bots-garden/mini-me · 2f57ae2

⑂ 2f57ae2

🛟 Updated.

k33g committed 2026-10-26T16:00:29+01:00 Browse files

2f57ae2 parent: b859ec4

modified INSTALL.LINUX.md +1 -1 Viewed

@@ -2,7 +2,7 @@
2	2
3	3	```bash
4	4	# download the binary release in https://rickub.com/bots-garden/mini-me/releases
5		-VERSION=1.0.1
	5	+VERSION=1.0.2
6	6	case "$(uname -m)" in
7	7	x86_64) ARCH=amd64 ;;
8	8	aarch64\|arm64) ARCH=arm64 ;;

  ```bash
  # download the binary release in https://rickub.com/bots-garden/mini-me/releases
--VERSION=1.0.1
++VERSION=1.0.2
  case "$(uname -m)" in
    x86_64)        ARCH=amd64 ;;
    aarch64|arm64) ARCH=arm64 ;;

modified INSTALL.MACOS.md +1 -1 Viewed

@@ -2,7 +2,7 @@
2	2
3	3	```bash
4	4	# download the binary release in https://rickub.com/bots-garden/mini-me/releases
5		-VERSION=1.0.1
	5	+VERSION=1.0.2
6	6	curl -fsSLO "https://rickub.com/bots-garden/mini-me/releases/download/v${VERSION}/mm-${VERSION}-darwin-arm64"
7	7	chmod +x ./mm-${VERSION}-darwin-arm64
8	8	xattr -cr ./mm-${VERSION}-darwin-arm64

  ```bash
  # download the binary release in https://rickub.com/bots-garden/mini-me/releases
--VERSION=1.0.1
++VERSION=1.0.2
  curl -fsSLO "https://rickub.com/bots-garden/mini-me/releases/download/v${VERSION}/mm-${VERSION}-darwin-arm64"
  chmod +x ./mm-${VERSION}-darwin-arm64
  xattr -cr ./mm-${VERSION}-darwin-arm64

modified INSTALL.WINDOWS.md +1 -1 Viewed

@@ -4,7 +4,7 @@ In PowerShell (no administrator rights needed):
4	4
5	5	```powershell
6	6	# download the binary release in https://rickub.com/bots-garden/mini-me/releases
7		-$Version = "1.0.1"
	7	+$Version = "1.0.2"
8	8	$Arch = if ($env:PROCESSOR_ARCHITECTURE -eq "ARM64") { "arm64" } else { "amd64" }
9	9	$Asset = "mm-$Version-windows-$Arch.exe"
10	10	$Base = "https://rickub.com/bots-garden/mini-me/releases/download/v$Version"

  ```powershell
  # download the binary release in https://rickub.com/bots-garden/mini-me/releases
--$Version = "1.0.1"
++$Version = "1.0.2"
  $Arch = if ($env:PROCESSOR_ARCHITECTURE -eq "ARM64") { "arm64" } else { "amd64" }
  $Asset = "mm-$Version-windows-$Arch.exe"
  $Base = "https://rickub.com/bots-garden/mini-me/releases/download/v$Version"

modified README.md +11 -1 Viewed

@@ -32,7 +32,7 @@ mm --about # what it is, in one screen
32	32	```
33	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`.
	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).
36	36
37	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
@@ -124,6 +124,13 @@ Anything that speaks ACP can host `mm -acp` the same way: JetBrains IDEs (In
124	124	- Unload a model: `/unload [model]` frees a model from the server's memory — in the terminal, the window and an editor —, and the `unload_model` tool lets the agent do it itself, e.g. on another agent's model once it has answered; llmman, Ollama and llama-server in router mode. `unloadModels: false` turns both off. See [Free a model's memory](docs/en/how-to/unload-a-model.md) and `demos/unload-models/`.
125	125	- Search a documentation folder: `/docs <words>` searches the text files of the folders named in `docSearch.dirs` (`.md`, `.adoc`, `.txt`… — only the extensions listed) and returns the best passages with their `path:line` link, ranked with BM25 — no index, no model (`docSearch.searchDocs`); the `search_docs` tool lets the model do it before it answers (`docSearch.autoSearchDocs`); both off by default. See [Search a documentation folder](docs/en/how-to/search-the-docs.md) and `demos/docs-search/`.
126	126	- Search earlier sessions: with sessions on, `/memory <words>` searches the project's stored conversations (`sessions.searchMemory`), and the `search_memory` tool lets the model do it when a question refers to something decided before (`sessions.autoSearchMemory`); both off by default. The search matches words, not meanings. See [Search earlier sessions](docs/en/how-to/search-earlier-sessions.md) and `demos/memory-search/`.
	127	+- Decision models: small models that answer questions about a text — a choice, a yes/no, a score — in a fraction of a second, through `/v1/systemone` (llama-server, llmman, Ollama). An agent file with a `decision:` block is a decider: run it with `mm -p` from a script or a hook, let it pick the skill before each question (`skillRouting`), drop the tool groups a request does not need (`toolRouting`), or approve read-only commands from a `preToolCall` hook (`allow`). See [Ask a decision model](docs/en/how-to/ask-a-decision-model.md), [Decision models](docs/en/explanation/decision-models.md) and the `demos/decision-*` folders.
	128	+- Type while it answers: a message sent during a turn is queued and runs once the turn ends, in order — in the line mode and the window; `Esc` (window) or `/abort` stops the turn. See [the slash commands reference](docs/en/reference/slash-commands.md).
	129	+- Struggle signals: when the model loops, fails several tool calls in a row, breaks a tool call, stalls, runs out of turns or fills its context window, mm says so apart from the answer — a coloured badge in the window's footer, a line in the terminal, a paragraph in an editor. The window also shows the completion's duration (`showCompletionTime`). See [Struggling models](docs/en/explanation/struggling-models.md) and `demos/struggle-signals/`.
	130	+- Download the models at start-up: `autoPull: true` pulls the models the agent will use that the server does not have yet — its own, its `mmConfigs` agents', its routing deciders' — with the progress on screen (llmman, Ollama, Docker Model Runner; llama.cpp gets advice instead). See [Run mini-me with llmman](docs/en/how-to/run-with-llmman.md) and `demos/auto-pull/`.
	131	+- Models that take turns in memory: `unloadModels: true` on an `mmConfigs` entry unloads the asking agent's model before the hand-off and the asked agent's model after it, so two models are never loaded together. See [Free a model's memory](docs/en/how-to/unload-a-model.md) and `demos/coding-helpers-unload-option/`.
	132	+- Use mini-me from another program: drive `mm -acp` over ACP — `demo.acp.sdk/nodejs/minime.js` gives Node.js `complete`, `stream`, cancellation and a permission callback, with no dependency. See [`demo.acp.sdk/`](demo.acp.sdk/README.en.md).
	133	+- Test a model: `testing/` holds two benches run by mm itself — a coordinator agent gives small tasks to a candidate agent whose model is under test, checks each result with a command, and writes a Markdown report: the model as a working agent (`testing/model-check/`) and function calling alone, with tools declared in the agent file (`testing/function-calling/`). See [`testing/`](testing/README.en.md).
127	134	- Docker Sandboxes: the sandbox kit lives in its own repository, [mini-me-kit](https://rickub.com/bots-garden/mini-me-kit); `sbx/` explains how to use it (`sbx run …`), with two mixins (`go-toolchain`, `cli-tools`) and ready-made configurations — see `sbx/README.md` and [Run mini-me in a Docker Sandbox](docs/en/how-to/run-in-a-docker-sandbox.md).
128	135
129	136	## Demos
@@ -141,6 +148,9 @@ The `demos/` directory holds ready-made set-ups (most with a README explaining h
141	148	\| `demos/mini-mes/` \| small teams of agents (`riker` coordinating a specifier and a coder, `gopher` a Go specialist) \|
142	149	\| `demos/little-coder/` \| a Go + htmx web-app generator for a small local model (Mellum2 12B on llmman, 32 GB RAM): a tested starter, skills, `AGENTS.md`, measured results \|
143	150	\| `demos/team/` \| a team of four agents (lead, specifier, coder, tester) on one small model (Ornith 1.5 9B on llmman) building Go + htmx apps through spec and test files, with measured results \|
	151	+\| `demos/coding-helpers-unload-option/` \| the same team as `demos/coding-helpers/` with `unloadModels: true` on its `mmConfigs` entries instead of unload hooks: the two models never in memory together, measured on llmman \|
	152	+\| `demos/auto-pull/` \| `autoPull: true` with SmolLM2-135M: a model the server does not have is downloaded at start-up, with its progress; also a team, and a misspelt repository name \|
	153	+\| `demos/struggle-signals/` \| a fake OpenAI-compatible server and `run-all.sh` that trigger every struggle signal (loop, failed calls, broken call, stalled, max turns, context full…) without a real model \|
144	154	\| `demo.acp.sdk/` \| mini-me as a library from other languages, by driving `mm -acp` over ACP: `nodejs/minime.js` (ticket 167) — `Agent.start`, `complete`, `stream`, cancel with an `AbortSignal`, a permission callback; no dependency, 11 tests with a fake mm, four examples measured on llmman \|
145	155	\| `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:`) \|
146	156	\| `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 \|

  ```
  > `install.sh` works only on macOS and Linux
--Or download a binary from the [releases page](https://rickub.com/bots-garden/mini-me/releases) and put it on your `PATH`.
++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).
  Then pick a configuration file. Copy one to `agent.yaml` in your project and adjust the `model:` and `system:` keys to taste:
  - **Unload a model**: `/unload [model]` frees a model from the server's memory — in the terminal, the window and an editor —, and the `unload_model` tool lets the agent do it itself, e.g. on another agent's model once it has answered; llmman, Ollama and llama-server in router mode. `unloadModels: false` turns both off. See [Free a model's memory](docs/en/how-to/unload-a-model.md) and `demos/unload-models/`.
  - **Search a documentation folder**: `/docs <words>` searches the text files of the folders named in `docSearch.dirs` (`.md`, `.adoc`, `.txt`… — only the extensions listed) and returns the best passages with their `path:line` link, ranked with BM25 — no index, no model (`docSearch.searchDocs`); the `search_docs` tool lets the model do it before it answers (`docSearch.autoSearchDocs`); both off by default. See [Search a documentation folder](docs/en/how-to/search-the-docs.md) and `demos/docs-search/`.
  - **Search earlier sessions**: with sessions on, `/memory <words>` searches the project's stored conversations (`sessions.searchMemory`), and the `search_memory` tool lets the model do it when a question refers to something decided before (`sessions.autoSearchMemory`); both off by default. The search matches words, not meanings. See [Search earlier sessions](docs/en/how-to/search-earlier-sessions.md) and `demos/memory-search/`.
++- **Decision models**: small models that answer questions about a text — a choice, a yes/no, a score — in a fraction of a second, through `/v1/systemone` (llama-server, llmman, Ollama). An agent file with a `decision:` block is a decider: run it with `mm -p` from a script or a hook, let it pick the skill before each question (`skillRouting`), drop the tool groups a request does not need (`toolRouting`), or approve read-only commands from a `preToolCall` hook (`allow`). See [Ask a decision model](docs/en/how-to/ask-a-decision-model.md), [Decision models](docs/en/explanation/decision-models.md) and the `demos/decision-*` folders.
++- **Type while it answers**: a message sent during a turn is queued and runs once the turn ends, in order — in the line mode and the window; `Esc` (window) or `/abort` stops the turn. See [the slash commands reference](docs/en/reference/slash-commands.md).
++- **Struggle signals**: when the model loops, fails several tool calls in a row, breaks a tool call, stalls, runs out of turns or fills its context window, mm says so apart from the answer — a coloured badge in the window's footer, a line in the terminal, a paragraph in an editor. The window also shows the completion's duration (`showCompletionTime`). See [Struggling models](docs/en/explanation/struggling-models.md) and `demos/struggle-signals/`.
++- **Download the models at start-up**: `autoPull: true` pulls the models the agent will use that the server does not have yet — its own, its `mmConfigs` agents', its routing deciders' — with the progress on screen (llmman, Ollama, Docker Model Runner; llama.cpp gets advice instead). See [Run mini-me with llmman](docs/en/how-to/run-with-llmman.md) and `demos/auto-pull/`.
++- **Models that take turns in memory**: `unloadModels: true` on an `mmConfigs` entry unloads the asking agent's model before the hand-off and the asked agent's model after it, so two models are never loaded together. See [Free a model's memory](docs/en/how-to/unload-a-model.md) and `demos/coding-helpers-unload-option/`.
++- **Use mini-me from another program**: drive `mm -acp` over ACP — `demo.acp.sdk/nodejs/minime.js` gives Node.js `complete`, `stream`, cancellation and a permission callback, with no dependency. See [`demo.acp.sdk/`](demo.acp.sdk/README.en.md).
++- **Test a model**: `testing/` holds two benches run by mm itself — a coordinator agent gives small tasks to a candidate agent whose model is under test, checks each result with a command, and writes a Markdown report: the model as a working agent (`testing/model-check/`) and function calling alone, with tools declared in the agent file (`testing/function-calling/`). See [`testing/`](testing/README.en.md).
  - **Docker Sandboxes**: the sandbox kit lives in its own repository, [mini-me-kit](https://rickub.com/bots-garden/mini-me-kit); `sbx/` explains how to use it (`sbx run …`), with two mixins (`go-toolchain`, `cli-tools`) and ready-made configurations — see `sbx/README.md` and [Run mini-me in a Docker Sandbox](docs/en/how-to/run-in-a-docker-sandbox.md).
  ## Demos
  | `demos/mini-mes/` | small teams of agents (`riker` coordinating a specifier and a coder, `gopher` a Go specialist) |
  | `demos/little-coder/` | a Go + htmx web-app generator for a small local model (Mellum2 12B on llmman, 32 GB RAM): a tested starter, skills, `AGENTS.md`, measured results |
  | `demos/team/` | a team of four agents (lead, specifier, coder, tester) on one small model (Ornith 1.5 9B on llmman) building Go + htmx apps through spec and test files, with measured results |
++| `demos/coding-helpers-unload-option/` | the same team as `demos/coding-helpers/` with `unloadModels: true` on its `mmConfigs` entries instead of unload hooks: the two models never in memory together, measured on llmman |
++| `demos/auto-pull/` | `autoPull: true` with SmolLM2-135M: a model the server does not have is downloaded at start-up, with its progress; also a team, and a misspelt repository name |
++| `demos/struggle-signals/` | a fake OpenAI-compatible server and `run-all.sh` that trigger every struggle signal (loop, failed calls, broken call, stalled, max turns, context full…) without a real model |
  | `demo.acp.sdk/` | mini-me as a library from other languages, by driving `mm -acp` over ACP: `nodejs/minime.js` (ticket 167) — `Agent.start`, `complete`, `stream`, cancel with an `AbortSignal`, a permission callback; no dependency, 11 tests with a fake mm, four examples measured on llmman |
  | `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:`) |
  | `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 |

modified install.sh +1 -1 Viewed

@@ -4,7 +4,7 @@ set -euo pipefail
4	4	BINARY_NAME="mm"
5	5	INSTALL_DIR="/usr/local/bin"
6	6
7		-rm "${INSTALL_DIR}/mm"
	7	+rm -f "${INSTALL_DIR}/mm"
8	8
9	9	echo "Building ${BINARY_NAME}..."
10	10	go build -o "${BINARY_NAME}" .

  BINARY_NAME="mm"
  INSTALL_DIR="/usr/local/bin"
--rm "${INSTALL_DIR}/mm"
++rm -f "${INSTALL_DIR}/mm"
  echo "Building ${BINARY_NAME}..."
  go build -o "${BINARY_NAME}" .