Skip to content

anything-llm

v1.14.0 Breaking

This release includes 2 breaking changes for platform teams planning a safe upgrade.

Published 1mo AI Agents & Assistants
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-computer agent-harness agent-orchestration agentic-ai ai-agents computer-use
+9 more
hermes-agent llm local-ai localai multimodal no-code open-claw self-hosted-ai vector-db

ReleasePort's take

Light signal
editorial:auto 1mo

The release introduces several new features (e.g., STT support for additional providers, TTS support for KokoroTTS) and fixes a context‑limit bug in agents.

Why it matters: Feature additions expand capability options; the agent context limit fix resolves a critical detection issue affecting workflow reliability.

Summary

AI summary

Updates Bug Fixes, feat, and fix across a mixed release.

Changes in this release

Feature Medium

Default chat thread is killed when creating a new thread.

Default chat thread is killed when creating a new thread.

Source: llm_adapter@2026-06-09

Confidence: high

 —
Feature Medium

All model providers are opt-out of tool calling by default, improving agent performance.

All model providers are opt-out of tool calling by default, improving agent performance.

Source: llm_adapter@2026-06-09

Confidence: high

 —
Feature Medium

Adds STT support for Deepgram, GenericOAI, Lemonade, and OpenAI.

Adds STT support for Deepgram, GenericOAI, Lemonade, and OpenAI.

Source: llm_adapter@2026-06-09

Confidence: high

 —
Feature Medium

Adds TTS support for KokoroTTS.

Adds TTS support for KokoroTTS.

Source: llm_adapter@2026-06-09

Confidence: high

 —
Feature Medium

Web‑scraping now converts pages to Markdown for better parsing.

Web‑scraping now converts pages to Markdown for better parsing.

Source: llm_adapter@2026-06-09

Confidence: high

 —
Feature Medium

Summary tool overhauled to provide transparent, longer summaries with confirmation prompts.

Summary tool overhauled to provide transparent, longer summaries with confirmation prompts.

Source: llm_adapter@2026-06-09

Confidence: high

 —
Feature Medium

Improves GenericOAI provider functionality.

Improves GenericOAI provider functionality.

Source: llm_adapter@2026-06-09

Confidence: high

 —
Feature Medium

Adds 24‑hour system variable date and time formats.

Adds 24‑hour system variable date and time formats.

Source: llm_adapter@2026-06-09

Confidence: high

 —
Feature Medium

Enhances LaTeX rendering support.

Enhances LaTeX rendering support.

Source: llm_adapter@2026-06-09

Confidence: high

 —
Bugfix Medium

Fixes context limit detection issue for agents.

Fixes context limit detection issue for agents.

Source: llm_adapter@2026-06-09

Confidence: high

 —
Bugfix Low

Resolves SEARXNG double‑encoding of search queries.

Resolves SEARXNG double‑encoding of search queries.

Source: granite4.1:30b@2026-06-09-audit

Confidence: low

 —
Bugfix Low

Applies universal timeout to all fetch requests.

Applies universal timeout to all fetch requests.

Source: granite4.1:30b@2026-06-09-audit

Confidence: low

 —
Bugfix Low

Escapes illegal XML characters in generated documents (e.g., Word files).

Escapes illegal XML characters in generated documents (e.g., Word files).

Source: granite4.1:30b@2026-06-09-audit

Confidence: low

 —
Bugfix Low

Adds uninstall checkbox on Windows to remove all AnythingLLM data.

Adds uninstall checkbox on Windows to remove all AnythingLLM data.

Source: granite4.1:30b@2026-06-09-audit

Confidence: low

 —
Bugfix Low

Fixes tray behavior when app starts in background or Desktop Assistant is toggled.

Fixes tray behavior when app starts in background or Desktop Assistant is toggled.

Source: granite4.1:30b@2026-06-09-audit

Confidence: low

 —
Full changelog

Improvements

  • [x] Cerebres provider
  • [x] The default chat thread is now killed when you create a new thread. If you have chats on the default thread, it will be available still. New workspaces or workspaces with no chats on default will no longer show it.
  • [x] All model providers are now opt-out of tool calling by default. Everything will call tools by default unless you opt-out offering better performance for agents everywhere
  • [x] STT Support for Deepgram, GenericOAI, Lemonade, & OpenAI
  • [x] TTS Support for KokoroTTS
  • [x] Web-scraping now will convert to markdown for better parsing and chat followup tasks with minimal context bloat
  • [x] Summary tool was overhauled. Now it will so better summaries with transparency as well as ask before continuing for longer summaries
  • [x] Improvements to the GenericOAI provider
  • [x] 24hour system variable formats
  • [x] Better LaTex rendering support

Bug Fixes

  • [x] Context limit detection issue for agents: https://github.com/Mintplex-Labs/anything-llm/pull/5716
  • [x] SEARXNG double encoding: https://github.com/Mintplex-Labs/anything-llm/pull/5723
  • [x] Timeouts for all fetch requests https://github.com/Mintplex-Labs/anything-llm/pull/5721
  • [x] Escape illegal XML in word docs, etc https://github.com/Mintplex-Labs/anything-llm/pull/5760
  • [x] (Windows) On unisntall, checkbox to remove all AnythingLLM data is now present
  • [x] Tray Fixes when app starts in background or Desktop Assistant feature is toggled.

What's Changed

  • docs: list all cloud embedding providers by @narutamaaurum in https://github.com/Mintplex-Labs/anything-llm/pull/5701
  • feat: add Cerebras as an LLM provider by @officialasishkumar in https://github.com/Mintplex-Labs/anything-llm/pull/5699
  • fix provider override in agents by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5716
  • docs: fix self-hosted terms wording by @Zhao73 in https://github.com/Mintplex-Labs/anything-llm/pull/5737
  • fix: avoid double-encoding SearXNG search queries by @trick77 in https://github.com/Mintplex-Labs/anything-llm/pull/5723
  • Kill default thread by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5739
  • feat: add server-side speech-to-text with OpenAI provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5596
  • Kokoro TTS provider by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5679
  • add windows paths to isWithin by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5685
  • apply universal sdk timeout by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5721
  • fix: support Azure & Dell Pro AI Studio providers in agent summarization fallback by @sanidhyasin in https://github.com/Mintplex-Labs/anything-llm/pull/5738
  • Turn HTML scraped sites to Markdown for better research by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5742
  • Improve agent summarizer tool by @shatfield4 in https://github.com/Mintplex-Labs/anything-llm/pull/5719
  • Generic OpenAI improvements by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5746
  • feat: make document sync stale-after interval configurable by @sanidhyasin in https://github.com/Mintplex-Labs/anything-llm/pull/5747
  • fix: strip XML-illegal control characters from generated documents by @sanidhyasin in https://github.com/Mintplex-Labs/anything-llm/pull/5760
  • feat(embed): opt-in deny-by-default for embeds with no allowlist by @dmitrymaranik in https://github.com/Mintplex-Labs/anything-llm/pull/5759
  • add 24 hours date and time formats to SystemVariables by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5778
  • Make native tool calling opt-out instead of opt-in by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5783
  • better LaTex support by @timothycarambat in https://github.com/Mintplex-Labs/anything-llm/pull/5779

New Contributors

  • @narutamaaurum made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5701
  • @Zhao73 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5737
  • @trick77 made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5723
  • @sanidhyasin made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5738
  • @dmitrymaranik made their first contribution in https://github.com/Mintplex-Labs/anything-llm/pull/5759

Full Changelog: https://github.com/Mintplex-Labs/anything-llm/compare/v1.13.0...v1.14.0

Breaking Changes

  • Model provider tool calling defaults changed to opt‑out (all providers now call tools unless explicitly opted out).
  • Default chat thread is killed when a new thread is created in workspaces without existing chats on the default thread.
View diff on GitHub

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

Share on X Share on Bluesky

Track anything-llm

Get notified when new releases ship.

Sign up free

About anything-llm

The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.

All releases →

Related context

Earlier breaking changes

  • v1.13.0 Breaks by renaming auto mode to agent mode.

Beta — feedback welcome: [email protected]