v4.0.0

[mudler]

---

🎉 LocalAI 4.0.0 Release! 🚀

LocalAI 4.0.0 is out!

This major release transforms LocalAI into a complete AI orchestration platform. We’ve embedded agentic and hybrid search capabilities directly into the core, completely overhauled the user interface with React for a modern experience, and are thrilled to introduce Agenthub ( link ) a brand new community hub to easily share and import agents. Alongside these massive updates, we've introduced powerful new features like Canvas mode for code artifacts, MCP apps and full MCP client-side support.

Feature	Summary
Agentic Orchestration & Agenthub	Native agent management with memory, skills, and the new Agenthub for community sharing.
Revamped React UI	Complete frontend rewrite for lightning-fast performance and modern UX.
Canvas Mode	Preview code blocks and artifacts side-by-side in the chat interface.
MCP Client-Side	Full Model Context Protocol support, MCP Apps, and tool streaming in chat.
WebRTC Realtime	WebRTC support for low-latency realtime audio conversations.
New Backends	Added experimental MLX Distributed, fish-speech, ace-step.cpp, and faster-qwen3-tts.
Infrastructure	Podman documentation, shell completion, and persistent data path separation.

---

🚀 Key Features

🤖 Native Agentic Orchestration & Agenthub

LocalAI now includes agentic capabilities embedded directly in the core. You can manage, import, start, and stop agents via the new UI.

• 🌐 Agenthub: We are launching Agenthub! This is a centralized community space to share common agents and import them effortlessly into your LocalAI instance.
• Agent Management: Full lifecycle management via the React UI. Create Agents, connect them to Slack, configure MCP servers and skills.
• Skills Management: Centralized skill database for AI agents.
• Memory: Agents can utilize memory with Hybrid search (PostgreSQL) or embedded in-memory storage (Chromem).
• Observability: New "Events" column in the Agents list to track observables and status.
• 📚 Documentation: Dive into the new capabilities in our official Agents documentation.

agents.mp4

🎨 Revamped UI & Canvas Mode

The Web interface has been completely migrated to React, bringing a smoother experience and powerful new capabilities:

• Canvas Mode: Enable "canvas mode" in the chat to see code blocks and artifacts generated by the LLM in a dedicated preview bar on the right.
• System View: Tabbed navigation separating Models and Backends for better organization.
• Model Size Warnings: Visual warnings when model storage exceeds system RAM to prevent lockups.
• Traces: Improved trace display using accordions for better readability.

model-fit-canvas-mode.mp4

🔌 MCP Apps & Client-Side Support

We’ve expanded support for the Model Context Protocol (MCP):

• MCP Apps: Select which servers to enable for the chat directly from the UI.
• Tool Streaming: Tools from MCP servers are automatically injected into the standard chat interface.
• Client-Side Support: Full client-side integration for MCP tools and streaming.
• Disable Option: Add LOCALAI_DISABLE_MCP to completely disable MCP support for security.

🎵 New Backends, Audio & Video Enhancements

• MLX Distributed (Experimental): We've added an experimental backend for running distributed workloads using Apple's MLX framework! Check out the docs here.
• New Audio Backends: Introduced fish-speech, ace-step.cpp, and faster-qwen3-tts (CUDA-only).
• WeRTC Realtime: WebRTC support added to the Realtime API and Talk page for better low-latency audio handling.
• TTS Improvements: Added sample_rate support via post-processing and multi-voice support for Qwen TTS.
• Video Generation: Fixed model selection dropdown sync and added vllm-omni backend detection.

🛠️ Infrastructure & Developer Experience

• Data Separation: New --data-path CLI flag and LOCALAI_DATA_PATH env var to separate persistent data (agents, skills) from configuration.
• Shell Completion: Dynamic completion scripts for bash, zsh, and fish.
• Podman Support: Dedicated documentation for Podman installation and rootless configuration.
• Gallery & Models: Model storage size display with RAM warnings, and fallback URI resolution for backend installation failures.
• Deprecations: HuggingFace backend support removed, and AIO images dropped to focus on main images.

---

🐞 Fixes & Improvements

• Logging: Fixed watchdog spamming logs when no interval was configured; downgraded health check logs to debug.
• CUDA Detection: Improved GPU vendor checks to prevent false CUDA detection on CPU-only hosts with runtime libs.
• Compatibility: Renamed json_verbose to verbose_json for OpenAI spec compliance (fixes Nextcloud integration).
• Embedding: Fixed embedding dimension truncation to return full native dimensions.
• Permissions: Changed model install file permissions to 0644 to ensure server readability.
• Windows Docker: Added named volumes to Docker Compose files for Windows compatibility.
• Model Reload: Models now reload automatically after editing YAML config (e.g., context_size).
• Chat: Fixed issue where thinking/reasoning blocks were sent to the LLM.
• Audio: Fixed img2img pipeline in diffusers backend and Qwen TTS duplicate argument error.

Known issues

• The diffusers backend fails to build currently (due to CI limit exhaustion) and it's not currently part of this release (the previous version is still available). We are looking into it but, if you want to help and know someone at Github that could help supporting us with better ARM runners, please reach out!

---

❤️ Thank You

LocalAI is a true FOSS movement — built by contributors, powered by community.

If you believe in privacy-first AI:

• ✅ Star the repo
• 💬 Contribute code, docs, or feedback
• 📣 Share with others

Your support keeps this stack alive.

---

✅ Full Changelog

📋 Click to expand full changelog

What's Changed

Breaking Changes 🛠

• Remove HuggingFace backend support by @localai-bot in Remove HuggingFace backend support #8971
• chore: drop AIO images by @mudler in chore: drop AIO images #9004

Bug fixes 🐛

• fix(cli): Fix watchdog running constantly and spamming logs by @nanoandrew4 in fix(cli): Fix watchdog running constantly and spamming logs #8624
• fix(api): Downgrade health/readiness check to debug by @nanoandrew4 in fix(api): Downgrade health/readiness check to debug #8625
• fix: rename json_verbose to verbose_json by @lukasdotcom in fix: rename json_verbose to verbose_json #8627
• fix(chatterbox): add support for cuda13/aarch64 by @mudler in fix(chatterbox): add support for cuda13/aarch64 #8653
• fix: reload model after editing YAML config (issue Changing context_size in YAML Configuration Editor requires restarting #8647) by @localai-bot in fix: reload model after editing YAML config (issue #8647) #8652
• fix(chat): do not send thinking/reasoning messages to the LLM by @mudler in fix(chat): do not send thinking/reasoning messages to the LLM #8656
• fix: change file permissions from 0600 to 0644 in InstallModel by @localai-bot in fix: change file permissions from 0600 to 0644 in InstallModel #8657
• fix: Add named volumes for Windows Docker compatibility by @localai-bot in fix: Add named volumes for Windows Docker compatibility #8661
• fix(gallery): add fallback URI resolution for backend installation by @localai-bot in fix(gallery): add fallback URI resolution for backend installation #8663
• fix: whisper breaking on cuda-13 (use absolute path for CUDA directory detection) by @localai-bot in fix: whisper breaking on cuda-13 (use absolute path for CUDA directory detection) #8678
• fix(gallery): clean up partially downloaded backend on installation failure by @localai-bot in fix(gallery): clean up partially downloaded backend on installation failure #8679
• fix: properly sync model selection dropdown in video generation UI by @localai-bot in fix: properly sync model selection dropdown in video generation UI #8680
• fix: allow reranking models configured with known_usecases by @localai-bot in fix: allow reranking models configured with known_usecases #8681
• fix: return full embedding dimensions instead of truncating trailing zeros (Bug Report: Embedding dimension mismatch for Jina-v3 and others (Returning 1/4 of expected dimensions) #8721) by @localai-bot in fix: return full embedding dimensions instead of truncating trailing zeros (#8721) #8755
• fix: Add vllm-omni backend to video generation model detection (Video Generation - model not selectable #8659) by @localai-bot in fix: Add vllm-omni backend to video generation model detection (#8659) #8781
• fix(qwen-tts): duplicate instruct argument in voice design mode by @Weathercold in fix(qwen-tts): duplicate instruct argument in voice design mode #8842
• Fix image upload processing and img2img pipeline in diffusers backend by @attilagyorffy in Fix image upload processing and img2img pipeline in diffusers backend #8879
• fix: gate CUDA directory checks on GPU vendor to prevent false CUDA detection by @sozercan in fix: gate CUDA directory checks on GPU vendor to prevent false CUDA detection #8942
• fix(llama-cpp): Set enable_thinking in the correct place by @richiejp in fix(llama-cpp): Set enable_thinking in the correct place #8973

Exciting New Features 🎉

• feat(traces): Use accordian instead of pop-ups by @richiejp in feat(traces): Use accordian instead of pop-ups #8626
• chore: remove install.sh script and documentation references by @localai-bot in chore: remove install.sh script and documentation references #8643
• docs: add Podman installation documentation by @localai-bot in docs: add Podman installation documentation #8646
• Add sample_rate support to TTS API via post-processing resampling by @Copilot in Add sample_rate support to TTS API via post-processing resampling #8650
• feat(backends): add faster-qwen3-tts by @localai-bot in feat(backends): add faster-qwen3-tts #8664
• feat(models): add model storage size display and RAM warning by @localai-bot in feat(models): add model storage size display and RAM warning #8675
• feat(ui): add model size estimation by @mudler in feat(ui): add model size estimation #8684
• feat: Add Free RPC to backend.proto for VRAM cleanup by @localai-bot in feat: Add Free RPC to backend.proto for VRAM cleanup #8751
• feat(qwen-tts): Support using multiple voices by @nanoandrew4 in feat(qwen-tts): Support using multiple voices #8757
• feat(ui): move to React for frontend by @mudler in feat(ui): move to React for frontend #8772
• feat: add WebSocket mode support for the response api by @bittoby in feat: add WebSocket mode support for the response api #8676
• feat: Add LOCALAI_DISABLE_MCP environment variable to disable MCP support by @localai-bot in feat: Add LOCALAI_DISABLE_MCP environment variable to disable MCP support #8816
• feat: add agentic management by @mudler in feat: add agentic management #8820
• feat: Add shell completion support for bash, zsh, and fish by @localai-bot in feat: Add shell completion support for bash, zsh, and fish #8851
• feat(downloader): add HF_MIRROR environment variable support by @localai-bot in feat(downloader): add HF_MIRROR environment variable support #8847
• feat: add Events column to Agents list page by @localai-bot in feat: add Events column to Agents list page #8870
• feat: Add tabs to System view for Models and Backends by @localai-bot in feat: Add tabs to System view for Models and Backends #8885
• feat: Add --data-path CLI flag for persistent data separation by @localai-bot in feat: Add --data-path CLI flag for persistent data separation #8888
• feat(mlx-distributed): add new (experimental) MLX-distributed backend by @mudler in feat(mlx-distributed): add new (experimental) MLX-distributed backend #8801
• chore(size): display size of HF models and allow to specify it from the gallery by @mudler in chore(size): display size of HF models and allow to specify it from the gallery #8907
• feat(ui): add canvas mode, support history in agent chat by @mudler in feat(ui): add canvas mode, support history in agent chat #8927
• feat(ui): MCP Apps, mcp streaming and client-side support by @mudler in feat(ui): MCP Apps, mcp streaming and client-side support #8947
• feat: add fish-speech backend by @mudler in feat: add fish-speech backend #8962
• feat(backends): add ace-step.cpp by @mudler in feat(backends): add ace-step.cpp #8965
• feat(realtime): WebRTC support by @richiejp in feat(realtime): WebRTC support #8790

🧠 Models

• chore(model gallery): 🤖 add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent #8693
• chore(model gallery): 🤖 add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent #8694
• chore(model gallery): 🤖 add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent #8695
• chore(model gallery): 🤖 add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent #8696
• chore(model gallery): 🤖 add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent #8698

📖 Documentation and examples

• fix(realtime): Add functions to conversation history by @richiejp in fix(realtime): Add functions to conversation history #8616
• docs: update diffusers multi-GPU documentation to mention tensor_parallel_size configuration by @localai-bot in docs: update diffusers multi-GPU documentation to mention tensor_parallel_size configuration #8621
• docs: Update Home Assistant links in README.md by @loryanstrant in docs: Update Home Assistant links in README.md #8688

👒 Dependencies

• chore(deps): bump fyne.io/fyne/v2 from 2.7.2 to 2.7.3 by @dependabot[bot] in chore(deps): bump fyne.io/fyne/v2 from 2.7.2 to 2.7.3 #8629
• chore(deps): bump github.com/anthropics/anthropic-sdk-go from 1.22.0 to 1.26.0 by @dependabot[bot] in chore(deps): bump github.com/anthropics/anthropic-sdk-go from 1.22.0 to 1.26.0 #8630
• chore(deps): bump github.com/gpustack/gguf-parser-go from 0.23.1 to 0.24.0 by @dependabot[bot] in chore(deps): bump github.com/gpustack/gguf-parser-go from 0.23.1 to 0.24.0 #8631
• chore(deps): bump actions/stale from 10.1.1 to 10.2.0 by @dependabot[bot] in chore(deps): bump actions/stale from 10.1.1 to 10.2.0 #8633
• chore(deps): bump goreleaser/goreleaser-action from 6 to 7 by @dependabot[bot] in chore(deps): bump goreleaser/goreleaser-action from 6 to 7 #8634
• chore(deps): bump github.com/mudler/cogito from 0.9.1-0.20260217143801-bb7f986ed2c7 to 0.9.1 by @dependabot[bot] in chore(deps): bump github.com/mudler/cogito from 0.9.1-0.20260217143801-bb7f986ed2c7 to 0.9.1 #8632
• chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/coqui by @dependabot[bot] in chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/coqui #8642
• chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/common/template by @dependabot[bot] in chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/common/template #8641
• chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/transformers by @dependabot[bot] in chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/transformers #8640
• chore(deps): bump sentence-transformers from 5.2.2 to 5.2.3 in /backend/python/transformers by @dependabot[bot] in chore(deps): bump sentence-transformers from 5.2.2 to 5.2.3 in /backend/python/transformers #8638
• chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/rerankers by @dependabot[bot] in chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/rerankers #8636
• chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/vllm by @dependabot[bot] in chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/vllm #8635
• chore(deps): bump actions/download-artifact from 7 to 8 by @dependabot[bot] in chore(deps): bump actions/download-artifact from 7 to 8 #8729
• chore(deps): bump actions/upload-artifact from 6 to 7 by @dependabot[bot] in chore(deps): bump actions/upload-artifact from 6 to 7 #8730
• chore(deps): bump github.com/openai/openai-go/v3 from 3.19.0 to 3.24.0 by @dependabot[bot] in chore(deps): bump github.com/openai/openai-go/v3 from 3.19.0 to 3.24.0 #8732
• chore(deps): bump github.com/modelcontextprotocol/go-sdk from 1.3.0 to 1.4.0 by @dependabot[bot] in chore(deps): bump github.com/modelcontextprotocol/go-sdk from 1.3.0 to 1.4.0 #8733
• chore(deps): bump go.opentelemetry.io/otel from 1.40.0 to 1.41.0 by @dependabot[bot] in chore(deps): bump go.opentelemetry.io/otel from 1.40.0 to 1.41.0 #8734
• chore(deps): bump go.opentelemetry.io/otel/metric from 1.40.0 to 1.41.0 by @dependabot[bot] in chore(deps): bump go.opentelemetry.io/otel/metric from 1.40.0 to 1.41.0 #8735
• chore(deps): bump github.com/google/go-containerregistry from 0.20.7 to 0.21.1 by @dependabot[bot] in chore(deps): bump github.com/google/go-containerregistry from 0.20.7 to 0.21.1 #8736
• chore(deps): bump go.opentelemetry.io/otel/sdk/metric from 1.40.0 to 1.42.0 by @dependabot[bot] in chore(deps): bump go.opentelemetry.io/otel/sdk/metric from 1.40.0 to 1.42.0 #8915
• chore(deps): bump github.com/openai/openai-go/v3 from 3.24.0 to 3.26.0 by @dependabot[bot] in chore(deps): bump github.com/openai/openai-go/v3 from 3.24.0 to 3.26.0 #8916
• chore(deps): bump go.yaml.in/yaml/v2 from 2.4.3 to 2.4.4 by @dependabot[bot] in chore(deps): bump go.yaml.in/yaml/v2 from 2.4.3 to 2.4.4 #8913
• chore(deps): bump github.com/labstack/echo/v4 from 4.15.0 to 4.15.1 by @dependabot[bot] in chore(deps): bump github.com/labstack/echo/v4 from 4.15.0 to 4.15.1 #8914
• chore(deps): bump docker/metadata-action from 5 to 6 by @dependabot[bot] in chore(deps): bump docker/metadata-action from 5 to 6 #8917
• chore(deps): bump actions/setup-node from 4 to 6 by @dependabot[bot] in chore(deps): bump actions/setup-node from 4 to 6 #8920
• chore(deps): bump docker/build-push-action from 6 to 7 by @dependabot[bot] in chore(deps): bump docker/build-push-action from 6 to 7 #8919
• chore(deps): bump docker/login-action from 3 to 4 by @dependabot[bot] in chore(deps): bump docker/login-action from 3 to 4 #8918
• chore(deps): bump node from 22-slim to 25-slim by @dependabot[bot] in chore(deps): bump node from 22-slim to 25-slim #8922

Other Changes

• docs: ⬆️ update docs version mudler/LocalAI by @localai-bot in docs: ⬆️ update docs version mudler/LocalAI #8618
• chore: ⬆️ Update ggml-org/llama.cpp to f75c4e8bf52ea480ece07fd3d9a292f1d7f04bc5 by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to f75c4e8bf52ea480ece07fd3d9a292f1d7f04bc5 #8619
• chore: ⬆️ Update ggml-org/llama.cpp to 2b6dfe824de8600c061ef91ce5cc5c307f97112c by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to 2b6dfe824de8600c061ef91ce5cc5c307f97112c #8622
• chore: ⬆️ Update ggml-org/llama.cpp to b68a83e641b3ebe6465970b34e99f3f0e0a0b21a by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to b68a83e641b3ebe6465970b34e99f3f0e0a0b21a #8628
• fix(webui): use different icon for System nav item by @localai-bot in fix(webui): use different icon for System nav item #8648
• chore: ⬆️ Update ggml-org/llama.cpp to 418dea39cea85d3496c8b04a118c3b17f3940ad8 by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to 418dea39cea85d3496c8b04a118c3b17f3940ad8 #8649
• feat(swagger): update swagger by @localai-bot in feat(swagger): update swagger #8654
• chore: ⬆️ Update ggml-org/llama.cpp to 3769fe6eb70b0a0fbb30b80917f1caae68c902f7 by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to 3769fe6eb70b0a0fbb30b80917f1caae68c902f7 #8655
• chore: ⬆️ Update ggml-org/llama.cpp to 723c71064da0908c19683f8c344715fbf6d986fd by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to 723c71064da0908c19683f8c344715fbf6d986fd #8660
• fix(qwen3.5): add qwen3.5 preset and mimick llama.cpp's PEG by @mudler in fix(qwen3.5): add qwen3.5 preset and mimick llama.cpp's PEG #8668
• chore: ⬆️ Update ggml-org/whisper.cpp to 9453b4b9be9b73adfc35051083f37cefa039acee by @localai-bot in chore: ⬆️ Update ggml-org/whisper.cpp to 9453b4b9be9b73adfc35051083f37cefa039acee #8671
• chore(deps): bump llama.cpp to 'ecbcb7ea9d3303097519723b264a8b5f1e977028' by @mudler in chore(deps): bump llama.cpp to 'ecbcb7ea9d3303097519723b264a8b5f1e977028' #8672
• docs: add CDI driver config for NVIDIA GPU in containers (fix Release today (just released) breaking when launching on CUDA hardware #8108) by @localai-bot in docs: add CDI driver config for NVIDIA GPU in containers (fix #8108) #8677
• docs: add TLS reverse proxy configuration guide by @localai-bot in docs: add TLS reverse proxy configuration guide #8673
• chore: ⬆️ Update ggml-org/llama.cpp to 05728db18eea59de81ee3a7699739daaf015206b by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to 05728db18eea59de81ee3a7699739daaf015206b #8683
• fix: simplify CI steps, fix gallery agent by @mudler in fix: simplify CI steps, fix gallery agent #8685
• fix: retry when LLM returns empty messages by @mudler in fix: retry when LLM returns empty messages #8704
• feat(swagger): update swagger by @localai-bot in feat(swagger): update swagger #8706
• feat: Add debug logging for pocket-tts voice issue pocket-tts fails to find custom voice #8244 by @localai-bot in feat: Add debug logging for pocket-tts voice issue #8244 #8715
• fix(ci): correct transformer backend path typo by @localai-bot in fix(ci): correct transformer backend path typo #8712
• chore: ⬆️ Update ggml-org/llama.cpp to 319146247e643695f94a558e8ae686277dd4f8da by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to 319146247e643695f94a558e8ae686277dd4f8da #8707
• fix: Implement responsive line wrapping for model names (Responsively line wrap loaded models on the home page of web UI #8209) by @localai-bot in fix: Implement responsive line wrapping for model names (#8209) #8720
• fix(qwen-tts): ensure all requirements files end with newline by @localai-bot in fix(qwen-tts): ensure all requirements files end with newline #8724
• chore(model-gallery): ⬆️ update checksum by @localai-bot in chore(model-gallery): ⬆️ update checksum #8728
• chore: ⬆️ Update ggml-org/llama.cpp to 4d828bd1ab52773ba9570cc008cf209eb4a8b2f5 by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to 4d828bd1ab52773ba9570cc008cf209eb4a8b2f5 #8727
• chore(model gallery): 🤖 add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent #8743
• chore: ⬆️ Update ggml-org/llama.cpp to ecd99d6a9acbc436bad085783bcd5d0b9ae9e9e9 by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to ecd99d6a9acbc436bad085783bcd5d0b9ae9e9e9 #8762
• chore(model gallery): 🤖 add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent #8770
• chore(model-gallery): ⬆️ update checksum by @localai-bot in chore(model-gallery): ⬆️ update checksum #8778
• chore: ⬆️ Update ggml-org/llama.cpp to 24d2ee052795063afffc9732465ca1b1c65f4a28 by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to 24d2ee052795063afffc9732465ca1b1c65f4a28 #8777
• docs: add autonomous development team section to README by @localai-bot in docs: add autonomous development team section to README #8780
• feat: Rename 'Whisper' model type to 'STT' in UI by @localai-bot in feat: Rename 'Whisper' model type to 'STT' in UI #8785
• chore: ⬆️ Update ggml-org/whisper.cpp to 30c5194c9691e4e9a98b3dea9f19727397d3f46e by @localai-bot in chore: ⬆️ Update ggml-org/whisper.cpp to 30c5194c9691e4e9a98b3dea9f19727397d3f46e #8796
• chore: ⬆️ Update ggml-org/llama.cpp to a0ed91a442ea6b013bd42ebc3887a81792eaefa1 by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to a0ed91a442ea6b013bd42ebc3887a81792eaefa1 #8797
• feat: pass-by metadata to predict options by @mudler in feat: pass-by metadata to predict options #8795
• fix: Add timeout-based wait for model deletion completion by @localai-bot in fix: Add timeout-based wait for model deletion completion #8756
• chore: Add LTX-2.3 model to gallery by @localai-bot in chore: Add LTX-2.3 model to gallery #8805
• chore: ⬆️ Update ggml-org/llama.cpp to 566059a26b0ce8faec4ea053605719d399c64cc5 by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to 566059a26b0ce8faec4ea053605719d399c64cc5 #8822
• chore(model gallery): 🤖 add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent #8828
• chore(model gallery): 🤖 add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent #8830
• feat: update descriptions for first 9 models in gallery/index.yaml by @localai-bot in feat: update descriptions for first 9 models in gallery/index.yaml #8831
• chore: ⬆️ Update ggml-org/llama.cpp to c5a778891ba0ddbd4cbb507c823f970595b1adc2 by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to c5a778891ba0ddbd4cbb507c823f970595b1adc2 #8837
• chore(docs): Populate coding guidelines in CONTRIBUTING.md by @localai-bot in chore(docs): Populate coding guidelines in CONTRIBUTING.md #8840
• fix: Remove debug print statement from soundgeneration.go (C2) by @localai-bot in fix: Remove debug print statement from soundgeneration.go (C2) #8843
• docs: Add comprehensive API error reference documentation by @localai-bot in docs: Add comprehensive API error reference documentation #8848
• docs: add Table of Contents to README.md by @localai-bot in docs: add Table of Contents to README.md #8846
• chore: ⬆️ Update leejet/stable-diffusion.cpp to c8fb3d245858d495be1f140efdcfaa0d49de41e5 by @localai-bot in chore: ⬆️ Update leejet/stable-diffusion.cpp to c8fb3d245858d495be1f140efdcfaa0d49de41e5 #8841
• docs: clarify SECURITY.md version support table with specific ranges and EOL dates by @localai-bot in docs: clarify SECURITY.md version support table with specific ranges and EOL dates #8861
• fix: Correct Talk Interface screenshot reference in README.md (H6) by @localai-bot in fix: Correct Talk Interface screenshot reference in README.md (H6) #8857
• feat: Add documentation for undocumented API endpoints by @localai-bot in feat: Add documentation for undocumented API endpoints #8852
• docs: add comprehensive development setup instructions to CONTRIBUTING.md (H7) by @localai-bot in docs: add comprehensive development setup instructions to CONTRIBUTING.md (H7) #8860
• feat(cli): add configurable backend image fallback tags via CLI options by @localai-bot in feat(cli): add configurable backend image fallback tags via CLI options #8817
• feat: add MIT license badge to README.md by @localai-bot in feat: add MIT license badge to README.md #8871
• feat: Create comprehensive troubleshooting guide (M1 task) by @localai-bot in feat: Create comprehensive troubleshooting guide (M1 task) #8856
• docs: expand GPU acceleration guide with L4T, multi-GPU, monitoring, and troubleshooting by @localai-bot in docs: expand GPU acceleration guide with L4T, multi-GPU, monitoring, and troubleshooting #8858
• feat: Add documentation URLs to CLI help text by @localai-bot in feat: Add documentation URLs to CLI help text #8874
• feat(functions): add peg-based parsing and allow backends to return tool calls directly by @mudler in feat(functions): add peg-based parsing and allow backends to return tool calls directly #8838
• chore: Update README.md screenshot references and alt text by @localai-bot in chore: Update README.md screenshot references and alt text #8862
• chore: ⬆️ Update ggml-org/llama.cpp to 35bee031e17ed2b2e8e7278b284a6c8cd120d9f8 by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to 35bee031e17ed2b2e8e7278b284a6c8cd120d9f8 #8872
• docs: Update model compatibility documentation with missing backends by @localai-bot in docs: Update model compatibility documentation with missing backends #8889
• docs: make examples repository link more prominent by @localai-bot in docs: make examples repository link more prominent #8895
• chore(model gallery): 🤖 add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent #8901
• chore(model gallery): 🤖 add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent #8902
• chore(model gallery): 🤖 add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent #8904
• feat: Redesign explorer and models pages with react-ui theme by @localai-bot in feat: Redesign explorer and models pages with react-ui theme #8903
• fix(ui): minor visual enhancements by @mudler in fix(ui): minor visual enhancements #8909
• feat(swagger): update swagger by @localai-bot in feat(swagger): update swagger #8923
• feat: Standardize CLI flag naming to kebab-case (M12) by @localai-bot in feat: Standardize CLI flag naming to kebab-case (M12) #8912
• chore: ⬆️ Update leejet/stable-diffusion.cpp to d6dd6d7b555c233bb9bc9f20b4751eb8c9269743 by @localai-bot in chore: ⬆️ Update leejet/stable-diffusion.cpp to d6dd6d7b555c233bb9bc9f20b4751eb8c9269743 #8925
• chore: ⬆️ Update ggml-org/llama.cpp to 23fbfcb1ad6c6f76b230e8895254de785000be46 by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to 23fbfcb1ad6c6f76b230e8895254de785000be46 #8921
• fix: correct grammar in CONTRIBUTING.md documentation section by @localai-bot in fix: correct grammar in CONTRIBUTING.md documentation section #8932
• feat: Expand section index pages with comprehensive navigation (M7) by @localai-bot in feat: Expand section index pages with comprehensive navigation (M7) #8929
• chore(model gallery): 🤖 add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent #8939
• chore(model-gallery): ⬆️ update checksum by @localai-bot in chore(model-gallery): ⬆️ update checksum #8945
• chore: ⬆️ Update ggml-org/llama.cpp to 10e5b148b061569aaee8ae0cf72a703129df0eab by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to 10e5b148b061569aaee8ae0cf72a703129df0eab #8946
• fix: include model name in mmproj file path to prevent model isolation (Models are not isolated from each other #8937) by @localai-bot in fix: include model name in mmproj file path to prevent model isolation (#8937) #8940
• feat(swagger): update swagger by @localai-bot in feat(swagger): update swagger #8961
• docs: Document GPU auto-fit mode limitations and trade-offs (closes auto-fit vs unloading with threshold #8562) by @localai-bot in docs: Document GPU auto-fit mode limitations and trade-offs (closes #8562) #8954
• chore(ui): improve errors and reporting during model installation by @mudler in chore(ui): improve errors and reporting during model installation #8979
• chore(model gallery): 🤖 add 1 new models via gallery agent by @localai-bot in chore(model gallery): 🤖 add 1 new models via gallery agent #8980
• fix(collections): start agent pool after http server by @mudler in fix(collections): start agent pool after http server #8981
• chore(model-gallery): ⬆️ update checksum by @localai-bot in chore(model-gallery): ⬆️ update checksum #8985
• chore: ⬆️ Update ggml-org/llama.cpp to 57819b8d4b39d893408e51520dff3d47d1ebb757 by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to 57819b8d4b39d893408e51520dff3d47d1ebb757 #8983
• chore: ⬆️ Update ace-step/acestep.cpp to 5aa065445541094cba934299cd498bbb9fa5c434 by @localai-bot in chore: ⬆️ Update ace-step/acestep.cpp to 5aa065445541094cba934299cd498bbb9fa5c434 #8984
• fix(ui): Move routes to /app to avoid conflict with API endpoints by @richiejp in fix(ui): Move routes to /app to avoid conflict with API endpoints #8978
• fix(conf): Don't overwrite env provided galleries with runtime conf by @richiejp in fix(conf): Don't overwrite env provided galleries with runtime conf #8994
• fix(flux.2-klein-9b): Use Qwen3-8b to avoid GGML assertion failure on tensor mismatch by @richiejp in fix(flux.2-klein-9b): Use Qwen3-8b to avoid GGML assertion failure on tensor mismatch #8995
• fix(acestep-cpp): resolve relative model paths in options by @localai-bot in fix(acestep-cpp): resolve relative model paths in options #8993
• chore: ⬆️ Update ggml-org/llama.cpp to e30f1fdf74ea9238ff562901aa974c75aab6619b by @localai-bot in chore: ⬆️ Update ggml-org/llama.cpp to e30f1fdf74ea9238ff562901aa974c75aab6619b #8997

New Contributors

• @loryanstrant made their first contribution in docs: Update Home Assistant links in README.md #8688
• @bittoby made their first contribution in feat: add WebSocket mode support for the response api #8676
• @Weathercold made their first contribution in fix(qwen-tts): duplicate instruct argument in voice design mode #8842
• @attilagyorffy made their first contribution in Fix image upload processing and img2img pipeline in diffusers backend #8879

Full Changelog: v3.12.1...v4.0.0

---

This discussion was created from the release v4.0.0.