Download Latest Version Kortix-Setup-0.10.15.exe (96.0 MB)
Email in envelope

Get an email when there's a new version of Suna

Home / v0.10.11
Name Modified Size InfoDownloads / Week
Parent folder
latest-mac.yml 2026-07-19 522 Bytes
latest.yml 2026-07-19 346 Bytes
Kortix-0.10.11-x86_64.AppImage 2026-07-19 115.8 MB
Kortix-Setup-0.10.11.exe 2026-07-19 96.0 MB
Kortix-Setup-0.10.11.exe.blockmap 2026-07-19 101.0 kB
latest-linux.yml 2026-07-19 384 Bytes
DESKTOP-SHA256SUMS 2026-07-19 935 Bytes
Kortix-0.10.11-universal-mac.zip 2026-07-19 197.7 MB
Kortix-0.10.11-universal-mac.zip.blockmap 2026-07-19 207.0 kB
Kortix-0.10.11-universal.dmg 2026-07-19 204.7 MB
Kortix-0.10.11-universal.dmg.blockmap 2026-07-19 214.1 kB
kortix-darwin-arm64 2026-07-19 69.6 MB
kortix-darwin-x64 2026-07-19 75.3 MB
kortix-linux-arm64 2026-07-19 99.8 MB
kortix-linux-x64 2026-07-19 100.7 MB
SHA256SUMS 2026-07-19 338 Bytes
README.md 2026-07-19 19.8 kB
v0.10.11 -- The LLM Gateway, rebuilt on the Vercel AI SDK and live models.dev -- per-model controls, OpenAI_Anthropic APIs, and a full UX overhaul source code.tar.gz 2026-07-19 90.0 MB
v0.10.11 -- The LLM Gateway, rebuilt on the Vercel AI SDK and live models.dev -- per-model controls, OpenAI_Anthropic APIs, and a full UX overhaul source code.zip 2026-07-19 93.2 MB
Totals: 19 Items   1.1 GB 1

LLM Gateway

  • Rebuilt on the Vercel AI SDK + live models.dev. The gateway now runs a single AI-SDK transport for every provider (OpenAI, Anthropic, Bedrock, OpenRouter and more), with the model catalog served verbatim from models.dev. The old per-provider transports and the LiteLLM sidecar have been removed.
  • Per-model generation controls. Set reasoning effort, temperature, top_p, and max output tokens per model — each control only appears when the model actually supports it (driven by the live catalog), and applies to every client (chat, SDK, and direct API).
  • Reasoning-effort selector in the chat composer for models that expose it (including a thinking-effort control for Claude models).
  • Two drop-in API surfaces: OpenAI-compatible /v1/chat/completions and Anthropic-compatible /v1/messages, plus /v1/models — all now documented in the API reference.
  • Provider & model manager overhaul: connect providers (incl. Bedrock via bearer token), browse models with pricing, context windows, and capabilities, verify that a key actually works, and see everything grouped under its real provider.
  • Anthropic extended thinking and prompt caching are applied correctly, and cost/usage are recorded accurately per request.
  • A gen_ai.* OpenTelemetry span is emitted per gateway call for downstream observability.

Templates

  • Many new business use-case templates across finance, sales, customer support, marketing, data, and recruiting — each with its own cover art.

Fixes & hardening

  • Sandbox proxy no longer times out healthy long reasoning/tool turns.
  • Blank projects can start sessions immediately (no more "agent not declared").
  • Project-scoped API tokens can drive their own project's sessions.
  • Per-project agent model pins no longer collide across projects.
  • Faster session/gateway paths and clearer errors on upstream failures.
  • Security & compliance: GuardDuty runtime monitoring, IAM baseline, root-login and patch/detection alerting, and corrected SSO/SCIM setup guides.

What's Changed

Full Changelog: https://github.com/kortix-ai/suna/compare/v0.10.10...v0.10.11

Source: README.md, updated 2026-07-19