This release adds 2 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+8 more
Summary
AI summaryHermes Desktop adds a native visual interface for managing Hermes agent conversations and integrations.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Low |
Adds Hermes Desktop native interface via `ollama launch hermes-desktop` with Windows support Adds Hermes Desktop native interface via `ollama launch hermes-desktop` with Windows support Source: llm_adapter@2026-06-08 Confidence: high |
— |
| Feature | Low |
Aligns OpenAI-compatible API models list with available model tags Aligns OpenAI-compatible API models list with available model tags Source: llm_adapter@2026-06-08 Confidence: high |
— |
| Refactor | Low |
Adds documentation describing the llama.cpp update process Adds documentation describing the llama.cpp update process Source: llm_adapter@2026-06-08 Confidence: high |
— |
| Refactor | Low |
Updates Zod schema examples to use native toJSONSchema helper Updates Zod schema examples to use native toJSONSchema helper Source: llm_adapter@2026-06-08 Confidence: high |
— |
Full changelog
Ollama Launch now supports Hermes Desktop, a native desktop interface for the Hermes agent. Run it alongside your Hermes agent to get a visual interface for managing conversations, integrations, and messaging apps.
ollama launch hermes-desktop
What's Changed
- Hermes Desktop is now available via
ollama launch hermes-desktopwith native Windows configuration path support - OpenAI-compatible API models list now aligns with available model tags
- Added documentation describing the llama.cpp update process
- Updated Zod schema examples to use the native toJSONSchema helper
Full Changelog: https://github.com/ollama/ollama/compare/v0.30.6...v0.30.7
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About ollama
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Beta — feedback welcome: [email protected]