miii-agent 0.1.13 → 0.1.15

package/README.md

@@ -16,7 +16,7 @@
   <a href="https://ollama.com"><img src="https://img.shields.io/badge/powered%20by-Ollama-black" alt="powered by Ollama"></a>
 </p>
 
-miii is a local-first AI coding agent that lives in your terminal. Powered by [Ollama](https://ollama.com), it reads your code, writes features, runs tests, and fixes bugs — entirely on your hardware, at native speed.
+miii is a local-first AI coding agent that lives in your terminal. Powered by [Ollama](https://ollama.com) — or any OpenAI-compatible local server like [llama.cpp](https://github.com/ggml-org/llama.cpp) and [LM Studio](https://lmstudio.ai) — it reads your code, writes features, runs tests, and fixes bugs entirely on your hardware, at native speed.
 
 ---
 
@@ -48,7 +48,7 @@ Most AI coding tools are wrappers around cloud APIs. They are slow, expensive, a
 
 miii flips the script:
 
-- **Absolute Privacy** — Powered by Ollama. Your code stays on your disk, period.
+- **Absolute Privacy** — Powered by Ollama, llama.cpp, or any local OpenAI-compatible server. Your code stays on your disk, period.
 - **Zero Friction** — No API keys, no billing, no accounts. Just `miii`.
 - **True Agency** — miii doesn't just chat; it decomposes problems, invokes tools, and verifies results like a senior engineer.
 - **Native Performance** — No network round-trips. Latency is limited by your GPU, not a CDN.
@@ -197,6 +197,35 @@ Settings live in `~/.miii/config.json` and are created on first run.
 | `ollamaHost` | Ollama API endpoint | URL string |
 | `effort` | Controls temperature & limits | `low` \| `medium` \| `high` |
 
+### Other Local Backends
+
+Ollama is the default, but miii talks to any **OpenAI-compatible** local server — so you can run [llama.cpp](https://github.com/ggml-org/llama.cpp) or [LM Studio](https://lmstudio.ai) instead. Your code still never leaves your machine.
+
+Start `llama-server` (ships with llama.cpp), then point a named provider at it:
+
+```bash
+llama-server -m ./qwen2.5-coder-14b.gguf --port 8080
+```
+
+```json
+{
+  "model": "qwen2.5-coder-14b",
+  "provider": "llamacpp",
+  "providers": {
+    "llamacpp": { "type": "openai", "baseUrl": "http://localhost:8080" }
+  }
+}
+```
+
+| Field | Description | Values |
+|-------|-------------|--------|
+| `provider` | Active provider name (keys into `providers`) | e.g. `ollama`, `llamacpp` |
+| `providers.<name>.type` | Wire protocol | `ollama` \| `openai` |
+| `providers.<name>.baseUrl` | Server endpoint | URL string |
+| `providers.<name>.apiKey` | Optional bearer token | string |
+
+Switch the active provider at launch with `miii --provider llamacpp`. Any `openai`-type provider on a `localhost` URL counts as local — no key, no cloud.
+
 ---
 
 ## System Architecture