Hermes Agent changelog
The last 25 stable releases of Hermes Agent, newest first, with the lines that remove, rename or deprecate something pulled out on top. Taken from the GitHub releases every morning.
Breaking changes and deprecations
- 2026.7.20
- Unified delegation concurrency caps (max_async_children deprecated); explain long provider waits on the live status line; deterministic tool-output risk exposure (#56955, #64775, #61793 — @teknium1)
- hermes config get / unset; warn on unknown root config keys + doctor deprecated-key reporting; display.timestamp_format (#65540, #67370, #40622 — @teknium1)
Latest releases
-
- Microsoft Store app: updates through the Store.
- Desktop app installed from the installer (.exe / .dmg): no change in this release; it updates with the next bundled release.
- CLI: hermes update, or re-run the installer one-liner.
- Docker / Hermes Cloud: nousresearch/hermes-agent:stable (or :latest).
-
- Desktop no longer shows suggestion pills above the composer. The pills appeared for no clear reason, mostly nudging you to set up MCP servers. They and the helpers that only they used are gone.
- Plugins that install nothing skip the dependency consent step. A plugin that declares no dependencies, or whose pyproject.toml installs nothing, now enables without an empty consent prompt.
- Dashboard: WhatsApp can be safely re-paired after logging out.
- Desktop plugin review: the surface lint no longer flags prototype writes; reviewers check them by hand.
- Desktop: the approval-mode chip follows the active profile's mode.
- Release builds: the desktop bundle's pre-build check gets enough time to verify archived build inputs when storage is slow.
- Microsoft Store app: updates through the Store.
- Desktop app installed from the installer (.exe / .dmg): no change in this release; it updates with the next bundled release.
- CLI: hermes update, or re-run the installer one-liner.
- Docker / Hermes Cloud: nousresearch/hermes-agent:stable (or :latest).
-
- Microsoft Store app: updates through the Store.
- Desktop app installed from the installer (.exe / .dmg): no change in this release; it updates with the next bundled release.
- CLI: hermes update, or re-run the installer one-liner.
- Docker / Hermes Cloud: nousresearch/hermes-agent:stable (or :latest).
-
- The gateway starts after a reboot again. After a restart, Linux can hand an early PID to an unrelated process, and the gateway could mistake it for a running gateway, so a supervised gateway (systemd, launchd, Docker)…
- Long local-model turns survive on laptops. Local requests always stream with prompt-reading progress (shown in the status line), stall timers skip time the machine was asleep, a recovered local server gets another try…
- Release: split the Microsoft Store bundle into its own windows-store lane (f9d8a740) —
- Agent: add nemotron super 3.5 default parameters (c59d2994) —
- Cli: add nemotron to NVIDIA NIM default model list (cc55270e) —
- Cli: add curated model list at the top in the model picker list (e6835fd3) —
- Release: choose what a stable release builds and tests with lanes (36a8ee18) —
- Plugin-catalog: add hermes-lang-ko — Korean Desktop language pack (e5f49b6a) —
- Plugin-catalog: add hermes-lang-pt-br (Brazilian Portuguese language pack) (0169e80c) —
- Contributors: add 2867297362mjb-sketch email mapping (9ab40641) —
-
- Agent): add nemotron super 3.5 default parameters (c59d2994) —
- Cli): add curated model list at the top in the model picker list (e6835fd3) —
- Plugin-catalog): add hermes-lang-ko — Korean Desktop language pack (e5f49b6a) —
- Plugin-catalog: add hermes-lang-pt-br (Brazilian Portuguese language pack) (0169e80c) —
- Plugin-catalog: add teamorouter (TeamoRouter model providers) (ef223406) —
- Plugin-catalog): add author-feed (5f6d6836) —
- Plugin-catalog): bump aux-ledger to 1.4.0 (6048066e) —
- Plugin-catalog): add the wait-ledger catalog card (77cb58e5) —
- Plugin-catalog): add wait-ledger (97e65322) —
- Community plugin: lightningai + lightningai-rate-limit (07515466) —
-
- A first launch that sets itself up — Open the desktop app on a computer where you have never used Hermes and it starts a short setup chat instead of a settings screen. One card at a time it asks your name, an accent c…
- Connectors: Hermes works inside your apps — The agent can now act in hosted apps such as Linear and Notion through the Nous tool gateway: ask for an app, sign in once in your browser, and the tools are usable in the s…
- Local models in one click — Hermes can now run open models entirely on your machine with nothing leaving it: no account, no API key. It installs and maintains llama.cpp with the right engine for your hardware (CPU, CU…
- Stable release channels — Hermes now ships tested SemVer releases. Every release passes source CI, Docker, Nix, signed desktop builds and install/upgrade runs on every OS before it is published, and source installs no…
- Signed desktop packages, the Microsoft Store, and one package manager — The desktop app is now a sealed, signed package that carries its own Python and Node and updates itself, so first launch builds nothing. Windows…
- The Plugin Catalog: 600 reviewed plugins — The plugin catalog launched this cycle and grew to 600 entries, each pinned to a reviewed commit and installable from Hermes Desktop or the CLI. Browse by category and star r…
- The Claude 5.5 and GPT-6 model wave — Claude Fable 5.1, Opus 5.5, Sonnet 5.5 and Haiku 5.5, GPT-6 Astra, Sol and Luna plus GPT-6.1 Sol, and Gemini 4 Argon are pickable on Nous Portal, OpenRouter and native routes wher…
- Sign in to websites with your password manager — The browser agent can log into sites with logins from 1Password, Bitwarden or Hermes's own encrypted vault, and the model never sees the password. If nothing is saved,…
- Bot Screen: watch your bot work, take over when it needs you — A bot running on a Linux gateway can have its own desktop that Hermes Desktop streams live. When it hits a login, a 2FA prompt or a CAPTCHA, you take the…
- One backend and one gateway for every profile — Hermes now runs a single messaging gateway and a single desktop backend per machine that serve all of your profiles, instead of one process per profile. Creating a profi…
-
- Updates now follow tagged releases. A source install of the official repository updates to the latest published vX.Y.Z release instead of every commit on main. An install already newer than the latest release stays wh…
- Choose the channel in the desktop app. Settings ▸ About ▸ Updates has an Update channel switch (Stable releases / Every commit) for source installs, and the update dialog now shows which channel you are on.
- Reasoning survives resume. Signed thinking replays after hermes chat --resume and on the next gateway turn, and Bedrock Converse reasoning models no longer get rejected on resumed sessions.
- Updates no longer fail behind some firewalls. Installs on main no longer fetch a release record that regional firewalls could answer with 403. The stable check uses your GitHub token when one is set (GITHUB_TOKEN or g…
- Desktop app: updates itself. Microsoft Store installs update through the Store.
- CLI: hermes update, or re-run the installer one-liner.
- Docker / Hermes Cloud: nousresearch/hermes-agent:stable (or :latest).
-
- Docker / Hermes Cloud: nousresearch/hermes-agent:stable (or :latest).
- CLI (git installs): hermes update, or re-run the installer one-liner.
- Desktop app and Termux: no change in this release; they update with the next bundled release.
- Spoofed X-Forwarded-For headers could reset the password-login rate limit and get around the per-IP cap on native sign-in
- Unauthenticated login requests could write unbounded values to the auth audit log
- The public /auth/ routes had no request-body size limit
- Native sign-in could send login codes to a non-loopback redirect, which allowed session takeover
- Automatic git calls (session workspace snapshot, subagent worktrees, kanban, worktree cleanup, hermes -w) could run clean/smudge/process filter programs defined by an untrusted repository's own config, before the firs…
- A quoted display name in the From header (e.g. "Victim " ) could make an attacker's message pass the email allowlist as an allowed sender
-
- hermes update (git installs), or re-run the installer one-liner.
- Docker / Hermes Cloud: images build from this tag (nousresearch/hermes-agent:v2026.9.24).
-
- hermes update (git installs), or re-run the installer one-liner.
- Docker / Hermes Cloud: images build from this tag (nousresearch/hermes-agent:v2026.9.21).
-
- Remote dashboard sessions no longer expire on refresh bursts (#110061, fixes #55712; salvage #71548 @Doud-FR, #55717 @liuhao1024). Both refresh paths on the gateway (cookie gate and the desktop's native bearer route)…
- Long-lived processes stop leaking duplicate state.db writer handles (#110934, fixes #100896 #103339; salvage #107974 @kshitijk4poor, mapping @Rroven): gateway, dashboard/Desktop backend, ACP and CLI readers attach rea…
- hermes update (git installs), or re-run the installer one-liner.
- Docker / Hermes Cloud: images build from this tag (nousresearch/hermes-agent:v2026.9.14).
-
- No more second writers. Profile gateways wrote hosted-room state into the root state.db every 5 seconds; the dashboard opened a writable handle on startup; cron's lifecycle guard did a raw open() on a live database (w…
- Healthy WAL databases stop wedging. OpenZFS (deleted) dentries and a close() racing an append_message both produced a sticky DeletedWalGenerationError on a perfectly good store; the read pool was handed out under an u…
- FTS damage no longer kills your turn. An error scoped to the full-text-search index was classified as whole-file corruption and fail-closed the conversation. It's now fts_index: search degrades, the index rebuilds lat…
- One corrupt row no longer kills sessions list, export, or insights. A TEXT timestamp or a 1e30 epoch used to crash the whole listing; malformed marker JSON crashed json_extract; more than 999 ids crashed bulk delete/p…
- Sessions never bind to or read another profile's database. The Desktop launch backend could pin itself to the wrong profile's state.db under a HERMES_HOME override race; session_search by bare ID silently scanned ever…
- Opening state.db no longer takes the write lock when nothing needs writing. A one-shot hermes process opening the store behind a busy gateway stalled 4–20 s and then failed with "database is locked". Now 0.01 s. (#108…
- A bare display: key in config.yaml no longer crashes every gateway turn (#106305); a queued-lane final refused by the platform is recorded and redelivered (#106316); a stalled WebSocket send no longer blocks every lat…
- Telegram bots must @mention when bots_require_mention is on, breaking bot-to-bot loops (#106534); Matrix renders LaTeX (#106515); Signal renders markdown tables (#106538); WhatsApp replies to view-once messages keep t…
- /model and auxiliary auto never bill a provider you didn't select (#107366); never auto-switch to a provider you have no credentials for (#107281); Bedrock Claude/Converse/Mantle models survive /model, fallback and re…
- Codex: patch-budget image 400 shrinks and retries (#106525); unentitled primary + fallback no longer oscillate (#106549); Azure Foundry replayed-reasoning rejection classified and pruned (#106718 @erosika). MCP OAuth…
-
- Existing install: hermes update
- Fresh install: curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
- Managed deployments should update through their deployment tooling using the new tag.
-
- Bot Mode — your agents become a society, built in — Bot Mode is now a bundled, default-on part of the desktop app: every agent profile gets a name, a deterministic avatar face (with randomize/lock controls), and a pla…
- hermes peer — bot-to-bot DMs between your agents — Any Hermes agent can now message any other by handle, across profiles and gateways, from the CLI or from inside a conversation. Ask your research bot to hand findings…
- Cron jobs that remember — Scheduled jobs stopped being goldfish. Cron agents now load and update persistent memory like every other agent, continuity=true carries each run's output into the next (so a monitor can dedu…
- Steer your subagents while they run — delegate_task gained live orchestration: list running children, steer one mid-flight with a course correction, or stop it early and keep the partial result. Add optional JSON-sche…
- The MCP command center — MCP servers and the catalog merged into one coherent desktop page with drag-in "paste anything" import, background health checks that nudge you to re-auth before a tool call fails, a fleet cos…
- A CLI power wave — Ctrl+P opens a fuzzy command palette, the /model picker filters as you type, /status shows reasoning mode, pending approvals, and context usage, and the status bar can display live cache-hit %, late…
- The agent drives the desktop's browser — The in-app browser stopped being a window the agent could only look at: Hermes now navigates, clicks, and reads it directly, and pages can be popped out to your system browser…
- Six new providers and a model catalog wave — Meta Model API (Muse Spark) arrives as a built-in provider, alongside CommandCode, Tencent TokenPlan, Nebius Token Factory, Ramp Router, and Actual Computer. The catalogs p…
- Security hardening across the board — Protected agent-instruction files (AGENTS.md, skills, memory stores) now always require write approval so a prompt-injected agent can't quietly rewrite its own standing orders. A…
- New providers: Actual Computer inference (#79644, salvage of #26491), CommandCode with GOAT/Pro/Max plans (#88308, salvage of #32909), Meta Model API (Muse Spark) as a built-in provider plugin (#88565), Tencent TokenP…
-
- hermes update from an existing install
- Fresh install: curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
-
- hermes update from an existing install
- Fresh install: curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
-
- hermes update from an existing install
- Fresh install: curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
-
- hermes update from an existing install
- Fresh install: curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
-
- Existing installs: hermes update
- Fresh install: see the installer one-liner in the README
-
- Talk to Hermes — streaming, conversational voice with barge-in — Voice mode used to mean: speak, wait for the whole reply to generate, then listen to one long audio file. Now Hermes speaks clause-by-clause as the resp…
- Wake words and hands-free control — Say your own open-vocabulary wake phrase ("hey Hermes", or anything you pick) and Hermes starts listening — detection runs on-device, so no audio leaves your machine while it waits.…
- Voice on every platform — Send a voice note to Hermes on WhatsApp, Feishu, DingTalk, LINE, QQ, Photon, or Weixin and it's transcribed and answered; auto-TTS replies are delivered platform-aware (opus where platforms w…
- Research you can trust — grounded citations with fact-checking — The new grounded-citations skill makes Hermes produce research where every claim is backed by a verifiable source: quotes are matched against the actual…
- Outbound webhooks — Hermes pushes events to your systems — Until now, integrating with Hermes meant polling or listening on a platform. Now Hermes pushes signed lifecycle events (session activity, turn completions, to…
- The desktop app becomes a platform — artifacts, plugin SDK, quick entry — Hermes desktop now renders artifacts: versioned cards with sandboxed live preview in a right-rail viewer, so generated HTML/apps run safely nex…
- Hermes speaks Agent-to-Agent — A2A v1.0 — A new bundled plugin implements the Agent-to-Agent protocol, so Hermes can discover, talk to, and be driven by other A2A-compatible agents. This closes issue #514 — one of the…
- CLI power-user wave — !command runs a shell command instantly without spending a model turn. /init scans your project and generates (or updates) an AGENTS.md. /diff shows staged/all/session changes from any surface, /…
- Correct the agent mid-turn — redirects — If Hermes is heading the wrong way, you no longer have to /stop and re-explain. Type a correction while it works and the active turn is redirected: work in flight is preserved,…
- Tools that fix themselves — A sweep of self-recovery upgrades means the agent wastes far fewer turns on tool friction: truncated terminal output spills to a file the agent can read back, patch detects already-applied…
-
- Breaking Unified delegation concurrency caps (max_async_children deprecated); explain long provider waits on the live status line; deterministic tool-output risk exposure (#56955, #64775, #61793 — @teknium1)
- Breaking hermes config get / unset; warn on unknown root config keys + doctor deprecated-key reporting; display.timestamp_format (#65540, #67370, #40622 — @teknium1)
- 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 appl…
- The desktop app speed wave — 20+ targeted perf PRs — Long replies used to cost 14× more CPU in the markdown splitter than they do now; giant diffs froze the review pane until we virtualized it; switching sessions thra…
- 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…
- 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 exa…
- 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…
- Watch your subagents work — live transcripts + durable background delegation — delegate_task dispatches now return live transcript files you can tail -f the moment the subagents launch: every tool call, result, and st…
- 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 (…
- 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 conf…
- New providers and the newest frontier models — Fireworks AI and DeepInfra land as first-class providers (Fireworks with cost estimation and a #2 slot in the provider picker), Upstage Solar joins via salvage, and the m…
- Crank the thinking to max — new reasoning effort tiers and per-model control — Reasoning effort gained max and ultra levels (GPT-5.6 and Codex's top tiers), selectable everywhere from the CLI to the desktop, with sane…
-
- Mixture-of-Agents is now a first-class model you can pick — MoA used to be a mode you toggled; now every named MoA preset shows up as a selectable model under a moa provider, right alongside Claude, GPT, and Grok in e…
- See every model's reasoning, then watch the answer stream in — When a MoA ensemble runs, each reference model's full output now renders as its own labelled block — you can read what GPT-5 thought, what Claude thought,…
- The agent verifies its own work — "done" means proven, not claimed — Hermes now records verification evidence for coding work and can decide it's finished by actually running your project's checks, not by asserting su…
- /learn — turn anything into a reusable skill by describing it — Run /learn and Hermes distills a reusable skill out of whatever you point it at — a directory, a URL, or just the workflow you walked it through five min…
- /journey — a playable timeline of everything Hermes has learned about you — The CLI and TUI gained /journey, a learning timeline that shows the memories and skills Hermes has accumulated over time — and you can edit o…
- Delegate a pile of work and keep going — background fan-out — delegate_task can now fan out multiple subagents that all run in the background: your chat is never blocked, and when every subagent finishes, their result…
- First-class coding Projects in the desktop app — The desktop app gained real, per-profile Projects — a sidebar of your codebases, a coding rail, a review pane, git worktree management, and agent-facing project tools,…
- Run Hermes at scale — scale-to-zero and drain coordination — The gateway can now go dormant when idle and quiesce cleanly before a restart, migration, or auto-update — without dropping in-flight conversations. A hoste…
- Cheaper self-improvement — smarter background review — The post-turn self-improvement fork (the one that decides whether to save a memory or skill) now routes to an auxiliary model, digests context instead of replayin…
- Compose your next prompt in your editor — /prompt — /prompt opens your $EDITOR so you can hand-write a long, multi-line prompt in real markdown instead of fighting a one-line input box. Draft a detailed spec, a struct…
-
- Hermes reaches iMessage — Photon Spectrum, no Mac relay required — There's now an iMessage platform plugin built on Photon's managed line pool. Run hermes photon login, authenticate with a device code, and Hermes can…
- Raft — Hermes joins the Raft agent network as a gateway channel — A new bundled Raft platform adapter lets Hermes connect to Raft as an external agent through a wake-channel bridge. Set RAFT_PROFILE, run the bridge, a…
- A substantially more capable desktop app — v0.16.0 shipped the desktop app; v0.17.0 deepened it across dozens of PRs. Rebindable keyboard shortcuts, native OS notifications with per-type toggles, live subagent watch-w…
- Background / async subagents — delegate work and keep going — delegate_task(background=true) now dispatches a subagent that runs in the background and returns a handle immediately. You and the model keep working while…
- Edit images, not just generate them — image-to-image in image_generate — image_generate can now edit and transform a source image, not only create one from scratch. Pass an existing image and a prompt and it routes to…
- Automation Blueprints — schedule things without learning cron — Pick an automation by name and Hermes asks you for what it needs — no cron syntax, no slot=value typing. One blueprint definition renders natively on eve…
- Cursor's Composer model, through your xAI Grok subscription — grok-composer-2.5-fast is now in the xAI OAuth model picker, with its context window reconciled to the full 200k. Composer is the fast coding model behind…
- Full profile builder in the dashboard — Build a complete Hermes profile from the browser — pick its model, choose its skills, attach its MCP servers — without hand-editing config.yaml. The dashboard also unified multi…
- Skills Hub browser rehaul — The dashboard's Skills Hub got a ground-up rework: connected hubs, a Featured section, full skill previews before you install, and a security scan on each skill. Browsing and installing ski…
- The memory tool got a major upgrade — atomic batch operations — The memory tool gained an operations array that applies a batch of add/replace/remove edits atomically against the final character budget. The model can…
Other agents
Claude CodeCodex CLIGemini CLICopilot CLIopencodeQwen CodeKimi CLIGooseMistral VibeCrushAiderCline All agents →
Run Hermes Agent next to the other agents and see when one needs you: AgentVera keeps them in one window on Mac, Windows and Linux, and on your phone.
Bring your agents to one desk.
Download, pick a project, open your first agent. Your installed CLIs are ready to go.