origin checks reject Cloudflare Tunnel/proxy access when Origin differs from the bind address. |