Nous Research shipped Hermes Agent v0.22.0, "The Threshold Release", on Oct 14 (UTC). Fresh desktop installs open a guided setup chat on a free trial model (nous/welcome) with no API key, connectors reach Gmail, Linear and Notion through the Nous tool gateway, a one-click llama.cpp runtime runs local models, installs now follow tested SemVer stable releases, and desktop builds are signed (including the Microsoft Store). The source tree shrank from about 1.06M to 698K lines (−34%).
Key Takeaways
- ✓Scale since v0.21.0: ~24,200 commits, ~6,080 merged PRs, ~7,180 issues closed, ~2,520 contributors, about 2.5x the v0.21.0 cycle
- ✓Leaner: source went from ~1.06M to 698K lines (−34%); gateway/run.py from 34,847 to 5,512 lines; ~19 rarely used tools now load on demand, roughly halving the desktop tool schema, and ~2.1k tokens came off the fixed prompt
- ✓Local models: installs llama.cpp b11370 for CPU/CUDA/Metal/Vulkan/ROCm, recommends only models that fit fully in GPU memory; catalog includes Qwen3.8 27B, Qwen3.6 35B-A3B, DeepSeek V4 Flash and any Hugging Face GGUF
- ✓600-plugin catalog, each pinned to a reviewed commit; memory providers (Honcho, Mem0, Supermemory and others) moved out of core
- ✓Faster updates that rebuild only what changed: 16.5 s vs 32.5 s on macOS (vendor figure)
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Hermes Agent v0.22.0 (Nous Research, released 2026-10-14 03:21 UTC) focuses on getting new users running. A fresh desktop install starts a guided setup chat on a free trial model (nous/welcome) that needs no API key, asks for preferences, apps and plugins, and suggests up to four first tasks. Connectors let the agent act in Gmail, Linear and Notion through the Nous tool gateway, creating a free connectors-only identity on first use; hosted apps and MCP servers now share one Connectors page, and one app can hold several named accounts. A one-click local runtime installs and maintains llama.cpp for CPU, CUDA, Metal, Vulkan or ROCm and recommends only models that fit fully in GPU memory (Qwen3.8 27B, Qwen3.6 35B-A3B, DeepSeek V4 Flash, any Hugging Face GGUF). Installs now follow tested SemVer stable releases by default (switch with hermes update --set-channel main), desktop packages are signed (MSIX via the Microsoft Store, notarized macOS for Apple Silicon), and a new hermes pm package manager swaps in hash-checked environments only after they pass a check. The plugin catalog reached 600 reviewed entries, one gateway and one backend now serve all profiles, and the source tree fell from about 1.06M to 698K lines. There are no model benchmarks in this release; the published numbers are engineering figures from the release notes.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.