fix(gallery): persist inference defaults under parameters

Gallery installs merged family defaults at the YAML root and only re-marshaled them on the artifact path. Persist the defaults in the loader-visible parameters map for every install path while preserving authored overrides.

Assisted-by: Codex:gpt-5

.agents/ci-caching.md

@@ -359,6 +359,26 @@ GitHub Actions caches are limited to 10 GB per repo. Steady-state worst case: ~8
 
 One residual self-hosted reference remains in `test-extra.yml` (`tests-vibevoice-cpp-grpc-transcription` uses `bigger-runner` for the 30s JFK-decode timeout headroom). That's a separate concern.
 
+### Small always-on jobs routed to `arc-runner-set`
+
+The hosted pool is shared across the whole *account*, not per repo, so a burst in one repo starves the others. On 2026-07-31 it went to **zero scheduled jobs for 35 consecutive minutes** with 39 jobs queued, while `arc-runner-set` completed 12 jobs without interruption over the same window. Actions was healthy globally at the time (other public repos were scheduling normally), so this is an account-level throttle, not an outage.
+
+`gh-pages.yml` (`build` + `deploy`) is therefore routed to `arc-runner-set` when `github.repository == 'mudler/LocalAI'`. It needs no fork-safety clause because it only triggers on push-to-master and `workflow_dispatch`, so it never executes pull-request code. The repository guard keeps forks (which have no such runner label) from queueing forever. It fetches its own toolchains via `setup-go` / `actions-hugo` and uses no `sudo`/`apt`.
+
+#### What the `arc-runner-set` image actually contains
+
+Measured 2026-07-31 on run `30637392862` by a preflight step, not assumed:
+
+| present | **absent** |
+|---|---|
+| `git`, `curl`, `unzip`, `tar`, `ldd`, `python3` | **`make`**, **`gcc`** |
+
+That is why `lint.yml` is **not** on the self-hosted pool. Both of its jobs were routed there and both failed in one second: `golangci-lint` needs `make` (for `make protogen-go`, itself needing `curl`+`unzip` to fetch protoc, and for `make lint`), and `build-scripts` additionally needs a C toolchain because the packaging-script tests compile a throwaway binary and inspect it with `ldd`. Both jobs are back on `ubuntu-latest`.
+
+The preflight steps were deliberately left in place. They cost about a second on the hosted pool and mean that whenever the runner image gains `make` + `gcc`, re-routing is one `runs-on:` line per job and any remaining gap reports itself by name rather than as an opaque mid-build failure.
+
+Note for any future re-route: `lint.yml` also triggers on `pull_request`, and a fork PR runs untrusted contributor code. That must never reach a persistent self-hosted runner, so any re-route has to stay push-only, e.g. `${{ (github.event_name == 'push' && github.repository == 'mudler/LocalAI') && 'arc-runner-set' || 'ubuntu-latest' }}`.
+
 ## Touching the cache pipeline
 
 When changing `image_build.yml`, `backend_build.yml`, any of the `backend/Dockerfile.*` files, `Dockerfile.base-grpc-builder`, `.docker/install-base-deps.sh`, `.docker/<backend>-compile.sh`, or `scripts/changed-backends.js`:

.github/workflows/gh-pages.yml

@@ -25,7 +25,20 @@ concurrency:
 
 jobs:
   build:
-    runs-on: ubuntu-latest
+    # Self-hosted. This workflow is push-to-master + workflow_dispatch only, so
+    # it never executes pull-request code and a fork cannot reach the runner
+    # with untrusted changes. The repository guard keeps forks (whose own master
+    # pushes would otherwise queue forever against a label they do not have) on
+    # the hosted pool.
+    #
+    # Why: the GitHub-hosted pool is shared account-wide and has repeatedly
+    # starved (2026-07-31: 35 consecutive minutes at zero scheduled jobs, while
+    # arc-runner-set kept completing work throughout). Publishing the site is
+    # small, frequent, and must not sit behind a saturated hosted queue.
+    #
+    # Needs only git, tar and curl on the runner: setup-go and actions-hugo
+    # fetch their own toolchains, and no step uses sudo, apt, make or unzip.
+    runs-on: ${{ github.repository == 'mudler/LocalAI' && 'arc-runner-set' || 'ubuntu-latest' }}
     env:
       HUGO_VERSION: "0.146.3"
     steps:
@@ -86,7 +99,11 @@ jobs:
     environment:
       name: github-pages
       url: ${{ steps.deployment.outputs.page_url }}
-    runs-on: ubuntu-latest
+    # Same routing as build: a hosted slot for a ~10s deploy is exactly the kind
+    # of job that should not block on a starved pool. deploy-pages authenticates
+    # with the job's OIDC token (id-token: write above), which self-hosted
+    # runners issue the same way hosted ones do.
+    runs-on: ${{ github.repository == 'mudler/LocalAI' && 'arc-runner-set' || 'ubuntu-latest' }}
     needs: build
     steps:
       - name: Deploy to GitHub Pages

.github/workflows/lint.yml

@@ -21,8 +21,41 @@ concurrency:
 
 jobs:
   golangci-lint:
+    # Self-hosted for PUSH only, and only in the canonical repo.
+    #
+    # This workflow also runs on pull_request, which for a fork PR means
+    # executing untrusted contributor code. That must never land on a
+    # self-hosted runner, so anything that is not a push to mudler/LocalAI stays
+    # on the ephemeral hosted pool. Pushes to master are trusted code that has
+    # already been reviewed and merged.
+    #
+    # Why at all: the hosted pool is shared account-wide and starved for 35
+    # straight minutes on 2026-07-31 while arc-runner-set kept completing jobs.
+    # Lint is small and runs on every commit, so it is a good candidate to move
+    # off the contended pool.
+    # REVERTED to hosted: the arc-runner-set image has git, curl, unzip, tar,
+    # ldd and python3, but NOT make (nor gcc). Measured on run 30637392862,
+    # where the preflight below named both. Re-route here once the runner image
+    # ships a C toolchain and make; the preflight stays so the next attempt
+    # fails by name in one second instead of opaquely mid-build.
     runs-on: ubuntu-latest
     steps:
+      - name: Preflight - required host tools
+        # The hosted images ship these; a self-hosted container image may not.
+        # Check up front so a missing tool reports itself by name instead of
+        # surfacing as an opaque failure inside `make protogen-go` (which needs
+        # curl + unzip for protoc) or `make lint`.
+        run: |
+          missing=""
+          for t in git curl unzip make tar; do
+            command -v "$t" >/dev/null 2>&1 || missing="$missing $t"
+          done
+          echo "runner: ${RUNNER_NAME:-unknown}  os: $(uname -sm)"
+          if [ -n "$missing" ]; then
+            echo "::error::missing required tools on this runner:$missing"
+            exit 1
+          fi
+          echo "all required tools present"
       - uses: actions/checkout@v7
         with:
           # Full history so golangci-lint's new-from-merge-base can reach
@@ -55,8 +88,30 @@ jobs:
     # container build (a missing transitive dep, a partial cuDNN family). Their
     # shell tests need nothing but bash + gcc + ldd, so run them on every PR
     # rather than waiting on a multi-GB cross-arch backend image build.
+    #
+    # Push-only self-hosted routing, same fork-safety reasoning as
+    # golangci-lint above.
+    # REVERTED to hosted: the arc-runner-set image has git, curl, unzip, tar,
+    # ldd and python3, but NOT make (nor gcc). Measured on run 30637392862,
+    # where the preflight below named both. Re-route here once the runner image
+    # ships a C toolchain and make; the preflight stays so the next attempt
+    # fails by name in one second instead of opaquely mid-build.
     runs-on: ubuntu-latest
     steps:
+      - name: Preflight - required host tools
+        # This job additionally needs a C toolchain: the packaging-script tests
+        # compile a throwaway binary and inspect it with ldd.
+        run: |
+          missing=""
+          for t in git make gcc ldd python3; do
+            command -v "$t" >/dev/null 2>&1 || missing="$missing $t"
+          done
+          echo "runner: ${RUNNER_NAME:-unknown}  os: $(uname -sm)"
+          if [ -n "$missing" ]; then
+            echo "::error::missing required tools on this runner:$missing"
+            exit 1
+          fi
+          echo "all required tools present"
       - uses: actions/checkout@v7
       - name: run packaging script tests
         run: make test-build-scripts

core/gallery/empty_base_install_test.go

@@ -236,8 +236,8 @@ var _ = Describe("InstallModelFromGallery with an empty base config", func() {
 		Expect(install(e.Name, gallery.GalleryModel{})).To(Succeed())
 		cfg := installedConfig(e.Name)
 		Expect(cfg["name"]).To(Equal(e.Name))
-		// The catalog's own overrides, verbatim, laid over the empty base.
-		Expect(cfg["parameters"]).To(Equal(e.Overrides["parameters"]))
+		// The catalog's model override survives inference-default enrichment.
+		Expect(cfg["parameters"]).To(HaveKeyWithValue("model", "LiquidAI_LFM2-1.2B-RAG-Q4_K_M.gguf"))
 		Expect(cfg["known_usecases"]).To(Equal(e.Overrides["known_usecases"]))
 	})
 })

core/gallery/inference_defaults_install_test.go

@@ -0,0 +1,90 @@
+package gallery_test
+
+import (
+	"context"
+	"os"
+	"path/filepath"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+	"gopkg.in/yaml.v3"
+
+	"github.com/mudler/LocalAI/core/gallery"
+	"github.com/mudler/LocalAI/pkg/modelartifacts"
+	"github.com/mudler/LocalAI/pkg/system"
+)
+
+var _ = Describe("gallery inference defaults", func() {
+	readPersistedConfig := func(modelsPath, name string) map[string]any {
+		data, err := os.ReadFile(filepath.Join(modelsPath, name+".yaml"))
+		Expect(err).NotTo(HaveOccurred())
+		persisted := map[string]any{}
+		Expect(yaml.Unmarshal(data, &persisted)).To(Succeed())
+		return persisted
+	}
+
+	expectNestedDefaults := func(persisted map[string]any) {
+		Expect(persisted).NotTo(HaveKey("temperature"))
+		Expect(persisted).NotTo(HaveKey("top_p"))
+		parameters, ok := persisted["parameters"].(map[string]any)
+		Expect(ok).To(BeTrue())
+		Expect(parameters).To(HaveKeyWithValue("temperature", 0.7))
+		Expect(parameters).To(HaveKeyWithValue("top_p", 0.42))
+		Expect(parameters).To(HaveKeyWithValue("top_k", 20))
+		Expect(parameters).To(HaveKeyWithValue("min_p", 0))
+		Expect(parameters).To(HaveKeyWithValue("repeat_penalty", 1))
+		Expect(parameters).To(HaveKeyWithValue("presence_penalty", 1.5))
+	}
+
+	It("persists defaults under parameters after artifact binding", func() {
+		modelsPath := GinkgoT().TempDir()
+		state, err := system.GetSystemState(system.WithModelPath(modelsPath))
+		Expect(err).NotTo(HaveOccurred())
+		resolved := modelartifacts.Spec{
+			Name: "model", Target: "model",
+			Source: modelartifacts.Source{Type: "huggingface", Repo: "owner/qwen3.5-model", Revision: "main"},
+			Resolved: &modelartifacts.Resolved{
+				Endpoint: "https://huggingface.co",
+				Revision: "0123456789abcdef0123456789abcdef01234567",
+				CacheKey: "0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef",
+			},
+		}
+		fake := &fakeArtifactMaterializer{result: modelartifacts.Result{Spec: resolved}}
+		definition := &gallery.ModelConfig{Name: "qwen3.5-artifact", ConfigFile: `
+backend: transformers
+artifacts:
+  - name: model
+    target: model
+    source: {type: huggingface, repo: owner/qwen3.5-model}
+parameters:
+  model: owner/qwen3.5-model
+  top_p: 0.42
+`}
+
+		_, err = gallery.InstallModel(context.Background(), state, "", definition, nil, nil, false,
+			gallery.WithArtifactMaterializer(fake))
+		Expect(err).NotTo(HaveOccurred())
+		expectNestedDefaults(readPersistedConfig(modelsPath, definition.Name))
+	})
+
+	It("persists defaults under parameters when the entry declares files", func() {
+		modelsPath := GinkgoT().TempDir()
+		state, err := system.GetSystemState(system.WithModelPath(modelsPath))
+		Expect(err).NotTo(HaveOccurred())
+		Expect(os.WriteFile(filepath.Join(modelsPath, "weights.gguf"), []byte("weights"), 0644)).To(Succeed())
+		definition := &gallery.ModelConfig{
+			Name: "qwen3.5-files",
+			ConfigFile: `
+backend: llama-cpp
+parameters:
+  model: weights.gguf
+  top_p: 0.42
+`,
+			Files: []gallery.File{{Filename: "weights.gguf", URI: "https://example.com/weights.gguf"}},
+		}
+
+		_, err = gallery.InstallModel(context.Background(), state, "", definition, nil, nil, false)
+		Expect(err).NotTo(HaveOccurred())
+		expectNestedDefaults(readPersistedConfig(modelsPath, definition.Name))
+	})
+})

core/gallery/models.go

@@ -622,35 +622,41 @@ func InstallModel(ctx context.Context, systemState *system.SystemState, nameOver
 		lconfig.ApplyInferenceDefaults(&modelConfig, name, modelConfig.Model)
 
 		// Merge inference defaults into configMap so they are persisted without losing unknown fields.
+		defaults := make(map[string]any)
 		if modelConfig.Temperature != nil {
-			if _, exists := configMap["temperature"]; !exists {
-				configMap["temperature"] = *modelConfig.Temperature
-			}
+			defaults["temperature"] = *modelConfig.Temperature
 		}
 		if modelConfig.TopP != nil {
-			if _, exists := configMap["top_p"]; !exists {
-				configMap["top_p"] = *modelConfig.TopP
-			}
+			defaults["top_p"] = *modelConfig.TopP
 		}
 		if modelConfig.TopK != nil {
-			if _, exists := configMap["top_k"]; !exists {
-				configMap["top_k"] = *modelConfig.TopK
-			}
+			defaults["top_k"] = *modelConfig.TopK
 		}
 		if modelConfig.MinP != nil {
-			if _, exists := configMap["min_p"]; !exists {
-				configMap["min_p"] = *modelConfig.MinP
-			}
+			defaults["min_p"] = *modelConfig.MinP
 		}
 		if modelConfig.RepeatPenalty != 0 {
-			if _, exists := configMap["repeat_penalty"]; !exists {
-				configMap["repeat_penalty"] = modelConfig.RepeatPenalty
-			}
+			defaults["repeat_penalty"] = modelConfig.RepeatPenalty
 		}
 		if modelConfig.PresencePenalty != 0 {
-			if _, exists := configMap["presence_penalty"]; !exists {
-				configMap["presence_penalty"] = modelConfig.PresencePenalty
+			defaults["presence_penalty"] = modelConfig.PresencePenalty
+		}
+		if len(defaults) > 0 {
+			parameters, ok := configMap["parameters"].(map[string]any)
+			if !ok {
+				parameters = make(map[string]any)
+				configMap["parameters"] = parameters
 			}
+			for key, value := range defaults {
+				if _, exists := parameters[key]; !exists {
+					parameters[key] = value
+				}
+			}
+		}
+
+		updatedConfigYAML, err = yaml.Marshal(configMap)
+		if err != nil {
+			return nil, fmt.Errorf("failed to marshal config with inference defaults: %v", err)
 		}
 
 		if valid, err := modelConfig.Validate(); !valid {

website/data/ecosystem.yaml

@@ -19,6 +19,10 @@
 
 contributors:
   note: "Engineers whose public profile names these employers have commits in the repository."
+  # The landing page prints the names only, not the per-company counts: a "1
+  # commit" stamp next to a large employer reads as weakness even though the
+  # claim is exactly as true. The counts stay here because they are the
+  # provenance for the list, and anyone re-checking it needs them.
   companies:
     - { name: "Microsoft",       people: 3, commits: 20 }
     - { name: "Spectro Cloud",   people: 3, commits: 11 }
@@ -51,47 +55,141 @@ contributors:
 
 integrations:
   note: "These projects reference LocalAI in their own repository or documentation."
+  # Admission rule: the project's OWN repository or official docs must name
+  # LocalAI as a provider, backend or integration. A blog post saying so is not
+  # enough, and neither is a generic "any OpenAI-compatible server" line that
+  # never names us. Every entry below was opened and read before being added,
+  # and the quote that justifies it is in the pull request that added it.
+  #
+  # Deliberately excluded after checking: LiteLLM, n8n, Home Assistant core,
+  # BionicGPT, Semantic Kernel, Spring AI, Jan, CrewAI, Haystack, Onyx,
+  # SillyTavern, Portkey and Kong all have zero mentions in their own repos.
+  # PrivateGPT and Langflow name us only in passing comparisons or a tooltip.
+  # Tools4AI has a LocalAI processor whose methods return null.
   projects:
     - name: AnythingLLM
       by: Mintplex Labs
       url: https://github.com/Mintplex-Labs/anything-llm
       what: "Runs LocalAI as a model provider for its chat and document workspaces."
-    - name: langchain4j
-      url: https://github.com/langchain4j/langchain4j
-      what: "Ships a LocalAI module, so JVM applications can target it directly."
     - name: LangChain
       url: https://python.langchain.com/docs/integrations/providers/localai/
       what: "Documents LocalAI as a provider in the Python integrations."
+    - name: LlamaIndex
+      url: https://docs.llamaindex.ai/en/stable/examples/llm/localai/
+      what: "Documents LocalAI as an OpenAI-compatible LLM you can point it at."
+    - name: Open WebUI
+      url: https://docs.openwebui.com/getting-started/quick-start/connect-a-provider/starting-with-openai-compatible
+      what: "Connects to LocalAI as an OpenAI-compatible local server."
+    - name: Dify
+      by: LangGenius
+      url: https://marketplace.dify.ai/plugin/langgenius/localai
+      what: "Ships an official LocalAI plugin for inference and embeddings."
+    - name: LibreChat
+      url: https://www.librechat.ai/docs/configuration/librechat_yaml/object_structure/speech
+      what: "Uses LocalAI as a speech provider for text to speech."
+    - name: RAGFlow
+      by: InfiniFlow
+      url: https://ragflow.io/docs/supported_models
+      what: "Lists LocalAI as a model provider, and ships a driver for it including rerank."
     - name: Flowise
       by: FlowiseAI
       url: https://github.com/FlowiseAI/Flowise
       what: "Offers LocalAI as a node for chat and embeddings in its visual builder."
+    - name: Continue
+      url: https://docs.continue.dev/customize/model-providers/top-level/openai
+      what: "Lists LocalAI among the OpenAI-compatible providers the editor can target."
+    - name: big-AGI
+      url: https://github.com/enricoros/big-AGI/blob/main/docs/config-local-localai.md
+      what: "Adds LocalAI as a model source, with its own setup page and env vars."
+    - name: K8sGPT
+      by: CNCF Sandbox
+      url: https://docs.k8sgpt.ai/reference/providers/backend/
+      what: "Lists LocalAI as an analysis backend, alongside Bedrock and Azure OpenAI."
+    - name: k8sgpt-operator
+      by: k8sgpt-ai
+      url: https://github.com/k8sgpt-ai/k8sgpt-operator
+      what: "Sets LocalAI as the backend on the K8sGPT custom resource, with no OpenAI secret."
+    - name: Nextcloud
+      url: https://apps.nextcloud.com/apps/integration_openai
+      what: "Points its text, image and speech features at a self-hosted LocalAI."
+    - name: Frigate
+      url: https://github.com/blakeblackshear/frigate/blob/dev/docs/docs/configuration/genai/config.md
+      what: "Names LocalAI as a server for its generative AI features."
+      # Present in the dev branch docs source; not yet on the published site.
+    - name: Kairos
+      url: https://github.com/kairos-io/kairos
+      what: "Ships LocalAI as part of its immutable Linux distribution."
     - name: AIKit
       by: Sertac Ozercan
       url: https://github.com/sozercan/aikit
       what: "Builds fine-tuned models into images that serve through LocalAI."
-    - name: Kairos
-      url: https://github.com/kairos-io/kairos
-      what: "Ships LocalAI as part of its immutable Linux distribution."
+    - name: langchain4j
+      url: https://github.com/langchain4j/langchain4j
+      what: "Ships a LocalAI module, so JVM applications can target it directly."
+    - name: promptfoo
+      url: https://www.promptfoo.dev/docs/providers/localai/
+      what: "Provides a localai: prefix so evals run against chat, completion and embeddings."
+    - name: Mods
+      by: Charm
+      url: https://github.com/charmbracelet/mods
+      what: "Reads a LocalAI endpoint from its config, so the CLI pipes shell output to a local model."
+    - name: TypingMind
+      url: https://docs.typingmind.com/manage-and-connect-ai-models/local-ai
+      what: "Documents pointing a custom model endpoint at a LocalAI server."
+    - name: baibot
+      by: etke.cc
+      url: https://github.com/etkecc/baibot/blob/main/docs/providers.md
+      what: "Has a first-class localai provider for text, speech to text and text to speech."
+    - name: LLM Vision
+      by: Home Assistant
+      url: https://github.com/valentinfrlch/ha-llmvision
+      what: "Lists LocalAI as a provider for analysing camera images and video feeds."
+    - name: VoxInput
+      url: https://github.com/richiejp/VoxInput
+      what: "Sends desktop voice input to LocalAI for transcription and a realtime assistant."
+    - name: Obsidian BMO Chatbot
+      url: https://github.com/longy2k/obsidian-bmo-chatbot
+      what: "Lists LocalAI as a self-hosted endpoint for the note-taking chat plugin."
+    - name: ShellOracle
+      url: https://github.com/djcopley/ShellOracle
+      what: "Ships a LocalAI provider for turning natural language into shell commands."
+    - name: QA-Pilot
+      url: https://github.com/reid41/QA-Pilot
+      what: "Runs its repository chat against a LocalAI base URL."
 
 press:
   note: "Written about LocalAI, by people who do not work on it."
+  # One card per outlet. SUSE published four posts, and listing them as four
+  # entries made a single vendor look like the whole of the coverage; as one
+  # series entry the repetition becomes the point instead of the problem.
+  #
+  # Every entry here has been opened and checked to confirm it is about this
+  # project. Two earlier "coverage" links were not: a modelslab.com piece that
+  # reviewed Frikallo/parakeet.cpp, an unrelated project of the same name, and
+  # a snailtext.app benchmark of Parakeet through ONNX Runtime that never
+  # mentioned LocalAI at all. Verify before adding.
   articles:
+    - outlet: Pulumi
+      title: "Deploy low-code LLM apps on AWS with Flowise and LocalAI"
+      author: "Engin Diri"
+      date: "2024-02-26"
+      url: https://www.pulumi.com/blog/low-code-llm-apps-with-local-ai-flowise-and-pulumi/
+      what: "A full EKS deployment, with LocalAI doing inference and no GPU in the cluster."
+    - outlet: Semaphore
+      title: "LocalAI: replacing OpenAI API with open-source"
+      author: "Tomas Fernandez"
+      date: "2023-12-19"
+      url: https://semaphore.io/blog/localai
+      what: "Swapping an existing OpenAI integration over to LocalAI, endpoint by endpoint."
+    - outlet: Spectro Cloud
+      title: "K8sGPT + LocalAI: unlock Kubernetes superpowers for free"
+      author: "Tyler Gillson"
+      date: "2023-04-29"
+      url: https://www.spectrocloud.com/blog/k8sgpt-localai-unlock-kubernetes-superpowers-for-free
+      what: "Cluster diagnosis through K8sGPT, answered by a model running on CPU."
     - outlet: SUSE
-      title: "Running AI locally"
+      title: "A four-part series on running AI locally"
       author: "Christian Huller"
       date: "2025-11-24"
       url: https://www.suse.com/c/running-ai-locally/
-      what: "Deploying LocalAI on openSUSE, then driving it from VS Code."
-    - outlet: SUSE
-      title: "Adding own documents to your local AI using RAG"
-      url: https://www.suse.com/c/adding-own-documents-to-your-local-ai-using-rag/
-      what: "Retrieval over your own documents, on top of LocalAI."
-    - outlet: SUSE
-      title: "Local AI and Confluence"
-      url: https://www.suse.com/c/local-ai-and-confluence/
-      what: "Putting a Confluence space behind a local model."
-    - outlet: SUSE
-      title: "Introduction to AI training with openSUSE"
-      url: https://www.suse.com/c/introduction-to-ai-training-with-opensuse/
-      what: "Training a LoRA and serving it through LocalAI."
+      what: "Install on openSUSE and drive it from VS Code, add your own documents with RAG, put a Confluence space behind a local model, then train a LoRA and serve it."

website/hugo.toml

@@ -18,6 +18,7 @@ enableEmoji = true
   huggingface = 'https://huggingface.co/mudler'
   # Refreshed by hand or by CI; shown in the nav and the traction band.
   stars = '48,042'
+  contributors = '224'
 
 [markup.goldmark.renderer]
   unsafe = true

website/layouts/index.html

@@ -13,6 +13,7 @@
         <div class="acts fd">
           <a class="btn" href="#start">Install LocalAI <span>→</span></a>
           <a class="btn btn--o" href="/docs/">Read the docs</a>
+          <a class="btn btn--o" href="{{ .Site.Params.github }}">&#9733; Star on GitHub</a>
         </div>
         <div class="figures fd">
           <div><b class="tnum" data-count="48042">0</b><span>GitHub stars</span></div>
@@ -279,7 +280,7 @@
     </div>
     <p class="mono rv" style="margin-top:.9rem;font-size:.66rem;color:var(--p-dim)">Qwen3.5-35B-A3B on an NVIDIA DGX Spark (GB10). Perplexity on wikitext-2-raw at context 2048. Full methodology in the technical report.</p>
     <div class="acts rv">
-      <a class="btn" href="https://huggingface.co/collections/mudler/apex-quants">APEX models on Hugging Face ↗</a>
+      <a class="btn" href="https://huggingface.co/collections/mudler/apex-quants-gguf">APEX models on Hugging Face ↗</a>
       <a class="btn btn--o" href="https://github.com/localai-org/apex-quant">Technical report ↗</a>
     </div>
   </div>
@@ -397,35 +398,9 @@
       <span>Deutsch</span><span>Español</span><span>français</span><span>日本語</span>
       <span>한국어</span><span>Português</span><span>Русский</span><span>中文</span>
     </div>
-    <p class="kicker rv mt3">Who turns up around it</p>
-    <h3 class="eco__h rv">Engineers from these companies have put code in</h3>
-    <p class="eco__note rv">Every name below is a person with commits in the repository whose public profile
-      names that employer. It is a claim about them, not about their employer, and the commit history is
-      there if you want to check it. Organisations that want to say they use LocalAI add themselves to
-      <a href="https://github.com/mudler/LocalAI/blob/master/ADOPTERS.md">ADOPTERS.md</a>.</p>
-    <ul class="eco eco--co rv">
-      {{- range .Site.Data.ecosystem.contributors.companies }}
-      <li><b>{{ .name }}</b><span>{{ .commits }} commit{{ if ne .commits 1 }}s{{ end }}{{ if gt .people 1 }}, {{ .people }} people{{ end }}</span></li>
-      {{- end }}
-    </ul>
-    <p class="eco__aside rv">Plus researchers at {{ delimit .Site.Data.ecosystem.contributors.academia ", " " and " }}.</p>
-
-    <h3 class="eco__h rv mt3">And these projects integrate it</h3>
-    <p class="eco__note rv">Each one references LocalAI in its own repository or documentation, so you can
-      verify any of them without taking our word for it.</p>
-    <div class="eco eco--int rv">
-      {{- range .Site.Data.ecosystem.integrations.projects }}
-      <a href="{{ .url }}"><b>{{ .name }}</b>{{ with .by }}<em>{{ . }}</em>{{ end }}<span>{{ .what }}</span></a>
-      {{- end }}
-    </div>
-
-    <h3 class="eco__h rv mt3">Written about elsewhere</h3>
-    <div class="eco eco--press rv">
-      {{- range .Site.Data.ecosystem.press.articles }}
-      <a href="{{ .url }}"><b>{{ .outlet }}</b><span>{{ .title }}</span><em>{{ .what }}</em></a>
-      {{- end }}
-    </div>
-
+    {{/* The strongest sentence in this section is somebody else's, so it opens
+         the section rather than closing it. Everything below is supporting
+         evidence for what these three people already said. */}}
     <p class="kicker rv mt3">What other people say</p>
     <div class="headline">
       <a class="hq rv" href="https://x.com/ggerganov/status/2065447087311917459">
@@ -442,6 +417,45 @@
         <span class="hq__go">Read the post &#8599;</span></a>
     </div>
 
+    {{/* Names run as a sentence rather than a grid of pills. A pill wall of
+         employers reads as a customer logo wall, which is a claim we are not
+         making; a sentence keeps it about the people, which is the true one. */}}
+    <p class="kicker rv mt3">Who shows up</p>
+    <h3 class="eco__h rv">{{ .Site.Params.contributors }} people have put code in this repository.</h3>
+    {{- $co := slice }}
+    {{- range .Site.Data.ecosystem.contributors.companies }}{{ $co = $co | append (printf "<b>%s</b>" .name) }}{{ end }}
+    {{- $ac := slice }}
+    {{- range .Site.Data.ecosystem.contributors.academia }}{{ $ac = $ac | append (printf "<b>%s</b>" .) }}{{ end }}
+    <p class="eco__names rv">Some of them do it from a desk at {{ delimit $co ", " " and " | safeHTML }}.
+      Others from labs at {{ delimit $ac ", " " and " | safeHTML }}.</p>
+    <p class="eco__note rv">That is where they work, not who sent them.
+      <a href="{{ .Site.Params.github }}/graphs/contributors">Check out the full contributor list, 200+ and growing &#8599;</a></p>
+
+    {{/* The list runs as a marquee because the count is the argument: any one
+         of these is a weak signal, and the whole moving line is the strong one.
+         It pauses on hover so the links stay usable. */}}
+    <h3 class="eco__h rv mt3">And many projects integrate it</h3>
+    <p class="eco__note rv">Click any name to see where they say so.</p>
+    <div class="reel reel--int rv">
+      <div class="reel__t">
+        {{- range .Site.Data.ecosystem.integrations.projects }}
+        <a href="{{ .url }}">{{ .name }}</a>
+        {{- end }}
+        {{- range .Site.Data.ecosystem.integrations.projects }}
+        <a href="{{ .url }}" tabindex="-1" aria-hidden="true">{{ .name }}</a>
+        {{- end }}
+      </div>
+    </div>
+    <p class="eco__aside rv">Using LocalAI at work? Add your organisation to
+      <a href="{{ .Site.Params.github }}/blob/master/ADOPTERS.md">ADOPTERS.md</a>.</p>
+
+    <h3 class="eco__h rv mt3">Written about elsewhere</h3>
+    <div class="eco eco--press rv">
+      {{- range .Site.Data.ecosystem.press.articles }}
+      <a href="{{ .url }}"><b>{{ .outlet }}</b><span>{{ .title }}</span><em>{{ .what }}</em></a>
+      {{- end }}
+    </div>
+
     <p class="kicker rv mt3">Built on, integrated with, written about</p>
     <div class="posts">
       <a class="post rv" href="https://x.com/sozercan/status/1769769695081546236">
@@ -477,17 +491,6 @@
         <p>Oh, high there @LocalAI_API, nice to see a terminal based UI for ya! (it&#x27;s a WIP, but just wanted something cleaner then CURL calls)</p>
         <span class="post__go">On X, 2023 &#8599;</span></a>
     </div>
-    <div class="cards">
-      <a class="cd rv" href="https://modelslab.com/blog/audio-generation/parakeet-cpp-vs-whisper-self-hosted-asr-comparison-2026"><p class="cd__k">Coverage</p>
-        <h3>parakeet.cpp vs Whisper</h3><p>An independent comparison of self-hosted ASR options put parakeet.cpp against Whisper on accuracy and speed.</p>
-        <span class="cite">modelslab.com ↗</span></a>
-      <a class="cd rv" href="https://snailtext.app/blog/whisper-vs-parakeet-tdt/"><p class="cd__k">Coverage</p>
-        <h3>Roughly 4x faster on CPU</h3><p>A third-party benchmark measured Parakeet TDT against Whisper Small through whisper.cpp on the same machine.</p>
-        <span class="cite">snailtext.app ↗</span></a>
-      <a class="cd rv" href="https://github.com/mudler/LocalAI/graphs/contributors"><p class="cd__k">Contributors</p>
-        <h3>224 people have shipped code</h3><p>Backends, gallery entries, docs, translations and bug fixes, from people who are not on the team.</p>
-        <span class="cite">github.com ↗</span></a>
-    </div>
   </div>
 </section>
 
@@ -496,15 +499,17 @@
   <div class="shell">
     <div class="bars rv" aria-hidden="true"><i></i><i></i><i></i><i></i></div>
     <p class="kicker rv">From the team</p>
-    <h2 class="rv mt1" style="max-width:20ch">Every release gets written up and demonstrated.</h2>
-    <p class="lede rv mt2">A changelog tells you what moved. These posts show you what it does, with a recording you can watch and a command you can run.</p>
+    <h2 class="rv mt1" style="max-width:22ch">We publish the numbers, including the ones that cost us.</h2>
+    <p class="lede rv mt2">APEX takes a 35B model from 64.6 GB to 12.2 GB, and from 30.4 to 74.4 tokens a second. Perplexity goes from 6.537 to 7.088. That trade is in the post too, with the command that produced it.</p>
+    {{/* Pulled from the posts themselves. The cards used to be hand-written,
+         which is how one of them ended up advertising a post that did not
+         exist, and how all three linked to the index instead of the article. */}}
     <div class="cards">
-      <a class="cd rv" href="/blog/"><p class="cd__k">Release · v4.8.0</p><h3>What landed in LocalAI 4.8</h3>
-        <p>The audio.cpp backend, Valkey vector search, configurable VAE tiling, and a faster realtime path.</p><span class="cd__go">Read the post →</span></a>
-      <a class="cd rv" href="/blog/"><p class="cd__k">Engineering</p><h3>Porting vLLM to C++</h3>
-        <p>What paged attention looks like without a Python runtime, and what it cost us to get there.</p><span class="cd__go">Read the post →</span></a>
-      <a class="cd rv" href="/blog/"><p class="cd__k">Benchmarks</p><h3>How APEX beats Q8_0 at a third of the size</h3>
-        <p>Per-tensor, per-layer precision for mixture-of-experts models, measured against the alternatives.</p><span class="cd__go">Read the post →</span></a>
+      {{- range first 3 (where .Site.RegularPages "Section" "blog") }}
+      <a class="cd rv" href="{{ .RelPermalink }}">
+        <p class="cd__k">{{ .Date.Format "2 January 2006" }}</p><h3>{{ .Title }}</h3>
+        <p>{{ .Params.summary | truncate 155 }}</p><span class="cd__go">Read the post →</span></a>
+      {{- end }}
     </div>
   </div>
 </section>

website/layouts/partials/footer.html

@@ -9,6 +9,6 @@
       <div><h4>Community</h4><ul><li><a href="https://github.com/mudler/LocalAI">GitHub</a></li><li><a href="https://discord.gg/uJAeKSAGDy">Discord</a></li><li><a href="https://twitter.com/LocalAI_API">X</a></li><li><a href="https://huggingface.co/mudler">Hugging Face</a></li></ul></div>
       <div><h4>Support us</h4><ul><li><a href="https://github.com/sponsors/mudler">Sponsor</a></li><li><a href="https://github.com/mudler/LocalAI/graphs/contributors">Contributors</a></li><li><a href="/docs/">Contributing</a></li></ul></div>
     </div>
-    <div class="foot__n"><span>© 2026 LocalAI</span><span>MIT licence</span><span>Design mock, not a live page</span></div>
+    <div class="foot__n"><span>© 2026 LocalAI</span><span>MIT licence</span><span><a href="{{ .Site.Params.github }}">Source on GitHub</a></span></div>
   </div>
 </footer>

website/layouts/partials/nav.html

@@ -13,7 +13,7 @@
     <a href="{{ .Site.Params.docsURL }}">Docs</a>
   </nav>
   <div class="topright">
-    <a class="pill" href="{{ .Site.Params.github }}/stargazers">&#9733; {{ .Site.Params.stars }}</a>
+    <a class="pill" href="{{ .Site.Params.github }}">&#9733; {{ .Site.Params.stars }}</a>
     <a class="go-btn" href="{{ $home }}#start">Install</a>
   </div>
 </header>

website/static/css/site.css

@@ -288,6 +288,15 @@ h2{font-size:clamp(2.1rem,5vw,3.9rem)}
 .reel span::before{content:"/ ";color:var(--cyan)}
 @keyframes roll{to{transform:translateX(-50%)}}
 
+/* Integrations reel. Same motion as the engines reel, but the items are links,
+   so it stops on hover or keyboard focus and the names stay clickable. */
+.reel--int .reel__t{animation-duration:64s}
+.reel--int:hover .reel__t,.reel--int:focus-within .reel__t{animation-play-state:paused}
+.reel--int a{font-family:'Geist Mono',monospace;font-size:.78rem;color:var(--dim);white-space:nowrap;
+  transition:color .18s}
+.reel--int a::before{content:"/ ";color:var(--cyan)}
+.reel--int a:hover,.reel--int a:focus-visible{color:var(--ink)}
+
 /* apex */
 .tw{overflow-x:auto;margin-top:2.2rem;border:1px solid var(--p-line);border-radius:8px;background:#fff}
 table{border-collapse:collapse;width:100%;min-width:640px;font-variant-numeric:tabular-nums}
@@ -344,10 +353,16 @@ tbody tr:hover td{background:rgba(95,205,228,.10)}
   letter-spacing:-.02em;color:var(--cyan);font-variant-numeric:tabular-nums}
 .big span{font-family:'Geist Mono',monospace;font-size:.58rem;letter-spacing:.11em;
   text-transform:uppercase;color:var(--faint)}
-.tl{margin-top:2.6rem;border-top:1px solid var(--line2);overflow-x:auto}
-.tl__t{display:flex;gap:0;min-width:min-content;padding-top:1.4rem}
-.tl__i{flex:0 0 15rem;padding:0 1.3rem 0 0;position:relative}
-.tl__i::before{content:"";position:absolute;left:0;top:-1.4rem;width:7px;height:7px;border-radius:50%;
+/* Six 15rem columns need 90rem, so the old flex row scrolled sideways on any
+   normal laptop. It wraps into a grid instead, and the rule that carried the
+   dots moves from the container onto each item so a wrapped row still gets a
+   line above it. */
+.tl{margin-top:2.6rem}
+/* Zero column gap so the borders of adjacent items meet and the rule reads as
+   one continuous line; the items carry their own right padding instead. */
+.tl__t{display:grid;grid-template-columns:repeat(auto-fit,minmax(13.5rem,1fr));gap:1.7rem 0}
+.tl__i{padding:1.4rem 1.3rem 0 0;position:relative;border-top:1px solid var(--line2)}
+.tl__i::before{content:"";position:absolute;left:0;top:0;width:7px;height:7px;border-radius:50%;
   background:var(--cyan);transform:translateY(-50%) scale(0);transition:transform .45s cubic-bezier(.16,1,.3,1)}
 .in .tl__i::before{transform:translateY(-50%) scale(1)}
 .tl__i:nth-child(1)::before{transition-delay:.05s}.tl__i:nth-child(2)::before{transition-delay:.13s}
@@ -442,14 +457,16 @@ footer{background:var(--deep);border-top:1px solid var(--line2);padding:3rem 0 4
 .eco__note{color:var(--dim);font-size:.92rem;max-width:66ch;margin-top:.7rem}
 .eco__note a{color:var(--cyan);text-decoration:underline;text-underline-offset:.2rem}
 .eco__aside{color:var(--faint);font-size:.85rem;margin-top:1rem;max-width:66ch}
+.eco__aside a{color:var(--cyan);text-decoration:underline;text-underline-offset:.2rem}
+
+/* Employers are set as a running sentence, not a grid of pills, so the line
+   reads as a statement about people rather than a wall of customer logos. The
+   names take weight and the connective text stays dim, which lets the eye
+   scan the list without the paragraph turning into a badge rack. */
+.eco__names{color:var(--dim);font-size:1rem;line-height:1.75;max-width:62ch;margin-top:1rem}
+.eco__names b{color:var(--ink);font-weight:600}
 
 .eco{list-style:none;padding:0;margin:1.4rem 0 0}
-.eco--co{display:flex;flex-wrap:wrap;gap:.5rem}
-.eco--co li{display:flex;align-items:baseline;gap:.5rem;padding:.5rem .8rem;border-radius:999px;
-  border:1px solid var(--line);background:rgba(255,255,255,.028);transition:border-color .22s,background .22s}
-.eco--co li:hover{border-color:rgba(95,205,228,.5);background:rgba(95,205,228,.07)}
-.eco--co b{font-size:.9rem;font-weight:600;color:var(--ink)}
-.eco--co span{font-family:'Geist Mono',monospace;font-size:.6rem;color:var(--faint);white-space:nowrap}
 
 .eco--int{display:grid;gap:.8rem}
 @media(min-width:700px){.eco--int{grid-template-columns:repeat(2,1fr)}}