Skip to main content
Auteryn

Changelog

What's new in Auteryn

v3.0
July 2026

The loop era

  • Goals: give an agent a goal and it keeps taking passes until a separate check agrees it's met — or your budget says stop
  • Loops: agents book their own next pass and wake on events instead of polling; every pass carries hard time and credit budgets
  • Swarms: a wide job fans out to up to four parallel agents, each on its own isolated machine, merged back into one answer
  • Self-evolving memory: agents write and consolidate their own notes and reflect after every run, so the next pass starts smarter — and every entry is yours to read and edit
  • Voice rebuilt on LiveKit: hand over a job by voice and hang up, ask for progress from the live run, watch artifacts render mid-call, and hear swarm milestones as they land
  • Bring your own machine: enroll a Linux box you own with one command — outbound-only, zero sandbox-compute credits — and drive it from your phone
  • Studio: agents and Skills drafted by AI from a description, a chat thread, a screen recording, or a YouTube link — always to the editor for your review
  • An autonomy dial on every agent — Autopilot, Guarded, Supervised, or Co-pilot — and a scheduled pass obeys the same dial you set
  • Fork any conversation to explore a branch without losing the original
  • Agent template gallery grown to 58 ready-to-install agents
v2.0
June 2026

The premium relaunch

  • Sandbox co-working: the agent's terminal, browser, and files are open to you mid-run — take control, hand it back
  • Two-hour autonomous runs with state checkpointed after every step; interrupted runs resume with full state
  • Voice: real phone calls via Twilio in designed or cloned voices, narrated decks, and podcasts
  • Model choice per agent: Gemini, Claude, GPT, or open-source models
  • Featured MCP catalog (28 servers, vendor-hosted and self-hosted) plus custom MCP server support
  • Google Workspace CLI in every sandbox: Gmail, Drive, Docs, Sheets, Calendar
  • Agent template gallery: 25 ready-to-install agents
  • Presentations: prompt to deck, theme designer, export to PDF/PPTX/MP4, publish to a link
v1.0.0
December 2025

Initial Release

  • Adaptive multi-agent orchestration with specialized agents for planning, execution, and verification
  • Gemini Computer Use integration for vision-based UI automation
  • Knowledge base with RAG-powered document retrieval
  • Flows for event-driven and scheduled automation
  • WhatsApp, Telegram, and SMS integrations via Twilio
  • GitHub, Jira, Confluence, and Google Drive integrations

We use cookies to enhance your experience and analyze site traffic. Learn more