v4.0.0

<!-- Release notes generated using configuration in .github/release.yml at master -->

---
# 🎉 LocalAI 4.0.0 Release! 🚀

<h1 align="center">
  <br>
  <img height="300" src="https://raw.githubusercontent.com/mudler/LocalAI/refs/heads/master/core/http/static/logo.png">
  <br>
  <br>
</h1>

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](https://agenthub.localai.io) ) 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](https://agenthub.localai.io/)**! 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](https://localai.io/features/agents).

https://github.com/user-attachments/assets/6270b331-e21d-4087-a540-6290006b381a

### 🎨 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.

https://github.com/user-attachments/assets/08cbb692-57da-48f7-963d-2e7b43883c18

### 🔌 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.

<img width="1920" height="912" alt="mcp apps" src="https://github.com/user-attachments/assets/ea50d29f-4a3b-412f-8c14-b8c3fb417278" />

### 🎵 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](https://localai.io/features/mlx-distributed/index.html).
- **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

<details>
<summary>📋 Click to expand full changelog</summary>


## What's Changed
### Breaking Changes 🛠
* Remove HuggingFace backend support by @localai-bot in https://github.com/mudler/LocalAI/pull/8971
* chore: drop AIO images by @mudler in https://github.com/mudler/LocalAI/pull/9004
### Bug fixes :bug:
* fix(cli): Fix watchdog running constantly and spamming logs by @nanoandrew4 in https://github.com/mudler/LocalAI/pull/8624
* fix(api): Downgrade health/readiness check to debug by @nanoandrew4 in https://github.com/mudler/LocalAI/pull/8625
* fix: rename json_verbose to verbose_json by @lukasdotcom in https://github.com/mudler/LocalAI/pull/8627
* fix(chatterbox): add support for cuda13/aarch64 by @mudler in https://github.com/mudler/LocalAI/pull/8653
* fix: reload model after editing YAML config (issue #8647) by @localai-bot in https://github.com/mudler/LocalAI/pull/8652
* fix(chat): do not send thinking/reasoning messages to the LLM by @mudler in https://github.com/mudler/LocalAI/pull/8656
* fix: change file permissions from 0600 to 0644 in InstallModel by @localai-bot in https://github.com/mudler/LocalAI/pull/8657
* fix: Add named volumes for Windows Docker compatibility by @localai-bot in https://github.com/mudler/LocalAI/pull/8661
* fix(gallery): add fallback URI resolution for backend installation by @localai-bot in https://github.com/mudler/LocalAI/pull/8663
* fix: whisper breaking on cuda-13 (use absolute path for CUDA directory detection) by @localai-bot in https://github.com/mudler/LocalAI/pull/8678
* fix(gallery): clean up partially downloaded backend on installation failure by @localai-bot in https://github.com/mudler/LocalAI/pull/8679
* fix: properly sync model selection dropdown in video generation UI by @localai-bot in https://github.com/mudler/LocalAI/pull/8680
* fix: allow reranking models configured with known_usecases by @localai-bot in https://github.com/mudler/LocalAI/pull/8681
* fix: return full embedding dimensions instead of truncating trailing zeros (#8721) by @localai-bot in https://github.com/mudler/LocalAI/pull/8755
* fix: Add vllm-omni backend to video generation model detection (#8659) by @localai-bot in https://github.com/mudler/LocalAI/pull/8781
* fix(qwen-tts): duplicate instruct argument in voice design mode by @Weathercold in https://github.com/mudler/LocalAI/pull/8842
* Fix image upload processing and img2img pipeline in diffusers backend by @attilagyorffy in https://github.com/mudler/LocalAI/pull/8879
* fix: gate CUDA directory checks on GPU vendor to prevent false CUDA detection by @sozercan in https://github.com/mudler/LocalAI/pull/8942
* fix(llama-cpp): Set enable_thinking in the correct place by @richiejp in https://github.com/mudler/LocalAI/pull/8973
### Exciting New Features 🎉
* feat(traces): Use accordian instead of pop-ups by @richiejp in https://github.com/mudler/LocalAI/pull/8626
* chore: remove install.sh script and documentation references by @localai-bot in https://github.com/mudler/LocalAI/pull/8643
* docs: add Podman installation documentation by @localai-bot in https://github.com/mudler/LocalAI/pull/8646
* Add `sample_rate` support to TTS API via post-processing resampling by @Copilot in https://github.com/mudler/LocalAI/pull/8650
* feat(backends): add faster-qwen3-tts by @localai-bot in https://github.com/mudler/LocalAI/pull/8664
* feat(models): add model storage size display and RAM warning by @localai-bot in https://github.com/mudler/LocalAI/pull/8675
* feat(ui): add model size estimation by @mudler in https://github.com/mudler/LocalAI/pull/8684
* feat: Add Free RPC to backend.proto for VRAM cleanup by @localai-bot in https://github.com/mudler/LocalAI/pull/8751
* feat(qwen-tts): Support using multiple voices by @nanoandrew4 in https://github.com/mudler/LocalAI/pull/8757
* feat(ui): move to React for frontend by @mudler in https://github.com/mudler/LocalAI/pull/8772
* feat: add WebSocket mode support for the response api by @bittoby in https://github.com/mudler/LocalAI/pull/8676
* feat: Add LOCALAI_DISABLE_MCP environment variable to disable MCP support by @localai-bot in https://github.com/mudler/LocalAI/pull/8816
* feat: add agentic management by @mudler in https://github.com/mudler/LocalAI/pull/8820
* feat: Add shell completion support for bash, zsh, and fish by @localai-bot in https://github.com/mudler/LocalAI/pull/8851
* feat(downloader): add HF_MIRROR environment variable support by @localai-bot in https://github.com/mudler/LocalAI/pull/8847
* feat: add Events column to Agents list page by @localai-bot in https://github.com/mudler/LocalAI/pull/8870
* feat: Add tabs to System view for Models and Backends by @localai-bot in https://github.com/mudler/LocalAI/pull/8885
* feat: Add --data-path CLI flag for persistent data separation by @localai-bot in https://github.com/mudler/LocalAI/pull/8888
* feat(mlx-distributed): add new (experimental) MLX-distributed backend by @mudler in https://github.com/mudler/LocalAI/pull/8801
* chore(size): display size of HF models and allow to specify it from the gallery by @mudler in https://github.com/mudler/LocalAI/pull/8907
* feat(ui): add canvas mode, support history in agent chat by @mudler in https://github.com/mudler/LocalAI/pull/8927
* feat(ui): MCP Apps, mcp streaming and client-side support by @mudler in https://github.com/mudler/LocalAI/pull/8947
* feat: add fish-speech backend by @mudler in https://github.com/mudler/LocalAI/pull/8962
* feat(backends): add ace-step.cpp by @mudler in https://github.com/mudler/LocalAI/pull/8965
* feat(realtime): WebRTC support by @richiejp in https://github.com/mudler/LocalAI/pull/8790
### 🧠 Models
* chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/8693
* chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/8694
* chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/8695
* chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/8696
* chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/8698
### 📖 Documentation and examples
* fix(realtime): Add functions to conversation history by @richiejp in https://github.com/mudler/LocalAI/pull/8616
* docs: update diffusers multi-GPU documentation to mention tensor_parallel_size configuration by @localai-bot in https://github.com/mudler/LocalAI/pull/8621
* docs: Update Home Assistant links in README.md by @loryanstrant in https://github.com/mudler/LocalAI/pull/8688
### 👒 Dependencies
* chore(deps): bump fyne.io/fyne/v2 from 2.7.2 to 2.7.3 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8629
* chore(deps): bump github.com/anthropics/anthropic-sdk-go from 1.22.0 to 1.26.0 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8630
* chore(deps): bump github.com/gpustack/gguf-parser-go from 0.23.1 to 0.24.0 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8631
* chore(deps): bump actions/stale from 10.1.1 to 10.2.0 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8633
* chore(deps): bump goreleaser/goreleaser-action from 6 to 7 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8634
* chore(deps): bump github.com/mudler/cogito from 0.9.1-0.20260217143801-bb7f986ed2c7 to 0.9.1 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8632
* chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/coqui by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8642
* chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/common/template by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8641
* chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/transformers by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8640
* chore(deps): bump sentence-transformers from 5.2.2 to 5.2.3 in /backend/python/transformers by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8638
* chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/rerankers by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8636
* chore(deps): bump grpcio from 1.76.0 to 1.78.1 in /backend/python/vllm by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8635
* chore(deps): bump actions/download-artifact from 7 to 8 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8729
* chore(deps): bump actions/upload-artifact from 6 to 7 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8730
* chore(deps): bump github.com/openai/openai-go/v3 from 3.19.0 to 3.24.0 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8732
* chore(deps): bump github.com/modelcontextprotocol/go-sdk from 1.3.0 to 1.4.0 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8733
* chore(deps): bump go.opentelemetry.io/otel from 1.40.0 to 1.41.0 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8734
* chore(deps): bump go.opentelemetry.io/otel/metric from 1.40.0 to 1.41.0 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8735
* chore(deps): bump github.com/google/go-containerregistry from 0.20.7 to 0.21.1 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8736
* chore(deps): bump go.opentelemetry.io/otel/sdk/metric from 1.40.0 to 1.42.0 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8915
* chore(deps): bump github.com/openai/openai-go/v3 from 3.24.0 to 3.26.0 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8916
* chore(deps): bump go.yaml.in/yaml/v2 from 2.4.3 to 2.4.4 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8913
* chore(deps): bump github.com/labstack/echo/v4 from 4.15.0 to 4.15.1 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8914
* chore(deps): bump docker/metadata-action from 5 to 6 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8917
* chore(deps): bump actions/setup-node from 4 to 6 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8920
* chore(deps): bump docker/build-push-action from 6 to 7 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8919
* chore(deps): bump docker/login-action from 3 to 4 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8918
* chore(deps): bump node from 22-slim to 25-slim by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/8922
### Other Changes
* docs: :arrow_up: update docs version mudler/LocalAI by @localai-bot in https://github.com/mudler/LocalAI/pull/8618
* chore: :arrow_up: Update ggml-org/llama.cpp to `f75c4e8bf52ea480ece07fd3d9a292f1d7f04bc5` by @localai-bot in https://github.com/mudler/LocalAI/pull/8619
* chore: :arrow_up: Update ggml-org/llama.cpp to `2b6dfe824de8600c061ef91ce5cc5c307f97112c` by @localai-bot in https://github.com/mudler/LocalAI/pull/8622
* chore: :arrow_up: Update ggml-org/llama.cpp to `b68a83e641b3ebe6465970b34e99f3f0e0a0b21a` by @localai-bot in https://github.com/mudler/LocalAI/pull/8628
* fix(webui): use different icon for System nav item by @localai-bot in https://github.com/mudler/LocalAI/pull/8648
* chore: :arrow_up: Update ggml-org/llama.cpp to `418dea39cea85d3496c8b04a118c3b17f3940ad8` by @localai-bot in https://github.com/mudler/LocalAI/pull/8649
* feat(swagger): update swagger by @localai-bot in https://github.com/mudler/LocalAI/pull/8654
* chore: :arrow_up: Update ggml-org/llama.cpp to `3769fe6eb70b0a0fbb30b80917f1caae68c902f7` by @localai-bot in https://github.com/mudler/LocalAI/pull/8655
* chore: :arrow_up: Update ggml-org/llama.cpp to `723c71064da0908c19683f8c344715fbf6d986fd` by @localai-bot in https://github.com/mudler/LocalAI/pull/8660
* fix(qwen3.5): add qwen3.5 preset and mimick llama.cpp's PEG by @mudler in https://github.com/mudler/LocalAI/pull/8668
* chore: :arrow_up: Update ggml-org/whisper.cpp to `9453b4b9be9b73adfc35051083f37cefa039acee` by @localai-bot in https://github.com/mudler/LocalAI/pull/8671
* chore(deps): bump llama.cpp to 'ecbcb7ea9d3303097519723b264a8b5f1e977028' by @mudler in https://github.com/mudler/LocalAI/pull/8672
* docs: add CDI driver config for NVIDIA GPU in containers (fix #8108) by @localai-bot in https://github.com/mudler/LocalAI/pull/8677
* docs: add TLS reverse proxy configuration guide by @localai-bot in https://github.com/mudler/LocalAI/pull/8673
* chore: :arrow_up: Update ggml-org/llama.cpp to `05728db18eea59de81ee3a7699739daaf015206b` by @localai-bot in https://github.com/mudler/LocalAI/pull/8683
* fix: simplify CI steps, fix gallery agent by @mudler in https://github.com/mudler/LocalAI/pull/8685
* fix: retry when LLM returns empty messages by @mudler in https://github.com/mudler/LocalAI/pull/8704
* feat(swagger): update swagger by @localai-bot in https://github.com/mudler/LocalAI/pull/8706
* feat: Add debug logging for pocket-tts voice issue #8244 by @localai-bot in https://github.com/mudler/LocalAI/pull/8715
* fix(ci): correct transformer backend path typo by @localai-bot in https://github.com/mudler/LocalAI/pull/8712
* chore: :arrow_up: Update ggml-org/llama.cpp to `319146247e643695f94a558e8ae686277dd4f8da` by @localai-bot in https://github.com/mudler/LocalAI/pull/8707
* fix: Implement responsive line wrapping for model names (#8209) by @localai-bot in https://github.com/mudler/LocalAI/pull/8720
* fix(qwen-tts): ensure all requirements files end with newline by @localai-bot in https://github.com/mudler/LocalAI/pull/8724
* chore(model-gallery): :arrow_up: update checksum by @localai-bot in https://github.com/mudler/LocalAI/pull/8728
* chore: :arrow_up: Update ggml-org/llama.cpp to `4d828bd1ab52773ba9570cc008cf209eb4a8b2f5` by @localai-bot in https://github.com/mudler/LocalAI/pull/8727
* chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/8743
* chore: :arrow_up: Update ggml-org/llama.cpp to `ecd99d6a9acbc436bad085783bcd5d0b9ae9e9e9` by @localai-bot in https://github.com/mudler/LocalAI/pull/8762
* chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/8770
* chore(model-gallery): :arrow_up: update checksum by @localai-bot in https://github.com/mudler/LocalAI/pull/8778
* chore: :arrow_up: Update ggml-org/llama.cpp to `24d2ee052795063afffc9732465ca1b1c65f4a28` by @localai-bot in https://github.com/mudler/LocalAI/pull/8777
* docs: add autonomous development team section to README by @localai-bot in https://github.com/mudler/LocalAI/pull/8780
* feat: Rename 'Whisper' model type to 'STT' in UI by @localai-bot in https://github.com/mudler/LocalAI/pull/8785
* chore: :arrow_up: Update ggml-org/whisper.cpp to `30c5194c9691e4e9a98b3dea9f19727397d3f46e` by @localai-bot in https://github.com/mudler/LocalAI/pull/8796
* chore: :arrow_up: Update ggml-org/llama.cpp to `a0ed91a442ea6b013bd42ebc3887a81792eaefa1` by @localai-bot in https://github.com/mudler/LocalAI/pull/8797
* feat: pass-by metadata to predict options by @mudler in https://github.com/mudler/LocalAI/pull/8795
* fix: Add timeout-based wait for model deletion completion by @localai-bot in https://github.com/mudler/LocalAI/pull/8756
* chore: Add LTX-2.3 model to gallery by @localai-bot in https://github.com/mudler/LocalAI/pull/8805
* chore: :arrow_up: Update ggml-org/llama.cpp to `566059a26b0ce8faec4ea053605719d399c64cc5` by @localai-bot in https://github.com/mudler/LocalAI/pull/8822
* chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/8828
* chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/8830
* feat: update descriptions for first 9 models in gallery/index.yaml by @localai-bot in https://github.com/mudler/LocalAI/pull/8831
* chore: :arrow_up: Update ggml-org/llama.cpp to `c5a778891ba0ddbd4cbb507c823f970595b1adc2` by @localai-bot in https://github.com/mudler/LocalAI/pull/8837
* chore(docs): Populate coding guidelines in CONTRIBUTING.md by @localai-bot in https://github.com/mudler/LocalAI/pull/8840
* fix: Remove debug print statement from soundgeneration.go (C2) by @localai-bot in https://github.com/mudler/LocalAI/pull/8843
* docs: Add comprehensive API error reference documentation by @localai-bot in https://github.com/mudler/LocalAI/pull/8848
* docs: add Table of Contents to README.md by @localai-bot in https://github.com/mudler/LocalAI/pull/8846
* chore: :arrow_up: Update leejet/stable-diffusion.cpp to c8fb3d245858d495be1f140efdcfaa0d49de41e5 by @localai-bot in https://github.com/mudler/LocalAI/pull/8841
* docs: clarify SECURITY.md version support table with specific ranges and EOL dates by @localai-bot in https://github.com/mudler/LocalAI/pull/8861
* fix: Correct Talk Interface screenshot reference in README.md (H6) by @localai-bot in https://github.com/mudler/LocalAI/pull/8857
* feat: Add documentation for undocumented API endpoints by @localai-bot in https://github.com/mudler/LocalAI/pull/8852
* docs: add comprehensive development setup instructions to CONTRIBUTING.md (H7) by @localai-bot in https://github.com/mudler/LocalAI/pull/8860
* feat(cli): add configurable backend image fallback tags via CLI options by @localai-bot in https://github.com/mudler/LocalAI/pull/8817
* feat: add MIT license badge to README.md by @localai-bot in https://github.com/mudler/LocalAI/pull/8871
* feat: Create comprehensive troubleshooting guide (M1 task) by @localai-bot in https://github.com/mudler/LocalAI/pull/8856
* docs: expand GPU acceleration guide with L4T, multi-GPU, monitoring, and troubleshooting by @localai-bot in https://github.com/mudler/LocalAI/pull/8858
* feat: Add documentation URLs to CLI help text by @localai-bot in https://github.com/mudler/LocalAI/pull/8874
* feat(functions): add peg-based parsing and allow backends to return tool calls directly by @mudler in https://github.com/mudler/LocalAI/pull/8838
* chore: Update README.md screenshot references and alt text by @localai-bot in https://github.com/mudler/LocalAI/pull/8862
* chore: :arrow_up: Update ggml-org/llama.cpp to `35bee031e17ed2b2e8e7278b284a6c8cd120d9f8` by @localai-bot in https://github.com/mudler/LocalAI/pull/8872
* docs: Update model compatibility documentation with missing backends by @localai-bot in https://github.com/mudler/LocalAI/pull/8889
* docs: make examples repository link more prominent by @localai-bot in https://github.com/mudler/LocalAI/pull/8895
* chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/8901
* chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/8902
* chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/8904
* feat: Redesign explorer and models pages with react-ui theme by @localai-bot in https://github.com/mudler/LocalAI/pull/8903
* fix(ui): minor visual enhancements by @mudler in https://github.com/mudler/LocalAI/pull/8909
* feat(swagger): update swagger by @localai-bot in https://github.com/mudler/LocalAI/pull/8923
* feat: Standardize CLI flag naming to kebab-case (M12) by @localai-bot in https://github.com/mudler/LocalAI/pull/8912
* chore: :arrow_up: Update leejet/stable-diffusion.cpp to `d6dd6d7b555c233bb9bc9f20b4751eb8c9269743` by @localai-bot in https://github.com/mudler/LocalAI/pull/8925
* chore: :arrow_up: Update ggml-org/llama.cpp to `23fbfcb1ad6c6f76b230e8895254de785000be46` by @localai-bot in https://github.com/mudler/LocalAI/pull/8921
* fix: correct grammar in CONTRIBUTING.md documentation section by @localai-bot in https://github.com/mudler/LocalAI/pull/8932
* feat: Expand section index pages with comprehensive navigation (M7) by @localai-bot in https://github.com/mudler/LocalAI/pull/8929
* chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/8939
* chore(model-gallery): :arrow_up: update checksum by @localai-bot in https://github.com/mudler/LocalAI/pull/8945
* chore: :arrow_up: Update ggml-org/llama.cpp to `10e5b148b061569aaee8ae0cf72a703129df0eab` by @localai-bot in https://github.com/mudler/LocalAI/pull/8946
* fix: include model name in mmproj file path to prevent model isolation (#8937) by @localai-bot in https://github.com/mudler/LocalAI/pull/8940
* feat(swagger): update swagger by @localai-bot in https://github.com/mudler/LocalAI/pull/8961
* docs: Document GPU auto-fit mode limitations and trade-offs (closes #8562) by @localai-bot in https://github.com/mudler/LocalAI/pull/8954
* chore(ui): improve errors and reporting during model installation by @mudler in https://github.com/mudler/LocalAI/pull/8979
* chore(model gallery): :robot: add 1 new models via gallery agent by @localai-bot in https://github.com/mudler/LocalAI/pull/8980
* fix(collections): start agent pool after http server by @mudler in https://github.com/mudler/LocalAI/pull/8981
* chore(model-gallery): :arrow_up: update checksum by @localai-bot in https://github.com/mudler/LocalAI/pull/8985
* chore: :arrow_up: Update ggml-org/llama.cpp to `57819b8d4b39d893408e51520dff3d47d1ebb757` by @localai-bot in https://github.com/mudler/LocalAI/pull/8983
* chore: :arrow_up: Update ace-step/acestep.cpp to `5aa065445541094cba934299cd498bbb9fa5c434` by @localai-bot in https://github.com/mudler/LocalAI/pull/8984
* fix(ui): Move routes to /app to avoid conflict with API endpoints by @richiejp in https://github.com/mudler/LocalAI/pull/8978
* fix(conf): Don't overwrite env provided galleries with runtime conf by @richiejp in https://github.com/mudler/LocalAI/pull/8994
* fix(flux.2-klein-9b): Use Qwen3-8b to avoid GGML assertion failure on tensor mismatch by @richiejp in https://github.com/mudler/LocalAI/pull/8995
* fix(acestep-cpp): resolve relative model paths in options by @localai-bot in https://github.com/mudler/LocalAI/pull/8993
* chore: :arrow_up: Update ggml-org/llama.cpp to `e30f1fdf74ea9238ff562901aa974c75aab6619b` by @localai-bot in https://github.com/mudler/LocalAI/pull/8997

</details>

## New Contributors
* @loryanstrant made their first contribution in https://github.com/mudler/LocalAI/pull/8688
* @bittoby made their first contribution in https://github.com/mudler/LocalAI/pull/8676
* @Weathercold made their first contribution in https://github.com/mudler/LocalAI/pull/8842
* @attilagyorffy made their first contribution in https://github.com/mudler/LocalAI/pull/8879

**Full Changelog**: https://github.com/mudler/LocalAI/compare/v3.12.1...v4.0.0