Hermes Agent Changelog
Every tagged release of Hermes Agent — 32 versions, 8 with codenames — distilled from the official release notes, with guides for the features they shipped.
LATEST
v0.21.1
2026-09-07Measured at commit 6178e9f4eed8d99f4fc550add939d58c7bed6206, the window since v0.21.0 contains 5,139 non-merge commits across 4,364 changed files (+601,014 / −768,419). GitHub reports 632 merged PRs in the release window at preparation time. These figures exclude the release-version commit.
September 2026
▶v0.21.12026-09-07
Measured at commit 6178e9f4eed8d99f4fc550add939d58c7bed6206, the window since v0.21.0 contains 5,139 non-merge commits across 4,364 changed files (+601,014 / −768,419). GitHub reports 632 merged PRs in the release window at preparation time. These figures exclude the release-version commit.
August 2026
▶v0.21.0Pantheon Release2026-08-31
Highlights
- 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 place in a shared roster. Create Discord-s…
- `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 to your coding bot and get the reply…
- 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 dedupe against what it already reported),…
- 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-schema validation on child outputs, per-d…
- 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 cost/usage overlay showing schema token es…
▶v0.20.62026-08-27
Since v0.20.5 (v2026.8.19, tagged August 21), this window landed ~1,313 commits across ~1,557 files (+177,113 / −21,682) — ~525 merged PRs including consent-gated real-profile browsing (use your default Chromium profile for local browsing, with Windows close-with-approval flow); the desktop Browser getting its own OS window plus a managed SSH remote-update engine and fleet profile rail
▶v0.20.52026-08-21
Since v0.20.4 (v2026.8.18, tagged August 18), this window landed ~746 commits across ~1,250 files (+111,500 / −20,701) — ~323 merged PRs including Bot Mode group-room threads, foldable conversation summaries, blob-face avatars, and PDF/file attachments with drag & drop; the keyless web tier (5-vendor free rotation with ring failover, web search on fresh installs with zero keys); a CLI
▶v0.20.42026-08-18
Since v0.20.3 (v2026.8.16.2, tagged August 17), this window landed ~146 commits across ~265 files (+21,697 / −2,217) — ~74 merged PRs including the desktop glass/translucency surface work (matte glass, frost picker, macOS pre-select), the tabbed SESSIONS|BOTS sidebar with per-bot hide/unhide, Bot Mode group-chat fixes (long-running member turns, Markdown rendering, cross-machine routin
▶v0.20.32026-08-17
Since v0.20.2 (v2026.8.16, tagged earlier today), this window landed ~250 commits across ~461 files (+42,613 / −1,641) — ~125 merged PRs including the MCP 2.x SDK migration and 2026-07-28 stateless protocol support, the bundled Bot Mode (hermes-bots) plugin with the core teammate protocol, the CommandCode provider plugin, subprocess Python runtime ownership hardening (PYTHONHOME/PYTHON
▶v0.20.22026-08-16
Since v0.20.1 (v2026.8.13, tagged August 13), this window landed ~967 commits across ~1,279 files (+128,522 / −7,622) — ~397 merged PRs of fixes and improvements spanning the desktop app (multi-gateway Connections registry, profile-scoped refreshes, MCP health checks and deep links), the CLI (Windows update probes, Kitty keyboard protocol, chat -c hardening), the gateway (persisted mod
▶v0.20.12026-08-13
Since v0.20.0 (August 3), this window landed 1,444 commits across ~656 merged PRs, touching 2,172 files (+233,872 / −75,244), and closed ~481 issues. It is a broad stabilization-and-fixes rollup spanning the desktop app, gateway platforms, installers, tool system, and provider catalogs.
▶v0.20.0Herald Release2026-08-03
Highlights
- 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 response streams, you can interrupt it mid-…
- 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. Multi-profile voice routing means diff…
- 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 want opus, captions attached correctly).…
- 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 page text (not hallucinated), citati…
- 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, tool events) to any HTTP endpoint you…
July 2026
▶v0.19.12026-07-30
Since v2026.7.20 (v0.19.0, July 20): ~2,789 commits · ~4,748 files changed · ~442,000 insertions · ~392,300 deletions on main. This window is dominated by bug-fix and salvage waves across the gateway, voice subsystem, desktop app, and installer, plus continued platform work (Buzz/Nostr channel, FLUX3 video generation and delivery, Telegram media reliability, voice-mode regressions).
▶v0.19.0Quicksilver Release2026-07-20
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, …
- 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 longe…
- 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, pr…
- 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…
- 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 l…
▶v0.18.22026-07-08
▶v0.18.12026-07-08
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.
▶v0.18.0Judgment Release2026-07-01
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,…
- 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 aggr…
- 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 success. `/goal` gained **completion cont…
- `/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 minutes ago. It writes the … - `/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 or delete any of them right from the…
June 2026
▶v0.17.0Reach Release2026-06-19
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 si…
- 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, and Raft can wake Hermes to handle mes…
- 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 agen…
- 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-en…
- 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 the backend's edit endpoint (same …
▶v0.16.0Surface Release2026-06-06
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 gi…
- 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 …
- 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, Disc…
- Hermes Desktop speaks Simplified Chinese — full 简体中文 in the chat GUI — The desktop app now ships a complete Simplified Chinese (简体中文) translation across every UI surface — the chat window itself, sidebar, settings, command center, cron, messaging, profiles…
- Leaner default skill set — Hermes ships only what you actually need — The bundled skill set got a deliberate trim. Skills that were redundant or dead are gone (`spotify` — superseded by the native Spotify plugin's 7 tools; `linear` — superseded by `hermes …
May 2026
▶v0.15.22026-05-29
▶v0.15.1Patch Release2026-05-29
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. Eve…
- 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 t…
- 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 …
- 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)
- 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. (#34045)
▶v0.15.0Velocity Release2026-05-28
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/…
- 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, sh…
- 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 invocation), hot-path optimizations cut 47% of per-conversation func…
- `session_search` rebuilt — no LLM, no cost, 4,500× faster — The old `session_search` was an aux-LLM-powered tool that cost ~$0.30/call and took ~30 seconds to summarize three sessions, sometimes confabulating when the right session wasn't even in the FTS5 …
- Promptware defense — Brainworm-class attacks blocked at three chokepoints — Inspired by recent Brainworm / Promptware Kill Chain research (Origin HQ, arxiv 2601.09625), Hermes now defends the context window against prompt-injection attacks that try to hija…
▶v0.14.02026-05-16
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 toke…
- 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…
- `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…
- 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. …
- Debloating wave — lighter installs, less you don't use — A clean `pip install hermes-agent` used to pull down everything: every messaging adapter SDK, every image-gen SDK, every voice/TTS provider, whether you used them or not. Now those heavy backends (Sl…
▶v0.13.02026-05-07
Highlights
- Multi-agent Kanban — delegate to an AI team that actually finishes — Spin up a durable board, drop tasks on it, and let multiple Hermes workers pick them up, hand off, and close them out. Heartbeats, reclaim, zombie detection, retry budgets, and a hallucin…
- `/goal` — the agent doesn't forget what you asked it to do — Lock the agent onto a target and it stays on task across turns. The Ralph loop as a first-class primitive. (#18262, #18275, #21287)
- Show it a video — new `video_analyze` tool for native video understanding on Gemini and compatible multimodal models. (@alt-glitch) (#19301)
- Clone a voice — xAI Custom Voices lands as a TTS provider with voice cloning support. (@alt-glitch) (#18776)
- Hermes speaks your language — static gateway + CLI messages translate to 7 locales: Chinese, Japanese, German, Spanish, French, Ukrainian, and Turkish. Docs site gains a Chinese (zh-Hans) locale. (#20231, #20329, #20467, #20474, #20430, #20431)
April 2026
▶v0.12.02026-04-30
Highlights
- Autonomous Curator — `hermes curator` runs as a background agent on the gateway's cron ticker (7-day cycle default). It grades your skill library, consolidates related skills, prunes dead ones, and writes per-run reports to `logs/curator/run.json` + `REPOR…
- Self-improvement loop — substantially upgraded — The background review fork (the core of Hermes' self-improvement: after each turn it decides what memories/skills to save or update) is now class-first (rubric-based rather than free-form), active-update bia…
- Skill integrations — major expansion — ComfyUI v5 with official CLI + REST + hardware-gated local install, moved from optional to built-in by default (#17610, #17631, #17734). TouchDesigner-MCP bundled by default, expanded with GLSL, post-FX, a…
- LM Studio — first-class provider — upgraded from a custom-endpoint alias to a full-blown native provider: dedicated auth, `hermes doctor` checks, reasoning transport, live `/models` listing. (Salvage of @kshitijk4poor's #17061.) (#17102)
- Four more new inference providers — GMI Cloud (first-class, salvage of #11955 — @isaachuangGMICLOUD), Azure AI Foundry with auto-detection, MiniMax OAuth with PKCE browser flow (salvage #15203), Tencent Tokenhub (salvage of #16860). (#16663…
▶v0.11.02026-04-23
Highlights
- New Ink-based TUI — `hermes --tui` is now a full React/Ink rewrite of the interactive CLI, with a Python JSON-RPC backend (`tui_gateway`). Sticky composer, live streaming with OSC-52 clipboard support, stable picker keys, status bar with per-turn stopwatch…
- Transport ABC + Native AWS Bedrock — Format conversion and HTTP transport were extracted from `run_agent.py` into a pluggable `agent/transports/` layer. `AnthropicTransport`, `ChatCompletionsTransport`, `ResponsesApiTransport`, and `BedrockTransport` each …
- Five new inference paths — Native NVIDIA NIM (#11774), Arcee AI (#9276), Step Plan (#13893), Google Gemini CLI OAuth (#11270), and Vercel ai-gateway with pricing + dynamic discovery (#13223 — @jerilynzheng). Plus Gemini routed through the native AI Studio …
- GPT-5.5 over Codex OAuth — OpenAI's new GPT-5.5 reasoning model is now available through your ChatGPT Codex OAuth, with live model discovery wired into the model picker so new OpenAI releases show up without catalog updates. (#14720)
- QQBot — 17th supported platform — Native QQBot adapter via QQ Official API v2, with QR scan-to-configure setup wizard, streaming cursor, emoji reactions, and DM/group policy gating that matches WeCom/Weixin parity. (#9364, #11831)
▶v0.10.02026-04-16
Highlights
- Nous Tool Gateway — Paid Nous Portal subscribers now get automatic access to web search (Firecrawl), image generation (FAL / FLUX 2 Pro), text-to-speech (OpenAI TTS), and browser automation (Browser Use) through their existing subscription.…
▶v0.9.02026-04-13
Highlights
- Local Web Dashboard — A new browser-based dashboard for managing your Hermes Agent locally. Configure settings, monitor sessions, browse skills, and manage your gateway — all from a clean web interface without touching config files or the terminal. The eas…
- Fast Mode (`/fast`) — Priority processing for OpenAI and Anthropic models. Toggle `/fast` to route through priority queues for significantly lower latency on supported models (GPT-5.4, Codex, Claude). Expands across all OpenAI Priority Processing models an…
- iMessage via BlueBubbles — Full iMessage integration through BlueBubbles, bringing Hermes to Apple's messaging ecosystem. Auto-webhook registration, setup wizard integration, and crash resilience. (#6437, #6460, #6494)
- WeChat (Weixin) & WeCom Callback Mode — Native WeChat support via iLink Bot API and a new WeCom callback-mode adapter for self-built enterprise apps. Streaming cursor, media uploads, markdown link handling, and atomic state persistence. Hermes now covers t…
- Termux / Android Support — Run Hermes natively on Android via Termux. Adapted install paths, TUI optimizations for mobile screens, voice backend support, and the `/image` command work on-device. (#6834)
▶v0.8.02026-04-08
Highlights
- Background Process Auto-Notifications (`notify_on_complete`) — Background tasks can now automatically notify the agent when they finish. Start a long-running process (AI model training, test suites, deployments, builds) and the agent gets notified on compl…
- Free Xiaomi MiMo v2 Pro on Nous Portal — Nous Portal now supports the free-tier Xiaomi MiMo v2 Pro model for auxiliary tasks (compression, vision, summarization), with free-tier model gating and pricing display in model selection. (#6018, #5880)
- Live Model Switching (`/model` Command) — Switch models and providers mid-session from CLI, Telegram, Discord, Slack, or any gateway platform. Aggregator-aware resolution keeps you on OpenRouter/Nous when possible, with automatic cross-provider fallback wh…
- Self-Optimized GPT/Codex Tool-Use Guidance — The agent diagnosed and patched 5 failure modes in GPT and Codex tool calling through automated behavioral benchmarking, dramatically improving reliability on OpenAI models. Includes execution discipline guidanc…
- Google AI Studio (Gemini) Native Provider — Direct access to Gemini models through Google's AI Studio API. Includes automatic models.dev registry integration for real-time context length detection across any provider. (#5577)
▶v0.7.02026-04-03
Highlights
- Pluggable Memory Provider Interface — Memory is now an extensible plugin system. Third-party memory backends (Honcho, vector stores, custom DBs) implement a simple provider ABC and register via the plugin system. Built-in memory is the default provider. Ho…
- Same-Provider Credential Pools — Configure multiple API keys for the same provider with automatic rotation. Thread-safe `least_used` strategy distributes load across keys, and 401 failures trigger automatic rotation to the next credential. Set up via the s…
- Camofox Anti-Detection Browser Backend — New local browser backend using Camoufox for stealth browsing. Persistent sessions with VNC URL discovery for visual debugging, configurable SSRF bypass for local backends, auto-install via `hermes tools`. (#4008, #…
- Inline Diff Previews — File write and patch operations now show inline diffs in the tool activity feed, giving you visual confirmation of what changed before the agent moves on. (#4411, #4423)
- API Server Session Continuity & Tool Streaming — The API server (Open WebUI integration) now streams tool progress events in real-time and supports `X-Hermes-Session-Id` headers for persistent sessions across requests. Sessions persist to the shared Sessio…
March 2026
▶v0.6.02026-03-30
Highlights
- Profiles — Multi-Instance Hermes — Run multiple isolated Hermes instances from the same installation. Each profile gets its own config, memory, sessions, skills, and gateway service. Create with `hermes profile create`, switch with `hermes -p
`, expo… - MCP Server Mode — Expose Hermes conversations and sessions to any MCP-compatible client (Claude Desktop, Cursor, VS Code, etc.) via `hermes mcp serve`. Browse conversations, read messages, search across sessions, and manage attachments — all through the Mo…
- Docker Container — Official Dockerfile for running Hermes Agent in a container. Supports both CLI and gateway modes with volume-mounted config. (#3668, closes #850)
- Ordered Fallback Provider Chain — Configure multiple inference providers with automatic failover. When your primary provider returns errors or is unreachable, Hermes automatically tries the next provider in the chain. Configure via `fallback_providers` in …
- Feishu/Lark Platform Support — Full gateway adapter for Feishu (飞书) and Lark with event subscriptions, message cards, group chat, image/file attachments, and interactive card callbacks. (#3799, #3817, closes #1788)
▶v0.5.02026-03-28
Highlights
- Nous Portal now supports 400+ models — The Nous Research inference portal has expanded dramatically, giving Hermes Agent users access to over 400 models through a single provider endpoint
- Hugging Face as a first-class inference provider — Full integration with HF Inference API including curated agentic model picker that maps to OpenRouter analogues, live `/models` endpoint probe, and setup wizard flow (#3419, #3440)
- Telegram Private Chat Topics — Project-based conversations with functional skill binding per topic, enabling isolated workflows within a single Telegram chat (#3163)
- Native Modal SDK backend — Replaced swe-rex dependency with native Modal SDK (`Sandbox.create.aio` + `exec.aio`), eliminating tunnels and simplifying the Modal terminal backend (#3538)
- Plugin lifecycle hooks activated — `pre_llm_call`, `post_llm_call`, `on_session_start`, and `on_session_end` hooks now fire in the agent loop and CLI/gateway, completing the plugin hook system (#3542)
▶v0.4.02026-03-24
Highlights
- OpenAI-compatible API server — Expose Hermes as an `/v1/chat/completions` endpoint with a new `/api/jobs` REST API for cron job management, hardened with input limits, field whitelists, SQLite-backed response persistence, and CORS origin protection (#1756,…
- 6 new messaging platform adapters — Signal, DingTalk, SMS (Twilio), Mattermost, Matrix, and Webhook adapters join Telegram, Discord, and WhatsApp. Gateway auto-reconnects failed platforms with exponential backoff (#2206, #1685, #1688, #1683, #2166, #2584)
- @ context references — Claude Code-style `@file` and `@url` context injection with tab completions in the CLI (#2343, #2482)
- 4 new inference providers — GitHub Copilot (OAuth + token validation), Alibaba Cloud / DashScope, Kilo Code, and OpenCode Zen/Go (#1924, #1879 by @mchzimm, #1673, #1666, #1650)
- MCP server management CLI — `hermes mcp` commands for installing, configuring, and authenticating MCP servers with full OAuth 2.1 PKCE flow (#2465)
▶v0.3.02026-03-17
Highlights
- Unified Streaming Infrastructure — Real-time token-by-token delivery in CLI and all gateway platforms. Responses stream as they're generated instead of arriving as a block. (#1538)
- First-Class Plugin Architecture — Drop Python files into `~/.hermes/plugins/` to extend Hermes with custom tools, commands, and hooks. No forking required. (#1544, #1555)
- Native Anthropic Provider — Direct Anthropic API calls with Claude Code credential auto-discovery, OAuth PKCE flows, and native prompt caching. No OpenRouter middleman needed. (#1097)
- Smart Approvals + /stop Command — Codex-inspired approval system that learns which commands are safe and remembers your preferences. `/stop` kills the current agent run immediately. (#1543)
- Honcho Memory Integration — Async memory writes, configurable recall modes, session title integration, and multi-user isolation in gateway mode. By @erosika. (#736)
▶v0.2.02026-03-12
Highlights
- Multi-Platform Messaging Gateway — Telegram, Discord, Slack, WhatsApp, Signal, Email (IMAP/SMTP), and Home Assistant platforms with unified session management, media attachments, and per-platform tool configuration.
- MCP (Model Context Protocol) Client — Native MCP support with stdio and HTTP transports, reconnection, resource/prompt discovery, and sampling (server-initiated LLM requests). (#291 — @0xbyt4, #301, #753)
- Skills Ecosystem — 70+ bundled and optional skills across 15+ categories with a Skills Hub for community discovery, per-platform enable/disable, conditional activation based on tool availability, and prerequisite validation. (#743 — @teyrebaz33, #785 — @te…
- Centralized Provider Router — Unified `call_llm()`/`async_call_llm()` API replaces scattered provider logic across vision, summarization, compression, and trajectory saving. All auxiliary consumers route through a single code path with automatic credential…
- ACP Server — VS Code, Zed, and JetBrains editor integration via the Agent Communication Protocol standard. (#949)