Skip to content

Release history

Khoj releases

Your AI second brain. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI.

All releases

16 shown

2.0.0-beta.28 Bug fix

Fixed web app access for users with no chat model after disabling memories.

Full changelog

🛠️ Fix

  • Fix using web app after disabling memories for users who never set chat model by @majiayu000 in https://github.com/khoj-ai/khoj/pull/1296
  • Fix showing deprecation banner on Khoj cloud by @debanjum in fdd5fd8f7

Full Changelog: https://github.com/khoj-ai/khoj/compare/2.0.0-beta.27...2.0.0-beta.28

2.0.0-beta.27 Bug fix

Fixed Khoj web app page template compatibility with Starlette 1.0.0.

Full changelog

🛠️ Fix

  • Fix Khoj web app page templates to be compatible with Starlette 1.0.0 by @debanjum in a19e7acd5

Full Changelog: https://github.com/khoj-ai/khoj/compare/2.0.0-beta.26...2.0.0-beta.27

2.0.0-beta.26 Bug fix
Notable features
  • Next.js 15 upgrade for faster, more reliable web app experience
  • Banner notifying Khoj cloud users about upcoming deprecation
  • Disabled subscribing to Khoj cloud from web app settings
Full changelog

🧪 Improve

  • Faster, more reliable web app experience with Next.js 15 upgrade in a9749c718
  • Add Banner to notify Khoj cloud users about the upcoming cloud deprecation by @debanjum in f7bce4893
  • Disable subscribing to Khoj cloud from web app settings page by @sabaimran in b864cb1f3

🛠️ Fix

  • Fix memories not loading on the web app Settings page in 0b8cf5112
  • Fix research agent occasionally stopping earlier than it should by @jnMetaCode in #1271
  • Fix Khoj sometimes ignoring content it already fetched from web pages by @jnMetaCode in #1269
  • Fix PDF files failing to process in some cases in by @BillionClaw in #1292
  • Make loading ChatModel name more robust by @yang1002378395-cmyk in #1277
  • Fix memory leaks when reading org-mode files by @buley in #1284

New Contributors

  • @04cb made their first contribution in https://github.com/khoj-ai/khoj/pull/1265
  • @Olexandr88 made their first contribution in https://github.com/khoj-ai/khoj/pull/1263
  • @jnMetaCode made their first contribution in https://github.com/khoj-ai/khoj/pull/1271
  • @yang1002378395-cmyk made their first contribution in https://github.com/khoj-ai/khoj/pull/1277
  • @BillionClaw made their first contribution in https://github.com/khoj-ai/khoj/pull/1292
  • @buley made their first contribution in https://github.com/khoj-ai/khoj/pull/1284

Full Changelog: https://github.com/khoj-ai/khoj/compare/2.0.0-beta.25...2.0.0-beta.26

2.0.0-beta.25 Bug fix
Notable features
  • Give Khoj Long Term Memories
  • Improve Obsidian Batch Sync with progress and storage usage display
  • Show autocomplete suggestions for File Query Filters in Obsidian App
Full changelog

What's Changed

  • Give Khoj Long Term Memories by @sabaimran in https://github.com/khoj-ai/khoj/pull/1168
  • Improve Obsidian Batch Sync. Show Progress, Storage Used on Settings Page by @hjamet in https://github.com/khoj-ai/khoj/pull/1221
  • Show autocomplete suggestions for File Query Filters on Obsidian App by @samhoooo in https://github.com/khoj-ai/khoj/pull/1128
  • Add ability to copy references from Web App by @kowshik24 in https://github.com/khoj-ai/khoj/pull/1144
  • Fix AttributeError when Eleven Labs API key is not set by @majiayu000 in https://github.com/khoj-ai/khoj/pull/1238

New Contributors

  • @kowshik24 made their first contribution in https://github.com/khoj-ai/khoj/pull/1144
  • @majiayu000 made their first contribution in https://github.com/khoj-ai/khoj/pull/1238

Full Changelog: https://github.com/khoj-ai/khoj/compare/2.0.0-beta.24...2.0.0-beta.25

2.0.0-beta.24 Bug fix
Security fixes
  • Prevented AI from interacting with user files in the code sandbox
Notable features
  • Render mermaid diagrams wrapped in markdown codeblocks on web app
Full changelog

🧪 Improve

  • Render mermaid diagram wrapped in markdown codeblocks on web app

🛠️ Fix

  • Fix subscriptions failures
  • Fix AI interacting with user files in code sandbox

Full Changelog: https://github.com/khoj-ai/khoj/compare/2.0.0-beta.23...2.0.0-beta.24

1.42.10 Bug fix

Fixed Khoj server setup when auto‑loading Ollama chat models on first run.

Full changelog

🛠️ Fix

  • Fix Khoj server setup with auto loaded Ollama chat models on first run by @debanjum in 8a50b5be0

Full Changelog: https://github.com/khoj-ai/khoj/compare/1.42.9...1.42.10

1.42.9 Maintenance

Minor fixes and improvements.

Full changelog

This is a maintenance release for the 1.x series.

🧪 Improve

  • Retry calls to Gemini API on on Stream Read Error in 0d4c40581
  • Bump free tier upload limits to 50Mb in 307e40c37

Full Changelog: https://github.com/khoj-ai/khoj/compare/1.42.8...1.42.9

1.42.8 New feature
Notable features
  • Friendly name display for available AI models on clients
  • Atomic sync of large knowledge bases with agents
Full changelog

🧪 Improve

  • Sync large knowledge bases with agents atomically in 9774bb012
  • Show friendly name for available ai models on clients in a8c47a70f

Full Changelog: https://github.com/khoj-ai/khoj/compare/1.42.7...1.42.8

1.42.7 New feature
Notable features
  • Support for new Deepseek R1 model (0528)
  • Ease of bulk selecting files to add/remove in agent knowledge base
Full changelog

🧪 Improve

  • Improve support for new Deepseek R1 model (0528) in 29e5d7ef0
  • Ease bulk (de-)selecting of files to add/remove to agent knowledge base in 1566e3c74
  • Improve image generation success in ca9109455, 4448ab665

🛠️ Fix

  • Fix semantic search to improve quality of document retrieval in 170a8036f.
  • Allow setting embedded postgres db directory via env var by @petergaultney in https://github.com/khoj-ai/khoj/pull/1202

New Contributors

  • @petergaultney made their first contribution in https://github.com/khoj-ai/khoj/pull/1202

Full Changelog: https://github.com/khoj-ai/khoj/compare/1.42.6...1.42.7

1.42.6 Maintenance

Routine maintenance release for Khoj.

Changelog

Full Changelog: https://github.com/khoj-ai/khoj/compare/1.42.5...1.42.6

1.42.5 Bug fix

Fixed rendering of deduplicated Gemini reasoning model thoughts.

Full changelog

🛠️ Fix

  • Save online references used by Khoj in 4946ea166
  • Render deduplicated thoughts of Gemini reasoning models in eaae1cf74
  • Use lower max output tokens for non reasoning Gemini models in 65644f78b
  • (Try) Get response from Openai o3 models in 71763684a
    Issue could not be reproduced locally, just appears on Khoj cloud currently. So unclear if fix will work and why the issue appears.

Full Changelog: https://github.com/khoj-ai/khoj/compare/1.42.4...1.42.5

1.42.4 Bug fix
Notable features
  • Chat with OpenAI o3 and o3-pro models
Full changelog

🎁 New

  • Chat with openai o3, o3-pro models in 753972997

🛠️ Fix

  • Display each agent's chat model (not the default chat model) on Agent page of web app in 5110a0608

Full Changelog: https://github.com/khoj-ai/khoj/compare/1.42.3...1.42.4

1.42.3 Bug fix
Notable features
  • Shared agent chat capability via [shared agents](https://blog.khoj.dev/posts/create-agents-on-khoj/)
  • Continuation of interrupted research sessions
Full changelog

This is a maintenance release to fix existing capabilities and regressions.

🛠️ Fix

  • Store code results on server and render them on web app in 64886cd0d
  • Let others chat with your shared agents in bd928b9f3
  • Continue interrupted research in b1a6e53d7
  • Using LLMs served via DeepInfra for Research mode in 313f648bd
  • Using Qwen3 models served over OpenAI compatible APIs in 9e73309d0

Full Changelog: https://github.com/khoj-ai/khoj/compare/1.42.2...1.42.3

1.42.2 Maintenance
⚠ Upgrade required
  • Deprecate unused slash commands: /summarize, /help, and /automations
  • Gunicorn worker timeouts are now configurable for production tuning
Notable features
  • Add retry last message button in web app
Full changelog

This is a maintenance release to simplify code and improve service stability.

🧪 Improve

  • Add button to retry last message via web app
  • Deprecate unused summarize, help and automations slash commands

🛠️ Fix

  • Reduce response failures by bumping up Gunicorn worker timeouts. Made the timeouts configurable to tune in production.

Full Changelog: https://github.com/khoj-ai/khoj/compare/1.42.1...1.42.2

1.42.1 Bug fix

Fixed saving conversations and files with strange characters or missing fields.

Full changelog

This release is intended to improve service stability.

🛠️ Fix

  • Improve automation completion. Delete broken automations in d45d9d4cf
  • Make saving conversations and files more robust to strange characters and missing fields in 4892e7332, 27534f653
  • Make Claude follow specified response schema in 65d9ad6cb

Full Changelog: https://github.com/khoj-ai/khoj/compare/1.42.0...1.42.1

1.42.0 New feature
Notable features
  • Experimental feature to give Khoj its own computer for browsing, file editing and terminal access (30+ minute research tasks).
  • Slash commands, agent switching, chat model switching added to the Khoj Obsidian plugin.
  • Ability to send suggestions while Khoj is researching; it will incorporate them automatically.
Full changelog

🎁 New

  • ✍🏽 Edit and discuss your notes with Khoj from Obsidian by @hjamet in https://github.com/khoj-ai/khoj/pull/1109
  • 🖥️ [Experimental] Enable Khoj to Operate Computer to complete more substantial tasks by @debanjum in https://github.com/khoj-ai/khoj/pull/1174, https://github.com/khoj-ai/khoj/pull/1190
    Self hosted users can give Khoj its own computer. Khoj can use it accomplish tasks that require visual browsing, file editing and terminal access in a transparent, controlled manner. Operator with research mode can work for 30+ minutes now to accomplish more substantial tasks like feature development, travel planning, shopping etc. See Operator Readme for setup details

🧪 Improve

  • Use Slash Commands, Switch Agents and Switch Chat Models in the Khoj Obsidian plugin by @hjamet in https://github.com/khoj-ai/khoj/pull/1109
  • Guide Khoj's research by sending messages while its doing research. It will automatically incorporate your suggestions
  • Show inner thoughts of reasoning models like Qwen3, Grok3, Gemini 2.5 in https://github.com/khoj-ai/khoj/pull/1172
  • Improve Research Mode Context Management in https://github.com/khoj-ai/khoj/pull/1179

🛠️ Fix

  • Improve chat response completions by fixing retry logic, reasoning tokens allowed in 4f3fdaf19, fd591c6e6, 31dcc44c2
  • Fix to cancel processing chat query on server when client disconnects

New Contributors

  • @PrinceSajjadHussain made their first contribution in https://github.com/khoj-ai/khoj/pull/1170

Full Changelog: https://github.com/khoj-ai/khoj/compare/1.41.0...1.42.0

Beta — feedback welcome: [email protected]