Skip to content

armgit / ruflo

Public Imported from GitHub
0

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

docs: surface "any model, local or remote" + ruvLLM in Web UI section

Reuven357338ec3461
diff --git a/README.md b/README.md
index 5c79e544df..f97914f021 100644
--- a/README.md
+++ b/README.md
@@ -187,7 +187,8 @@ claude mcp add ruflo -- npx -y @claude-flow/cli@latest
| | What it is | Why it matters |
|---|------------|----------------|
-| 🧠 | **6 frontier models** | Qwen 3.6 Max (default), Claude Sonnet 4.6, Claude Haiku 4.5, Gemini 2.5 Pro, Gemini 2.5 Flash, GPT-4o β€” switch any time. One key (OpenRouter) covers them all. |
+| 🧠 | **Any model, local or remote** | 6 curated frontier models out-of-the-box β€” Qwen 3.6 Max (default), Claude Sonnet 4.6, Claude Haiku 4.5, Gemini 2.5 Pro, Gemini 2.5 Flash, GPT-4o β€” via OpenRouter. Add your own: any OpenAI-compatible endpoint (vLLM, Ollama, LM Studio, Together, Groq, self-hosted). |
+| 🦾 | **ruvLLM self-learning AI** | Native support for [ruvLLM](https://github.com/ruvnet/ruvllm) β€” RuFlo's self-improving local model layer. Routes to MicroLoRA adapters, learns from your trajectories via SONA, and stays on your machine. Pair with the cloud models or run fully offline. |
| πŸ› οΈ | **~210 tools, ready to call** | 5 server groups (Core, Intelligence, Agents, Memory, DevTools) plus an 18-tool gallery that runs entirely in your browser β€” works offline. |
| ⚑ | **Tools run in parallel** | One model response can fire 4–6+ tools at the same time. The UI shows them as cards with a *Step 1 β€” 2 tools completed* badge so you can see exactly what ran. |
| πŸ’Ύ | **Memory that sticks** | Say *"remember my favorite color is indigo"* and ask weeks later β€” RuFlo recalls it. Backed by AgentDB + HNSW vector search (β‰₯150Γ— faster than brute force). |
diff --git a/ruflo/src/ruvocal/src/lib/components/RufloHelpModal.svelte b/ruflo/src/ruvocal/src/lib/components/RufloHelpModal.svelte
index 9614ec0cc9..a5a6a98df1 100644
--- a/ruflo/src/ruvocal/src/lib/components/RufloHelpModal.svelte
+++ b/ruflo/src/ruvocal/src/lib/components/RufloHelpModal.svelte
@@ -255,7 +255,11 @@
</tbody>
</table>
</div>
- <p class="mt-2 text-[11px] text-gray-500 dark:text-gray-400">All models route through OpenRouter. Switch any time via <strong>Models</strong> in the sidebar.</p>
+ <p class="mt-2 text-[11px] text-gray-500 dark:text-gray-400">Cloud models route through OpenRouter β€” switch any time via <strong>Models</strong> in the sidebar.</p>
+ <div class="mt-3 rounded-lg border border-emerald-300/40 bg-emerald-50/50 px-3 py-2 text-xs dark:border-emerald-700/40 dark:bg-emerald-900/10">
+ <p class="font-semibold text-emerald-900 dark:text-emerald-200">🦾 Any model β€” including local + self-learning</p>
+ <p class="mt-1 text-emerald-900/80 dark:text-emerald-200/80">RuFlo speaks any OpenAI-compatible endpoint: vLLM, Ollama, LM Studio, Together, Groq, or self-hosted. Native support for <a href="https://github.com/ruvnet/ruvllm" target="_blank" rel="noopener" class="underline">ruvLLM</a> β€” RuFlo's self-improving local model layer with MicroLoRA adapters that learn from your trajectories via SONA. Pair cloud + local, or run fully offline.</p>
+ </div>
</section>
<section class="mb-6">