# hermes-agent changelog

> The agent that grows with you

- Vendor: NousResearch
- Category: AI
- Official site: https://hermes-agent.nousresearch.com/
- Tracked by: What's New (https://whatsnew.fyi/product/hermes-agent)
- Harvested from: GitHub (NousResearch/hermes-agent)
- Entries below: 10 (newest first)

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

## Releases

### v2026.7.20 — Hermes Agent v0.19.0 (2026.7.20) — The Quicksilver Release

- Date: 2026-07-20
- Version: v2026.7.20
- Original notes: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.7.20
- Permalink: https://whatsnew.fyi/product/hermes-agent/releases/v2026.7.20

- **changed** — Reduced first-token latency by approximately 80% across all platforms (CLI, gateway, TUI, desktop, and cron)
- **added** — Reasoning models now stream their thinking live by default
- **changed** — Response box paints per token instead of per line
- **changed** — Desktop app markdown splitter performance improved by 14× for long replies
- **changed** — Virtualized diff review pane to prevent freezing on large diffs
- **changed** — Session switching no longer causes layout thrashing
- **changed** — Streaming no longer re-renders the sidebar and tool rows per token
- **changed** — Profile backends pre-warm on hover intent
- **changed** — Boot-hidden panes mount at idle instead of on the cold-start critical path
- **added** — Added /subscription and /topup commands to manage Nous subscription from the terminal
- **added** — Desktop app now includes a billing settings tab
- **changed** — Smart approvals are now the default for flagged commands, with LLM-based independent assessment instead of requiring user approval for each command
- **added** — User-defined deny rules to block commands even under yolo mode
- **added** — Added /deny command to tell the agent why a command was refused
- **added** — Pluggable SecretSource interface to fetch secrets from Bitwarden and 1Password at load time
- **added** — Support for multiple vaults simultaneously with deterministic precedence and conflict warnings
- **added** — Per-variable provenance tracking for secrets
- **added** — Delegate_task dispatches now return live transcript files that can be monitored in real-time
- **added** — Background delegation completions are now durable, surviving process restarts through an ownership-checked ledger

#### 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. ([#59332](https://github.com/NousResearch/hermes-agent/pull/59332), [#59389](https://github.com/NousResearch/hermes-agent/pull/59389) — @teknium1)

- **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 thrashes layout no more. Streaming no longer re-renders the sidebar and every tool row per token, profile backends pre-warm on hover intent, and boot-hidden panes mount at idle instead of on the cold-start critical path. The net effect: the desktop app feels like a native app under load, even with huge transcripts and busy agents. ([#67154](https://github.com/NousResearch/hermes-agent/pull/67154), [#67818](https://github.com/NousResearch/hermes-agent/pull/67818), [#65898](https://github.com/NousResearch/hermes-agent/pull/65898), [#66033](https://github.com/NousResearch/hermes-agent/pull/66033), [#66747](https://github.com/NousResearch/hermes-agent/pull/66747), [#67742](https://github.com/NousResearch/hermes-agent/pull/67742) and more — @OutThisLife)

- **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. ([#51639](https://github.com/NousResearch/hermes-agent/pull/51639), [#61054](https://github.com/NousResearch/hermes-agent/pull/61054), [#61067](https://github.com/NousResearch/hermes-agent/pull/61067) — @alt-glitch)

- **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>` (wh

_[Truncated at 4000 characters — full notes: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.7.20]_

### v2026.7.7.2 — Hermes Agent v0.18.2 (2026.7.7.2)

- Date: 2026-07-08
- Version: v2026.7.7.2
- Original notes: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.7.7.2
- Permalink: https://whatsnew.fyi/product/hermes-agent/releases/v2026.7.7.2

- **fixed** — WhatsApp bridge dependency now installs from the published npm release instead of a pinned git commit, making installs and Docker image builds reliable

#### Hermes Agent v0.18.2 (v2026.7.7.2)

**Release Date:** July 7, 2026

> Same-day patch on top of v0.18.1, picking up the WhatsApp Baileys dependency fix needed for tagged-release Docker builds.

---

##### What's in this patch

- **fix(whatsapp): unpin Baileys from git commit, use published 7.0.0-rc13** ([#60643](https://github.com/NousResearch/hermes-agent/pull/60643)) — the WhatsApp bridge dependency now installs from the published npm release instead of a pinned git commit, making installs and Docker image builds reliable.

Full curated release notes for the entire post-v0.18.0 window ship with v0.19.0.

##### Updating

```bash
hermes update        # existing installs
pip install -U hermes-agent
```

**Full Changelog**: [v2026.7.7...v2026.7.7.2](https://github.com/NousResearch/hermes-agent/compare/v2026.7.7...v2026.7.7.2)

### v2026.7.7 — Hermes Agent v0.18.1 (2026.7.7)

- Date: 2026-07-08
- Version: v2026.7.7
- Original notes: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.7.7
- Permalink: https://whatsnew.fyi/product/hermes-agent/releases/v2026.7.7

#### Hermes Agent v0.18.1 (v2026.7.7)

**Release Date:** July 7, 2026

> Patch release. This tag rolls up the ~660 PRs merged since v0.18.0 (July 1) — bug fixes, hardening, and in-progress feature work — into a stable tagged release for downstream consumers (Docker images, hosted deployments, PyPI installs).

---

##### About this release

This is an infrastructure-driven patch tag rather than a fully curated release. Since v0.18.0 shipped six days ago, main has accumulated roughly **667 commits across ~990 files (+89.5k/−10.4k lines)**, including installer/updater self-healing on Windows, dashboard and gateway fixes, WhatsApp dashboard pairing, MCP and provider fixes, and a large volume of stability work.

**Full curated release notes for this window will ship with v0.19.0**, which will document everything from v0.18.0 onward — highlights, feature areas, and complete contributor credits. Nothing in this window is skipped; it's documented in the next minor release.

##### Updating

```bash
hermes update        # existing installs
pip install -U hermes-agent
```

**Full Changelog**: [v2026.7.1...v2026.7.7](https://github.com/NousResearch/hermes-agent/compare/v2026.7.1...v2026.7.7)

### v2026.7.1 — Hermes Agent v0.18.0 (2026.7.1) — The Judgment Release

- Date: 2026-07-01
- Version: v2026.7.1
- Original notes: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.7.1
- Permalink: https://whatsnew.fyi/product/hermes-agent/releases/v2026.7.1

- **added** — Mixture-of-Agents is now a first-class model selectable in every model picker (CLI, TUI, desktop, gateway) as named MoA presets under a moa provider
- **added** — Each reference model's full output renders as a labelled block in Mixture-of-Agents ensembles, with the aggregator's answer streaming live
- **added** — /goal gained completion contracts allowing you to state what done looks like and judge completion against evidence instead of model assertion
- **added** — pre_verify hook for wiring in custom checks to verify coding work
- **added** — /learn command turns anything into a reusable skill by describing it, writing the skill to standards in CONTRIBUTING.md automatically
- **fixed** — Resolved all P0 and P1 issues and PRs in the entire Hermes Agent repo, clearing approximately 700 highest-priority items

#### Hermes Agent v0.18.0 (v2026.7.1)

**Release Date:** July 1, 2026
**Since v0.17.0:** ~1,720 commits · 998 merged PRs · 2,215 files changed · ~251,000 insertions · ~41,000 deletions · **949 issues closed** · **370+ community contributors**

> **The Judgment Release.** Over the last week and a half the team put nearly all of its effort into one goal: resolve **every P0 and P1 issue and PR in the entire Hermes Agent repo** — and as of this release, **100% of them are closed.** Zero open P0s. Zero open P1s. That's **~700 highest-priority items** cleared as part of **~1,950 total issues and PRs closed** this window. We intend to keep P0/P1 at zero from here on.
>
> On top of that clean-sweep, v0.18.0 is about how *well* Hermes thinks and how it *knows when its work is actually done*. Mixture-of-Agents became a first-class citizen — named ensembles of models you can pick like any other model, with every reference model's reasoning shown to you and the aggregator's answer streamed live. The agent learned to verify its own work against evidence instead of vibes, `/goal` gained completion contracts, and `/learn` + `/journey` turned self-improvement into something you can see and steer. Underneath, the gateway became genuinely deployable-at-scale (scale-to-zero, drain coordination), the desktop grew first-class coding projects and a playable memory graph, and subagents can now fan out in the background.

##### 🎯 The P0/P1 Clean Sweep — 100% resolved

This is the release headline. For a week and a half the team hammered the priority backlog day and night, and every single P0 and P1 across the whole repo is now closed:

| Priority | Issues closed | PRs merged |
|---|---|---|
| **P0** (critical) | 3 | 8 |
| **P1** (high) | 493 | 188 |
| **Total** | **496** | **196** |

That's **~692 highest-priority items resolved** in twelve days — and at the moment the sweep completed, the open P0/P1 count hit **0 across the entire repo.** The final cluster to fall was the interrupt-protected-compression sibling-fork bug (issue #56391) and its fix (#56416), closed on an all-nighter right before this release cut.

Special shoutout to **@kshitijk4poor**, who burned through the priority backlog day and night alongside the core team — the cron reliability wave, the compression-fork fix, the credential-exfil hardening, and a huge share of the P1 closures are his.

We're keeping P0/P1 at **0** from here forward. 🫡

##### ✨ Highlights

- **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 every model picker (CLI, TUI, desktop, gateway). Pick "my-council" the same way you'd pick any model, and Hermes routes your prompt through that ensemble automatically. An ensemble of frontier models deliberating on your hardest questions is now one selection away, on every surface. ([#46081](https://github.com/NousResearch/hermes-agent/pull/46081), [#53548](https://github.com/NousResearch/hermes-agent/pull/53548), [#53561](https://github.com/NousResearch/hermes-agent/pull/53561) — @teknium1)

- **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, and what Grok thought, before the aggregator synthesizes them into one answer. And that final answer now streams to you live instead of appearing all at once after a long silence. This works in the CLI, the TUI, and the desktop app. You get to watch the committee deliberate, not just read the verdict. ([#53793](https://github.com/NousResearch/hermes-agent/pull/53793), [#53855](https://github.com/NousResearch/hermes-agent/pull/53855), [#55625](https://github.com/NousResearch/hermes-agent/pull/55625), [#56101](https://github.com/NousResearch/hermes-agent/pull/56101) — @teknium1)

- **The agent ver

_[Truncated at 4000 characters — full notes: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.7.1]_

### v2026.6.19 — Hermes Agent v0.17.0 (v2026.6.19)

- Date: 2026-06-19
- Version: v2026.6.19
- Original notes: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.6.19
- Permalink: https://whatsnew.fyi/product/hermes-agent/releases/v2026.6.19

- **added** — Hermes can now send and receive iMessage through Photon Spectrum without requiring a Mac relay or BlueBubbles bridge
- **added** — Raft agent network integration allows Hermes to connect as an external agent through a wake-channel bridge with privacy-by-contract design
- **added** — Desktop app now supports rebindable keyboard shortcuts
- **added** — Desktop app now displays native OS notifications with per-type toggles
- **added** — Desktop app now features live subagent watch-windows that stream a delegated agent's activity into its own pane
- **added** — Desktop app now includes a composer model selector with per-model presets
- **added** — Desktop app now supports automatic RTL/bidi text direction
- **added** — Desktop app now has a resizable VS Code-themed terminal pane
- **added** — Desktop app now supports per-thread composer drafts
- **added** — Desktop app can now install any VS Code Marketplace theme directly into the app
- **added** — Subagents can now run in the background with delegate_task(background=true), returning a handle immediately while work continues
- **added** — image_generate can now edit and transform source images in addition to generating new ones
- **added** — Automation Blueprints allow scheduling tasks without learning cron syntax
- **added** — grok-composer-2.5-fast model is now available in the xAI OAuth model picker with full 200k context window
- **changed** — Desktop app substantially improved across dozens of areas including features and user experience
- **changed** — memory tool received a major upgrade
- **changed** — Skills Hub browser was rehauled
- **changed** — Dashboard now includes a full profile builder and secure login
- **fixed** — Curator no longer spends auxiliary model budget on routine runs

#### Hermes Agent v0.17.0 (v2026.6.19)

**Release Date:** June 19, 2026
**Since v0.16.0:** ~1,475 commits · ~800 merged PRs · 1,693 files changed · 235,390 insertions · 50,730 deletions · 300+ issues closed · 245 community contributors

> **The Reach Release.** v0.16.0 put Hermes on your desktop. v0.17.0 is about how far that reach extends — across new places to talk to it, deeper into the tools you already use, and out to the people running Hermes for a team. Hermes reached two new channels (iMessage via Photon, and the Raft agent network), the desktop app gained substantial new capability, subagents can now run in the background, image generation learned to edit, and Cursor's Composer model is reachable through an xAI Grok subscription. The dashboard got a full profile builder and secure login, the Skills Hub browser was rehauled, the `memory` tool got a major upgrade, and the curator stopped spending aux-model budget on every routine run. 300+ issues closed ride along, plus a security round.

##### ✨ Highlights

- **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 send and receive iMessage — no Mac sitting in a closet running a relay, no BlueBubbles bridge to babysit. It's positioned as the successor to BlueBubbles: free to start, nothing to self-host. If your friends and family live in the blue bubbles, Hermes lives there now too. ([#32348](https://github.com/NousResearch/hermes-agent/pull/32348), [#42582](https://github.com/NousResearch/hermes-agent/pull/42582), [#44713](https://github.com/NousResearch/hermes-agent/pull/44713) — @teknium1)

- **Raft — Hermes joins the Raft agent network as a gateway channel** — A new bundled Raft platform adapter lets Hermes connect to [Raft](https://raft.build) as an external agent through a wake-channel bridge. Set `RAFT_PROFILE`, run the bridge, and Raft can wake Hermes to handle messages — with a privacy-by-contract design where wake payloads carry only metadata (event IDs, timestamps), never message bodies. Another surface where Hermes can show up and do work. ([#48210](https://github.com/NousResearch/hermes-agent/pull/48210) — @xxchan, @teknium1)

- **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-windows** that stream a delegated agent's activity into its own pane, a composer model selector with per-model presets, automatic RTL/bidi text direction, a resizable VS Code-themed terminal pane, per-thread composer drafts, and the ability to install **any VS Code Marketplace theme** directly into the app. The desktop is now a serious daily driver, not a preview. ([#45866](https://github.com/NousResearch/hermes-agent/pull/45866), [#40660](https://github.com/NousResearch/hermes-agent/pull/40660), [#47060](https://github.com/NousResearch/hermes-agent/pull/47060), [#46959](https://github.com/NousResearch/hermes-agent/pull/46959), [#43292](https://github.com/NousResearch/hermes-agent/pull/43292), [#44596](https://github.com/NousResearch/hermes-agent/pull/44596) — @OutThisLife, @teknium1)

- **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 it churns, and the full result re-enters the conversation as a new turn the moment it finishes. Kick off a long research dive or a multi-step build, then carry on with something else instead of sitting blocked waiting on it. ([#40946](https://github.com/NousResearch/hermes-agent/pull/40946), [#46968](https://github.com/NousResearch/hermes-agent/pull/46968) — @teknium1)

- **Edit images, not just generate them — image-to-image in `image_generate`**

_[Truncated at 4000 characters — full notes: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.6.19]_

### v2026.6.5 — Hermes Agent v0.16.0 (2026.6.5) — The Surface Release

- Date: 2026-06-06
- Version: v2026.6.5
- Original notes: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.6.5
- Permalink: https://whatsnew.fyi/product/hermes-agent/releases/v2026.6.5

- **added** — Add native desktop application for macOS, Linux, and Windows with one-click install, in-app self-update, drag-and-drop file support, inline model picker in status bar, and concurrent multi-profile sessions
- **added** — Add ability to connect desktop app to remote Hermes gateway over OAuth or username/password authentication
- **added** — Add browser-based administration panel in web dashboard for configuring messaging channels, MCP catalog, credentials, webhooks, memory, and OIDC/username-password login
- **added** — Add Quick Setup via Nous Portal for first-time setup to get from install to first message in seconds
- **added** — Add Simplified Chinese translation for desktop application
- **added** — Add /undo command to take back the last N turns
- **added** — Add fuzzy-searchable model picker across desktop, web, TUI, and CLI interfaces
- **changed** — Trim default skill set to essential capabilities
- **changed** — Add NVIDIA/skills to trusted Skills Hub taps
- **fixed** — Fix CVE-2026-48710 by pinning Starlette version
- **fixed** — Harden SSRF off-loop protections
- **security** — Strip credentials from subprocess calls

#### Hermes Agent v0.16.0 (v2026.6.5)

**Release Date:** June 5, 2026
**Since v0.15.2:** 874 commits · 542 merged PRs · 1,962 files changed · 205,216 insertions · 46,217 deletions · 399 issues closed (2 P0, 62 P1, 16 security-tagged) · 170 community contributors (including co-authors)

> **The Surface Release.** Hermes meets you wherever you work. A brand-new native desktop app — built across 100 PRs and 159 commits in a single week — gives you Hermes as a real macOS/Linux/Windows application: one-click install, in-app self-update, drag-and-drop files into chat, an inline model picker in the status bar, concurrent multi-profile sessions, a full Simplified Chinese translation, and the ability to connect to a remote Hermes gateway over OAuth or username/password. Alongside it, the web dashboard grew a full browser-based administration panel (MCP catalog, messaging channels, credentials, webhooks, memory, pluggable OIDC / username-password login), and first-time setup got a "Quick Setup via Nous Portal" path that gets you from install to first message in seconds. The default skill set was trimmed to what you actually need, NVIDIA/skills joined the trusted Skills Hub taps, the model picker is now fuzzy-searchable everywhere (desktop, web, TUI, CLI), and `/undo` finally lets you take back the last N turns. 2 P0 and 62 P1 closures ride along, plus a security round (CVE-2026-48710 Starlette pin, SSRF off-loop hardening, subprocess credential stripping).

---

##### ✨ Highlights

- **Hermes Desktop — a real native app, not a terminal wrapper** — This is the headline. There's now a `apps/desktop/` Electron application that installs like any other desktop app on macOS, Linux, and Windows, updates itself in place from inside the app, and gives you a polished GUI for everything Hermes does. You get a proper chat window with streaming, a session list you can archive and search, drag-and-drop files anywhere in the chat area, clipboard image paste, a Cmd+K command palette, and a model picker right in the status bar. If you've been telling friends "it's a CLI agent" and watching their eyes glaze over — now you can just send them an installer. None of this existed a week ago. ([#20059](https://github.com/NousResearch/hermes-agent/pull/20059), [#35607](https://github.com/NousResearch/hermes-agent/pull/35607), [#37099](https://github.com/NousResearch/hermes-agent/pull/37099), [#37379](https://github.com/NousResearch/hermes-agent/pull/37379), [#38631](https://github.com/NousResearch/hermes-agent/pull/38631) — @OutThisLife, @jquesnelle, @ethernet8023, @austinpickett, @benbarclay)

- **Run the desktop app against a remote Hermes — sign in with OAuth or username/password** — The desktop app doesn't have to run Hermes locally. Point it at a remote Hermes gateway (your homelab, a hosted box, a teammate's server) and it connects over a secure WebSocket, authenticating with OAuth or a username/password login — no fiddling with `--insecure` flags or hand-copied session tokens. Each profile can target its own remote host, and you can run concurrent sessions across multiple profiles in one window with cross-profile `@session` links. The practical version: your laptop runs a thin GUI, the heavy agent runs wherever your API keys and compute live. ([#37888](https://github.com/NousResearch/hermes-agent/pull/37888), [#38851](https://github.com/NousResearch/hermes-agent/pull/38851), [#39330](https://github.com/NousResearch/hermes-agent/pull/39330), [#39778](https://github.com/NousResearch/hermes-agent/pull/39778) — @benbarclay, @OutThisLife, @teknium1)

- **The web dashboard is now a full admin panel — configure everything from the browser** — The dashboard grew from "view your sessions" into a complete administration surface. There's a Channels page that sets up every gateway messaging platform (Telegram, Discord, Slack, etc.) from the browser, an admin panel for the MCP catalog with enable/disable toggles, credential management, webhook and hook creation, memo

_[Truncated at 4000 characters — full notes: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.6.5]_

### v2026.5.29.2 — Hermes Agent v0.15.2 (2026.5.29.2)

- Date: 2026-05-29
- Version: v2026.5.29.2
- Original notes: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.5.29.2
- Permalink: https://whatsnew.fyi/product/hermes-agent/releases/v2026.5.29.2

- **fixed** — Ship bundled plugin.yaml manifests in wheel and sdist

#### Hermes Agent v0.15.2 (v2026.5.29.2)

**Release Date:** May 29, 2026

##### 🐛 Bug Fixes

- Packaging): ship bundled plugin.yaml manifests in wheel and sdist ([`827f7f07`](https://github.com/NousResearch/hermes-agent/commit/827f7f07825be57108cbea18325e8f5e9fb5d2f2))

##### 👥 Contributors

Thank you to everyone who contributed to this release!

- @outsourc-e (1 commit)
- @dparikh79 (1 commit)
- @ousiaresearch (1 commit)
- @libre-7 (1 commit)

**Full Changelog**: [v2026.5.29...v2026.5.29.2](https://github.com/NousResearch/hermes-agent/compare/v2026.5.29...v2026.5.29.2)

### v2026.5.29 — Hermes Agent v0.15.1 (2026.5.29) — The Patch Release

- Date: 2026-05-29
- Version: v2026.5.29
- Original notes: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.5.29
- Permalink: https://whatsnew.fyi/product/hermes-agent/releases/v2026.5.29

- **fixed** — Dashboard infinite-reload loop in loopback mode caused by 401 responses from /api/auth/me triggering stale-token reload guard
- **changed** — Docker dashboard --insecure is now an explicit HERMES_DASHBOARD_INSECURE=1 env var opt-in instead of being inferred from bind host
- **fixed** — MCP bare commands (npx, npm, node) now resolve against /usr/local/bin for Docker compatibility
- **fixed** — Skills page source pills and category sidebar now reflect live catalog state
- **fixed** — Kanban worker SIGTERM signal now properly terminates the process
- **added** — Skills page now loads full 19,932-entry skills.sh catalog instead of partial paginated results
- **fixed** — Kanban workers now receive images referenced in task bodies for vision-capable models
- **fixed** — Markdown files now deliver correctly with media-delivery validation using denylist-only approach
- **fixed** — Gateway probe stepdown no longer attempts to step down to smaller model without explicit provider context limit
- **fixed** — /yolo mid-session now enables per-session bypass instead of only toggling environment variable
- **changed** — /model and hermes model commands now show the same list with disk cache for picker startup

#### Hermes Agent v0.15.1 (v2026.5.29)

**Release Date:** May 29, 2026
**Since v0.15.0:** 28 commits · 21 merged PRs · hotfix release · 9 contributors

> **The Patch Release.** A same-day hotfix for v0.15.0. Headline fix: the dashboard infinite-reload loop that hit anyone running v0.15.0 in loopback mode (Docker, hosted Hermes, fresh installs). A handful of other v0.15.0 follow-ups go along for the ride — kanban worker SIGTERM, `/model` picker unification, `/yolo` session bypass, the full 19,932-entry skills.sh catalog, `.md` media delivery restoration, gateway probe-stepdown safety, web-URL redaction passthrough, kanban worker vision on referenced images, hindsight observation-default. Docker users get an explicit `--insecure` opt-in env var (no more bind-host inference), MCP server bare-command PATH resolution, and arm64 PR-build cache fixes.

---

##### ✨ Highlights

- **Dashboard 401 reload loop fixed** — In loopback mode the dashboard's identity probe (`/api/auth/me`) returns 401 by design, but v0.15.0's stale-token reload guard treated every 401 as a rotated session token and full-page-reloaded to pick up a fresh one. Every successful sibling call cleared the one-shot reload guard, so the page reload-looped forever (Firefox: "Navigated to /sessions" storm; Chrome: React re-render storm). Fix adds an `allowUnauthorized` opt-out to `fetchJSON` that skips only the loopback stale-token reload — 401 still throws so `AuthWidget` swallows it, gated-mode `login_url` redirects are unaffected. Closes [#34206](https://github.com/NousResearch/hermes-agent/issues/34206), [#34202](https://github.com/NousResearch/hermes-agent/issues/34202). ([#30698](https://github.com/NousResearch/hermes-agent/pull/30698) — @austinpickett)

- **Docker dashboard `--insecure` is now an explicit env opt-in, never derived from bind host** — Previously the Docker entrypoint inferred `--insecure` when the dashboard bound to a non-loopback host. That conflated "I want LAN access" with "I want to disable the same-origin guard." The fix splits them: bind host is bind host, and disabling the dashboard's loopback auth requires an explicit `HERMES_DASHBOARD_INSECURE=1`. Existing setups that genuinely wanted insecure binding must now set the env var. ([#34188](https://github.com/NousResearch/hermes-agent/pull/34188), [#34204](https://github.com/NousResearch/hermes-agent/pull/34204) — @benbarclay)

- **MCP bare command resolution under Docker** — MCP servers configured with bare commands (`npx`, `npm`, `node`) now resolve against `/usr/local/bin` so they actually launch inside the Docker image where those binaries live. v0.15.0 left these failing silently in containers when the agent's effective PATH didn't include the Node toolchain location. ([#34186](https://github.com/NousResearch/hermes-agent/pull/34186) — @benbarclay)

- **Skills page sidebar / source pills restored** — A stale `useMemo` dependency in the new dashboard skills page collapsed the source pills and category sidebar to "All" only. Fixed; both surfaces now reflect the live catalog state. ([#34194](https://github.com/NousResearch/hermes-agent/pull/34194))

- **Kanban worker can be killed again** — `SIGTERM` on a kanban worker was being absorbed by an intermediate process and the worker stayed running. Closes [#28181](https://github.com/NousResearch/hermes-agent/issues/28181). ([#34045](https://github.com/NousResearch/hermes-agent/pull/34045))

- **Full skills.sh catalog (858 → 19,932 entries)** — The skills hub page was pulling a partial paginated catalog. The fetch now walks the sitemap, so all 19,932 skills.sh entries surface in the picker instead of just the first 858. ([#34025](https://github.com/NousResearch/hermes-agent/pull/34025))

---

##### 🐛 Bug Fixes

###### Dashboard / Web

- **`/api/auth/me` 401 no longer triggers reload loop** in loopback mode — ([#30698](https://github.com/NousResearch/hermes-agent/pull/30698) — @austinpickett)
- **Skills page source pills + category sidebar restore

_[Truncated at 4000 characters — full notes: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.5.29]_

### v2026.5.28 — Hermes Agent v0.15.0 (2026.5.28) — The Velocity Release

- Date: 2026-05-28
- Version: v2026.5.28
- Original notes: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.5.28
- Permalink: https://whatsnew.fyi/product/hermes-agent/releases/v2026.5.28

- **changed** — Refactored run_agent.py from 16,083 lines to 3,821 lines (-76%) with code redistributed across 14 cohesive modules under agent/
- **changed** — Enhanced Kanban with multi-agent platform capabilities including auto-decomposition, swarm topology, scheduled tasks, per-task worktrees, per-task model overrides, and task lifecycle management
- **changed** — Improved cold-start performance by deferring openai._base_client import, optimizing hot paths, deferring compression checks, and implementing adaptive subprocess polling
- **changed** — Rebuilt session_search to eliminate LLM dependency and cost, achieving 4,500× performance improvement and reducing search time from 90 seconds to 20 milliseconds
- **changed** — Reduced hermes --version cold start time from 701ms to 258ms (63% improvement)
- **changed** — Reduced per-conversation function calls by 47% (from 399k to 213k for 31-turn chat)
- **added** — Added multi-agent orchestrator endpoints including /workers/active, /runs/{id}, and /inspect for task monitoring
- **added** — Added skill bundles feature to load entire workflows with a single slash command
- **added** — Added Bitwarden Secrets Manager integration to replace per-provider API keys with single bootstrap token
- **added** — Added two new image generation providers: Krea 2 Medium and Krea 2 Large
- **added** — Added FAL image generation provider as plugin
- **added** — Added Nous-approved MCP catalog with interactive picker
- **added** — Added OpenHands orchestration skill
- **added** — Added ntfy as the 23rd messaging platform
- **added** — Added Web Search plugin for xAI integration
- **added** — Added xai-oauth hermes proxy upstream support
- **added** — Added multi-session orchestrator to Ink TUI
- **changed** — Implemented retired-May-15 xAI model detection with hermes migrate xai command
- **changed** — Enhanced xAI integration with natural TTS speech-tag pauses
- **added** — Added base_url leak guard for xAI
- **added** — Added OpenAI-style execution guidance for Grok model
- **security** — Added Promptware defense against Brainworm-class attacks

#### Hermes Agent v0.15.0 (v2026.5.28)

**Release Date:** May 28, 2026
**Since v0.14.0:** 1,302 commits · 747 merged PRs · 1,746 files changed · 282,712 insertions · 36,699 deletions · 560+ issues closed (15 P0, 65 P1, 19 security-tagged) · 321 community contributors (including co-authors)

> **The Velocity Release.** Hermes gets dramatically faster — to start, to run, to ship work, and to grow. The 16,083-line `run_agent.py` collapses to 3,821 (-76%) across 14 cohesive `agent/*` modules. Kanban grew into a real multi-agent platform across 104 PRs — orchestrator auto-decomposition, swarm topology, scheduled tasks, worktree-per-task, per-task model overrides. The cold-start perf wave keeps going: another second shaved off launch, 47% fewer per-conversation function calls, `hermes --version` flipping the head-to-head benchmark against Codex CLI. `session_search` is 4,500× faster and free now. Promptware defense lands against Brainworm-class attacks. Bitwarden Secrets Manager replaces N per-provider API keys with one bootstrap token. Skill bundles let one slash command load a whole workflow. The Ink TUI gets a multi-session orchestrator. Two new image_gen providers (Krea 2 Medium + Large, FAL ported to plugin), the Nous-approved MCP catalog with an interactive picker, an OpenHands orchestration skill, ntfy as the 23rd messaging platform, and a deep xAI integration round (Web Search plugin, xai-oauth `hermes proxy` upstream, retired-May-15 model detection + `hermes migrate xai`, natural TTS speech-tag pauses, base_url leak guard, OpenAI-style execution guidance for Grok). 15 P0 + 65 P1 closures alongside.

---

##### ✨ Highlights

- **The Big Refactor — `run_agent.py` is no longer 16,000 lines** — The file at the heart of Hermes — the agent conversation loop — has been reduced from 16,083 lines to 3,821 (-76%), with the extracted code redistributed across 14 cohesive modules under `agent/`. Behavior is unchanged: every extraction keeps a thin forwarder on `AIAgent`, every test patch path still works, every external caller is compatible. The reason you care: future Hermes development moves faster, plugin authors can finally grep the codebase, and the file that took 90 seconds to load in your editor opens in a blink. ([#27248](https://github.com/NousResearch/hermes-agent/pull/27248))

- **Kanban grew into a real multi-agent platform — 104 PRs end to end** — Triage auto-decomposes one task into a tree of sub-tasks. `hermes kanban swarm` creates a full Swarm v1 graph in one command — root, parallel workers, gated verifier, gated synthesizer, shared blackboard. Tasks support per-task model overrides (cheap models for boilerplate, expensive ones for hard sub-tasks), board-level default workdirs, per-task worktree paths and branches, scheduled start times, configurable claim TTL, retry fingerprinting, stale-task detection, respawn guards, and a drag-to-delete trash zone. Workers report through `/workers/active`, `/runs/{id}`, and `/inspect` endpoints. ([#27572](https://github.com/NousResearch/hermes-agent/pull/27572), [#28443](https://github.com/NousResearch/hermes-agent/pull/28443), [#28364](https://github.com/NousResearch/hermes-agent/pull/28364), [#28394](https://github.com/NousResearch/hermes-agent/pull/28394), [#28462](https://github.com/NousResearch/hermes-agent/pull/28462), [#28384](https://github.com/NousResearch/hermes-agent/pull/28384), [#28467](https://github.com/NousResearch/hermes-agent/pull/28467), [#28455](https://github.com/NousResearch/hermes-agent/pull/28455), [#28452](https://github.com/NousResearch/hermes-agent/pull/28452), [#28432](https://github.com/NousResearch/hermes-agent/pull/28432), [#28468](https://github.com/NousResearch/hermes-agent/pull/28468), [#28420](https://github.com/NousResearch/hermes-agent/pull/28420))

- **Cold-start perf wave keeps going — another second saved, 47% fewer per-turn function calls** — Three new optimization rounds: defer `openai._base_client` import (-240ms / -17MB on every CLI invoc

_[Truncated at 4000 characters — full notes: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.5.28]_

### v2026.5.16 — Hermes Agent v0.14.0 (2026.5.16)

- Date: 2026-05-16
- Version: v2026.5.16
- Original notes: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.5.16
- Permalink: https://whatsnew.fyi/product/hermes-agent/releases/v2026.5.16

- **added** — xAI Grok available as SuperGrok OAuth provider with grok-4.3 bumped to 1M context window
- **added** — OpenAI-compatible local proxy for OAuth providers via hermes proxy command
- **added** — x_search as first-class X (Twitter) search tool with OAuth or API key authentication
- **added** — Microsoft Teams integration with Graph auth, webhook listener, pipeline runtime, and outbound delivery
- **added** — LINE and SimpleX Chat as new messaging platforms
- **added** — Cross-session 1-hour Claude prompt caching
- **added** — /handoff command that transfers sessions live
- **added** — Native button UI for clarify on Telegram and Discord
- **added** — Discord channel history backfill
- **added** — LSP semantic diagnostics on every write
- **added** — Unified pluggable video_generate
- **added** — computer_use cua-driver backend for non-Anthropic providers
- **added** — Clickable URLs in any terminal
- **added** — Zed ACP Registry integration via uvx
- **added** — Native Windows beta
- **added** — 9 new optional skills
- **added** — OpenRouter Pareto Code router
- **added** — huggingface/skills as trusted default tap
- **changed** — Hermes Agent now available as pip install hermes-agent on PyPI
- **changed** — Heavy backends now lazy-install on first use instead of being bundled by default
- **changed** — [all] extras drop everything covered by lazy-deps
- **changed** — Installer falls back through tiers when a wheel does not fit platform
- **changed** — Hermes launch shaved approximately 19 seconds off cold-start time
- **changed** — Browser CDP calls are 180x faster
- **fixed** — Supply-chain advisory checker scans every install for unsafe versions

#### Hermes Agent v0.14.0 (v2026.5.16)

**Release Date:** May 16, 2026
**Since v0.13.0:** 808 commits · 633 merged PRs · 1393 files changed · 165,061 insertions · 545 issues closed (12 P0, 50 P1) · 215 community contributors (including co-authors)

> The Foundation Release — Hermes installs and runs anywhere, ships with the things you actually want to use, and stops shipping the things you don't. xAI Grok lands as a SuperGrok OAuth provider with grok-4.3 bumped to a 1M context window. A new OpenAI-compatible local proxy turns any OAuth-authed Hermes provider — Claude Pro, ChatGPT Pro, SuperGrok — into an endpoint that Codex / Aider / Cline / Continue can hit. `x_search` lands as a first-class X (Twitter) search tool with OAuth-or-API-key auth. The Microsoft Teams stack is wired end-to-end (Graph auth + webhook listener + pipeline runtime + outbound delivery). A debloating wave makes installs dramatically lighter — heavyweight backends now lazy-install on first use, the `[all]` extras drop everything covered by lazy-deps, and a tiered install falls back when a wheel rejects on your platform. `pip install hermes-agent` works from PyPI. The cold-start wave shaves ~19 seconds off `hermes` launch. Browser CDP calls are 180x faster. Two new messaging platforms (LINE + SimpleX Chat) bring the total to 22. Cross-session 1-hour Claude prompt caching, `/handoff` that actually transfers sessions live, native button UI for `clarify` on Telegram and Discord, Discord channel history backfill, LSP semantic diagnostics on every write, a unified pluggable `video_generate`, a `computer_use` cua-driver backend that finally works with non-Anthropic providers, clickable URLs in any terminal, Zed ACP Registry integration via `uvx`, native Windows beta, 9 new optional skills, OpenRouter Pareto Code router, huggingface/skills as a trusted default tap. 12 P0 + 50 P1 closures.

---

##### ✨ Highlights

- **xAI Grok via SuperGrok OAuth — and grok-4.3 jumps to a 1M context window** — If you pay for SuperGrok, you can now use Grok inside Hermes by signing in with your xAI account — no API key, no separate billing. The wire-through also bumps grok-4.3 to a 1M token context window, so you can drop whole codebases or research corpora into a single prompt. Includes proper handling for entitlement errors and an SSH-to-tunnel docs page for when you're SSH'd into a remote box and need to complete the OAuth flow. ([#26534](https://github.com/NousResearch/hermes-agent/pull/26534), [#26664](https://github.com/NousResearch/hermes-agent/pull/26664), [#26644](https://github.com/NousResearch/hermes-agent/pull/26644), [#26592](https://github.com/NousResearch/hermes-agent/pull/26592))

- **OpenAI-compatible local proxy for OAuth providers** — Run `hermes proxy` and you get a `http://localhost:port` endpoint that speaks the OpenAI API but is backed by whichever OAuth provider you're signed into — Claude Pro, ChatGPT Pro, SuperGrok. Now any tool that expects an OpenAI-compatible endpoint (Codex CLI, Aider, Cline, Continue, your custom scripts) just works with your existing subscription, no API key required. One subscription, every tool. ([#25969](https://github.com/NousResearch/hermes-agent/pull/25969))

- **`x_search` — first-class X (Twitter) search tool** — The agent can now search X directly without installing a skill or wiring up a custom integration. Search the timeline, find threads, surface specific posts — straight from the chat. Auth with either your X OAuth login or an API key, whichever you have. ([#26763](https://github.com/NousResearch/hermes-agent/pull/26763))

- **Microsoft Teams — end-to-end** — Hermes can now read messages from Teams and post back. The full Microsoft Graph stack lands together: auth + client foundation, a webhook listener that receives Teams events, a pipeline plugin runtime, and outbound delivery. Wire up the bot once, then chat to your agent from any Teams channel, DM, or group. (salvages of #21408–#21411) ([#21922](https://github.com/N

_[Truncated at 4000 characters — full notes: https://github.com/NousResearch/hermes-agent/releases/tag/v2026.5.16]_