Hermes Agent v0.19.0 (v2026.7.20)

Release Date: July 20, 2026

Since v0.18.0: ~2,245 commits · ~1,065 merged PRs · ~2,465 files changed · ~300,000 insertions · ~36,000 deletions · ~3,300 issues closed · 450+ community contributors

The Quicksilver Release. Hermes is the messenger god, and this window we made him move like it. First-turn time-to-first-token dropped ~80% on every platform, reasoning streams live by default, the desktop app got a ~20-PR speed overhaul (14× faster streaming markdown, virtualized diffs, snappy session switching), and the TUI renders markdown incrementally. Around that speed spine: you can now manage your Nous subscription without leaving the terminal, plug Bitwarden and 1Password straight into Hermes, let smart approvals judge flagged commands for you by default, watch your subagents work live, and trust that a finished response survives a gateway crash thanks to a durable delivery ledger. This release also rolls up everything from the v0.18.1 and v0.18.2 infrastructure patch tags — those windows are fully documented here.

✨ Highlights

• 
  

  Hermes got dramatically faster — first token in a fraction of the time — Cold-start "Initializing agent..." used to eat ~4.3 seconds before your first turn even reached the model; it's now ~0.9s, an ~80% cut that applies to the CLI, gateway, TUI, desktop, and cron alike. Round 2 attacked what you see while waiting: reasoning models now stream their thinking live by default (no more staring at a spinner for 30 seconds), and the response box paints per token instead of per line. If Hermes ever felt like it took a deep breath before answering, that breath is gone. ( — , , , )

  
  


• 
  

  Manage your Nous plan from the terminal — /subscription and /topup — Changing your subscription used to mean a trip to the billing website. Now /subscription opens a full flow right in the TUI or classic CLI: see your plan and remaining allowance, preview exactly what an upgrade costs ("Pay $46.30 & upgrade now") or when a downgrade takes effect, and apply it — with scheduled-change banners and undo. The desktop app got a matching billing settings tab. Your wallet never has to leave the keyboard. (, )

  
  


• 
  

  Smart approvals are now the default — When Hermes wants to run a flagged command, an LLM reviewer now assesses it independently instead of asking you to approve every single one — and each verdict covers only that exact command, so a later command matching the same pattern gets its own review. Combined with the new user-defined deny rules (which block commands even under yolo mode) and /deny <reason> (which tells the agent why you refused so it course-corrects), day-to-day approval fatigue drops sharply without giving up control. (, )

  
  


• 
  

  Plug your password manager into Hermes — Bitwarden & 1Password secret sources — API keys no longer have to live in a plaintext .env. A new pluggable SecretSource interface lets Hermes fetch secrets from Bitwarden and 1Password (op:// references) at load time, with multiple vaults enabled simultaneously, deterministic precedence, conflict warnings, and per-variable provenance. This consolidated eleven competing community PRs into one orchestrated interface — future vault providers drop in as plugins. (, 1Password provider salvaged from , )

  
  


• 
  

  A finished answer can no longer be lost — the delivery-obligation ledger — If the gateway died between generating your response and confirming the platform actually delivered it, that answer used to be silently gone (and you'd paid for the turn). Final responses are now recorded in a durable ledger in state.db around the platform send and redelivered on the next boot — closing a P1 silent-loss window for Telegram, Discord, Slack, and every other channel. ()

  
  


• 
  

  One gateway, many profiles — profile-based message routing — A single multiplexed gateway sharing one bot token can now route specific guilds, channels, or threads to different profiles — each with fully isolated config, skills, memory, and secrets. Point your work Discord server at the work profile and your hobby server at personal, from one bot. A second multiplex hardening wave means one misconfigured profile can no longer take down the whole gateway. (, — + six salvaged contributors)

  
  


• 
  

  New providers and the newest frontier models — Fireworks AI and DeepInfra land as first-class providers (Fireworks with cost estimation and a , — 's , , , , )

  
  


• 
  

  Your sessions, your data — export everything — hermes sessions export now writes Markdown, Quarto, HTML, prompt-only, and even Hugging Face-ready trace formats, with the full filter surface (age, workspace, platform), an opt-in --redact secret-scrubbing pass, and compacted-session lineage stitched into one logical export. Pair with the new prune filters and bulk archive to keep your session store tidy. Your conversation history is a real dataset now, not a black box. (, , )

  
  


• 
  

  Security hardening round — This window closed a long list of credential-surface gaps: Vertex credentials scoped away from subprocess env and through profile secret scopes, media/vision/image-gen local-file reads routed through one shared credential-read guard, a webhook body-size-cap sweep across every aiohttp server, bot-token redaction in Telegram transport errors, Fireworks token prefixes added to the redactor, six P1 browser/MEDIA/.env hardening PRs salvaged in one pass, and CI hardened against untrusted-ref interpolation. (, , , , — — , , , , )



• Cut startup serialization + per-turn REST amplification; pre-warm profile backends and gateway sockets on hover intent; idle-mount boot-hidden panes; fast model picker + dialogs (, — , , , — , )

Everywhere else

• TUI renders streamed markdown incrementally per block ()


• Skill discovery cached by scan signature; snapshot manifest builds ~5× faster; text prefilter before AST parse in tool discovery (, , , — )


• hermes update skips npm install when Node manifests are unchanged; dashboard session-list payloads trimmed + messages paginated ( — — in provider pickers (, )


• DeepInfra hardened integration; Upstage Solar provider (, )


• GPT-5.6 (Sol/Terra/Luna + Pro) end-to-end — context lengths, native/Codex catalogs, pricing, compaction caps across every route (, building on , , — , — )


• GLM-5.2 native reasoning_effort controls; Gemini request-context improvements; extra HTTP headers for LLM API calls; per-client model routing on the API server ( — , )


• Claude Sonnet 5 fully wired — curated lists, intro pricing, and metadata across every route ()


• Hide providers you don't use — enabled: false per-provider flag + excluded_providers config scrub unwanted providers from /model pickers and built-in resolution ()


• Bedrock catalog wave: real context-window probing from the live endpoint, 1M-context rows for current-gen Claude + Fable, geo-prefix parity, versioned profile-ID pricing, Opus 4.8/4.7 rows (, — — , — — , , )


• MoA: reference_max_tokens to cap advisor output and cut latency; per-preset fanout cadence (user_turn runs advisors once per user turn); stale presets surfaced without retries; half-filled preset saves rejected at the API boundary; aggregator resolves reasoning like an acting model (, )

Delegation, approvals & the agent loop

• Live subagent transcripts + durable background completions (see Highlights) ( — , , , , — , , — , — — — — )


• hermes config get / unset; warn on unknown root config keys + doctor deprecated-key reporting; display.timestamp_format (, )


• Auxiliary model usage recorded per task in session accounting; conversation-scoped Nous Portal usage tags across aux/MoA/delegate calls; --usage-file JSON report for hermes -z (, )

Sessions & compression

• Sessions export: Markdown/QMD/HTML/prompt-only/trace formats, HF upload, --redact, unified filters; full prune filter surface + bulk archive; CLI workspace filter + restore-cwd-on-resume (, , , , , , , — )

🌐 Gateway, Fleet & Relay

• Durable delivery-obligation ledger for final responses (see Highlights) ()


• Profile-based routing for inbound messages + multiplex hardening wave 2 + GATEWAY_MULTIPLEX_PROFILES override (see Highlights) (, , , , — , , — , , , )

📱 Messaging Platforms

• Inline choice pickers for /reasoning and /fast on Telegram, Discord, and Matrix — one-tap native buttons instead of typing ()


• WhatsApp: native Baileys polls (clarify renders as a poll), locations, rich inbound metadata; dashboard pairing flow ( — , , — — )


• Telegram: per-topic free-response allowlist; Google Chat clarify prompts rendered as cards ( — , — )

🖥️ Hermes Desktop App

• Contribution-driven shell on a layout-tree model — panes, zones, and layouts as data; plugin-scoped i18n locale bundles followed ( — , — )


• Hermes Cloud connection mode (salvage of , — )


• Keybind hint tooltips + keybinds settings tab + unified worktree dialog; base-branch picker for new worktrees; green unread dot for background-finished sessions; background-task sidebar indicators; grouped tool calls across text-less messages; auto-scrolling window for long tool-call runs (, , — )


• Session + project color system (inherit from project, per-session override, shared across sidebar/tabs); unified active-project identity in chat status; workspace path status action (, — salvaging , , , , — )


• Full TypeScript conversion of the desktop tree ()

📊 Web Dashboard

• Memory provider switching; safe session import flow; WhatsApp pairing; Discord-specific toolsets editable from the web UI; clarified manual Telegram bot setup (, , , )


• Terminal keep-alive + reattach for dashboard chat sessions; heavy turns isolated in a compute host; paste/drop images into Chat; browser.headed schema toggle; profile + gateway topology on /api/status; mobile/hosted OpenAI OAuth login (, , — , — — — )


• Stacked slash-skill invocations — /skill-a /skill-b do XYZ loads both skills in order (Claude Code port), with autocomplete + ghost text ( — , , — )


• TUI: model picker refresh support; custom skill bundles dispatched as agent turns; banner sizes skills display to terminal width (, , )


• Hermes Console REPL + perf follow-ups; hermes curator usage all-skills view; entry-point plugins surfaced in hermes plugins list (, — , , , , , , , — , )


• Kanban: modal create-task dialog + editable board project directory; Done-card results made obvious; grab-to-pan board scrolling; attachment toolset + CLI with SSRF-guarded URL fetch; project directory captured at board creation (, , )


• Cron: durable execution audit history; one-shot stale-removal race fixed; run-claim TTL derived from HERMES_CRON_TIMEOUT (, , , , , — )

🔒 Security & Reliability

• Vertex: credential/project/region resolution through the profile secret scope; VERTEX_CREDENTIALS_PATH/GOOGLE_APPLICATION_CREDENTIALS stripped from subprocess env ( — — , — , , , , , )


• computer-use: subprocess env sanitized across all five cua-driver spawn sites ( — — — — — , )


• Docker: terminal network toggle with full-path coverage; Git Bash Mandatory-ASLR install failures detected; Windows updater console hidden during handoff (, — — , )


• Gateway/agent: tool_call_id deduplicated across pre-API sanitizers; background review inherits parent reasoning_config for Anthropic cache parity; /new memory extraction moved off the command path (, , → reverted in and ships in this release.

👥 Contributors

450+ people contributed to this release (via commits, co-author trailers, and salvaged PRs) — the biggest contributor window yet. Thank you, all of you.

Core team

• — desktop app (the speed wave, layout-tree shell, Capabilities page, session colors, vibe reactions, TUI incremental markdown, perf harness)


• — CI overhaul (JS/TS tests wired in, autofix-via-PR, python speedups), desktop keybinds/worktrees/status indicators, full desktop TypeScript conversion


• — terminal billing (/subscription, /topup), desktop billing tab


• — desktop custom endpoint settings


• — security hardening: Vertex credential/project/region scoping through the profile secret scope, subprocess env stripping, Raft chunked-request body limits


• — desktop stability: zoom across display moves, LaTeX rendering, resume-stall and runtime-readiness fixes


• — desktop declarative memory-provider panel + honcho recall/timeout correctness


• — browser private-page CDP guard, cron one-shot liveness, gateway compression fail-closed


• — dashboard: mobile channel setup, Discord toolsets from web UI, Telegram setup clarity


• — cron one-shot stale-removal race, dashboard multiplex port-binding guard


• , , , , , , — targeted fixes across desktop, TUI, gateway, cron, webhook, nix, and browser surfaces


• Salvaged-work authors whose PRs were cherry-picked with credit this window: (sessions export), , , and many more — see the salvage PR bodies for full attribution

All contributors

, , , ,

, , , , , , , ,

, , , , , , , , , , , ,

, , , ,

, , , ,

, , , ,

, , , , , , , , , , , , , , ,

, , , , , , , , , , , , , , , , , , , , , , ,

, , , ,

, , , ,

, , , ,

, @irresi, @isfttr, @isheng-eqi, @itsflownium, @izumi0uu, @Jaaneek, @JacketPants,

@jaisup, @jakelongvu-bot, @jakepresent, @jaketracey, @JAlmanzarMint, @JasonFang1993, @jbbottoms, @jcjc81,

@JiaDe-Wu, @Jiahui-Gu, @Jigoooo, @jingsong-liu, @jneeee, , @kuangmi-bit, @kubolko, @kyssta-exe, @Kyzcreig, @l0h1nth, @labsobsidian, @laurinaitis,

@LavyaTandel, @lawyer112, @lemonwan, , @morluto, @msh01, @mssteuer, @mvanhorn, @nanami7777777, @nankingjing, ,

@okisdev, @OmarB97, @ooiuuii, @ooovenenoso, @oppih, @Osraka, @ostravajih, @otsune, , @pixel4039,

@plcunha, @pnascimento9596, @Polyhistor, , @rabadaki, @ragingbulld, @RainbowAndSun, @rainbowgore, @randimt, @rarf, @rasitakyol,

@rayjun, @raymondyan-zhijie, @re-ITRT, @RenoMG, @Rival, @RKelln, @rlaehddus302, , @sharziki, @shashwatgokhe,

, @SiteupAgencia, , @ssiweifnag, @stantheman0128, @StellarisW, @stephenschoettler, @suninrain086, @superposition,

@Supersynergy, @sweetcornna, @szafranski, @tanmayxchoudhary, @tarunravi, @tcconnally, @terry197913, @Thatgfsj,

@thegoodguysla, @thestudionorth, @TheTom, @TinkerOfThings, @tjboudreaux, @tjp2021, @Tortugasaur, @Tosko4,

@Tranquil-Flow, @trevorgordon981, @trismegistus-wanderer, @tt-a1i, @tuancookiez-hub, @TurgutKural, @Umi4Life,

, @Vissirexa, @vizi0uz, @vkkong, @vKongv, @VolodymyrBg, @vortexopenclaw, @VrtxOmega, , @webtecnica, @wesleion, @wesleysimplicio, @williamumu,

@WilsonKinyua, @wxy-nlp, @wyuebei-cloud, @x7peeps, @x9x9x9x9x9x91, @xuezhaolan,