Hermes Agent v0.19.0 cuts first-token latency to 0.9s and adds smart approvals
NousResearch · x · 2026-07-21
Hermes Agent v0.19.0 ships a broad release aimed at agent workflows, cutting cold-start first-token time from about 4.3s to 0.9s and adding a faster desktop app, terminal billing, default smart approvals, password-manager secret loading, live subagent transcripts, and a delivery ledger so completed answers are not lost.
The release also adds profile routing, expandable model/provider support, session export, incremental TUI Markdown, and various security and UX improvements. The changelog cites 1,065 PRs, 2,245 commits, 3,300 issues closed, and 450+ contributors.
Related event: Hermes Agent v0.19.0 Released: Slashing Latency and Revamping Desktop(8 posts)→
More from coding & agent
- Shopify design lead on AI-era workflow: designers are becoming full-stack editors — KlausCodes · 2026-10-26
- Ultrametric open-sources Open Startup Repo to let AI agents run startup operations — garrytan · 2026-10-26
- MCP fault injection study: agent task scores drop 60% under realistic tool failures, scale doesn't help — dair_ai · 2026-10-26
- General agents burn ~140M tokens/month on LinkedIn outreach; scripts do it 60x cheaper — ChrisHarpon2 · 2026-10-26
- OpenAI upgrades Decisions API: 400 questions per call, native voice and image support — OpenAIDevs · 2026-10-26
- NLI alone rejects 5/6 new agent memories; a 0.45 similarity gate fixes it all — Alternative_Pin9598 · 2026-10-26