| @@ -32,7 +32,7 @@ mm --about # what it is, in one screen |
| 32 | ``` | 32 | ``` |
| 33 | > `install.sh` works only on macOS and Linux | 33 | > `install.sh` works only on macOS and Linux |
| 34 | | 34 | |
| 35 | -Or download a binary from the [releases page](https://rickub.com/bots-garden/mini-me/releases) and put it on your `PATH` — step by step for [macOS](INSTALL.MACOS.md), [Linux](INSTALL.LINUX.md) and [Windows](INSTALL.WINDOWS.md). | 35 | +Or download a binary from the [releases page](https://rickub.com/bots-garden/mini-me/releases) and put it on your `PATH` — step by step for [macOS](INSTALL.MACOS.md), [Linux](INSTALL.LINUX.md) and [Windows](INSTALL.WINDOWS.md). From v1.0.5, the macOS binary is signed with a Developer ID and notarized by Apple: downloaded with a browser, it runs without a quarantine step. |
| 36 | | 36 | |
| 37 | Then pick a configuration file. Copy one to `agent.yaml` in your project and adjust the `model:` and `system:` keys to taste: | 37 | Then pick a configuration file. Copy one to `agent.yaml` in your project and adjust the `model:` and `system:` keys to taste: |
| 38 | | 38 | |
| @@ -156,6 +156,7 @@ The `demos/` directory holds ready-made set-ups (most with a README explaining h |
| 156 | | `demo.acp.sdk/` | mini-me as a library from other languages, by driving `mm -acp` over ACP — four clients with the same API (start, complete, stream, cancel, permission callback), four examples and tests against a fake mm each: `nodejs/` (ticket 167, no dependency), `nodejs-sdk/` (ticket 188, official ACP TypeScript SDK), `go/` (ticket 168, package `minime`), `kotlin/` (ticket 187, official ACP Kotlin SDK); see [demo.acp.sdk/README.en.md](demo.acp.sdk/README.en.md) | | 156 | | `demo.acp.sdk/` | mini-me as a library from other languages, by driving `mm -acp` over ACP — four clients with the same API (start, complete, stream, cancel, permission callback), four examples and tests against a fake mm each: `nodejs/` (ticket 167, no dependency), `nodejs-sdk/` (ticket 188, official ACP TypeScript SDK), `go/` (ticket 168, package `minime`), `kotlin/` (ticket 187, official ACP Kotlin SDK); see [demo.acp.sdk/README.en.md](demo.acp.sdk/README.en.md) | |
| 157 | | `testing/` | model testers run by mm itself: a coordinator (Gemma 4 12B) follows a skill, gives small tasks to a `candidate` agent whose model is under test (Qwen3.5 4B for model-check, Luciole 1B for function-calling), checks each result with a command and writes a Markdown report — `model-check/` (tool calls, exact instructions, Go code that must run, several steps) and `function-calling/` (only tools declared in the candidate's `tools:`) | | 157 | | `testing/` | model testers run by mm itself: a coordinator (Gemma 4 12B) follows a skill, gives small tasks to a `candidate` agent whose model is under test (Qwen3.5 4B for model-check, Luciole 1B for function-calling), checks each result with a command and writes a Markdown report — `model-check/` (tool calls, exact instructions, Go code that must run, several steps) and `function-calling/` (only tools declared in the candidate's `tools:`) | |
| 158 | | `demos/dev.team/` | a team of five agents for a 32 GB laptop (ticket 152): a Qwen3.5 4B coordinator hands each request to a reformulator, a coder, a reviewer or a tutor (Gemma 4 12B, Mellum2 12B); hooks keep one model in memory at a time; measured: bug fixes, lessons and reviews work, new features not yet | | 158 | | `demos/dev.team/` | a team of five agents for a 32 GB laptop (ticket 152): a Qwen3.5 4B coordinator hands each request to a reformulator, a coder, a reviewer or a tutor (Gemma 4 12B, Mellum2 12B); hooks keep one model in memory at a time; measured: bug fixes, lessons and reviews work, new features not yet | |
| | 159 | +| `demos/learning-rust/` | Tuto, an agent that answers with mini tutorials (Mellum2 12B on llmman), searching nine Ratatui tutorials (Rust terminal UIs) before it answers, with rust-analyzer for `lsp`; run in a Docker Sandbox with the Rust toolchain and opened in Zed over SSH (`start-zed.sh`, `stop-zed.sh`), the agent file mounted read-only | |
| 159 | | `demos/blog-team/` | the smallest team: a lead, a coder and a reviewer in 75 lines of YAML, one model (Mellum2 12B Q8_0 on llmman), written for a blog post | | 160 | | `demos/blog-team/` | the smallest team: a lead, a coder and a reviewer in 75 lines of YAML, one model (Mellum2 12B Q8_0 on llmman), written for a blog post | |
| 160 | | `demos/translator/` | a French ↔ English translator (Gemma 4 E4B on llmman): `AGENTS.md` for the style, skills for technical texts, e-mails and idioms, `$styles` for professional / informal / Slack versions, `translate.sh` for files | | 161 | | `demos/translator/` | a French ↔ English translator (Gemma 4 E4B on llmman): `AGENTS.md` for the style, skills for technical texts, e-mails and idioms, `$styles` for professional / informal / Slack versions, `translate.sh` for files | |
| 161 | | `demos/qwen-style/` | a general coding agent whose system prompt follows Qwen Code's, adapted to mm's tools, in three configurations on llmman: Qwen3.8 27B, Qwen3-Coder-Next, Qwen3.6 35B-A3B — Qwen Code's `new-app` and `simplify` skills, measured results | | 162 | | `demos/qwen-style/` | a general coding agent whose system prompt follows Qwen Code's, adapted to mm's tools, in three configurations on llmman: Qwen3.8 27B, Qwen3-Coder-Next, Qwen3.6 35B-A3B — Qwen Code's `new-app` and `simplify` skills, measured results | |