From 5ba8a4422aaabe7ff20f15ff86bbc6e5d0a91249 Mon Sep 17 00:00:00 2001 From: Sweaterdog Date: Thu, 26 Mar 2026 02:17:38 -0700 Subject: [PATCH 1/7] Revise local model usage instructions in README Updated local model recommendations and installation instructions. --- README.md | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 5c768a38d..0fdc0250b 100644 --- a/README.md +++ b/README.md @@ -81,11 +81,8 @@ You can configure the agent's name, model, and prompts in their profile like `an For more comprehensive model configuration and syntax, see [Model Specifications](#model-specifications). -For local models we support [ollama](https://ollama.com/) and we provide our own finetuned models for you to use. -To install our models, install ollama and run the following terminal command: -```bash -ollama pull sweaterdog/andy-4:micro-q8_0 && ollama pull embeddinggemma -``` +For local models, we recommend you use **LM Studio** for the Andy series of models. +Please see our [huggingface page for more info.](https://huggingface.co/collections/Mindcraft-CE) ## Online Servers To connect to online servers your bot will need an official Microsoft/Minecraft account. You can use your own personal one, but will need another account if you want to connect too and play with it. To connect, change these lines in `settings.js`: From eebd757b44d307487ce5cc026d930d55fe355304 Mon Sep 17 00:00:00 2001 From: Sweaterdog Date: Thu, 26 Mar 2026 02:21:04 -0700 Subject: [PATCH 2/7] Delete profiles/andy-4-reasoning.json --- profiles/andy-4-reasoning.json | 14 -------------- 1 file changed, 14 deletions(-) delete mode 100644 profiles/andy-4-reasoning.json diff --git a/profiles/andy-4-reasoning.json b/profiles/andy-4-reasoning.json deleted file mode 100644 index f6e2939ea..000000000 --- a/profiles/andy-4-reasoning.json +++ /dev/null @@ -1,14 +0,0 @@ -{ - "name": "andy_4_thinking", - - "model": "ollama/sweaterdog/andy-4:micro-q8_0", - - "conversing": "You are a playful Minecraft bot named $NAME that can converse with players, see, move, mine, build, and interact with the world by using commands.\n$SELF_PROMPT Act human-like as if you were a typical Minecraft player, rather than an AI. Be very brief in your responses, don't apologize constantly, don't give instructions or make lists unless asked, and don't refuse requests. Think in high amounts before responding. Don't pretend to act, use commands immediately when requested. Do NOT say this: 'Sure, I've stopped.', instead say this: 'Sure, I'll stop. !stop'. Do NOT say this: 'On my way! Give me a moment.', instead say this: 'On my way! !goToPlayer(\"playername\", 3)'. Respond only as $NAME, never output '(FROM OTHER BOT)' or pretend to be someone else. If you have nothing to say or do, respond with an just a tab '\t'. This is extremely important to me, take a deep breath and have fun :)\nSummarized memory:'$MEMORY'\n$STATS\n$INVENTORY\n$COMMAND_DOCS\n$EXAMPLES\nReason before responding. Conversation Begin:", - - "coding": "You are an intelligent mineflayer bot $NAME that plays minecraft by writing javascript codeblocks. Given the conversation, use the provided skills and world functions to write a js codeblock that controls the mineflayer bot ``` // using this syntax ```. The code will be executed and you will receive it's output. If an error occurs, write another codeblock and try to fix the problem. Be maximally efficient, creative, and correct. Be mindful of previous actions. Do not use commands !likeThis, only use codeblocks. The code is asynchronous and MUST USE AWAIT for all async function calls, and must contain at least one await. You have `Vec3`, `skills`, and `world` imported, and the mineflayer `bot` is given. Do not import other libraries. Think deeply before responding. Do not use setTimeout or setInterval. Do not speak conversationally, only use codeblocks. Do any planning in comments. This is extremely important to me, think step-by-step, take a deep breath and good luck! \n$SELF_PROMPT\nSummarized memory:'$MEMORY'\n$STATS\n$INVENTORY\n$CODE_DOCS\n$EXAMPLES\nConversation:", - - "saving_memory": "You are a minecraft bot named $NAME that has been talking and playing minecraft by using commands. Update your memory by summarizing the following conversation and your old memory in your next response. Prioritize preserving important facts, things you've learned, useful tips, and long term reminders. Do Not record stats, inventory, or docs! Only save transient information from your chat history. You're limited to 500 characters, so be extremely brief, think about what you will summarize before responding, minimize words, and provide your summarization in Chinese. Compress useful information. \nOld Memory: '$MEMORY'\nRecent conversation: \n$TO_SUMMARIZE\nSummarize your old memory and recent conversation into a new memory, and respond only with the unwrapped memory text: ", - - "bot_responder": "You are a minecraft bot named $NAME that is currently in conversation with another AI bot. Both of you can take actions with the !command syntax, and actions take time to complete. You are currently busy with the following action: '$ACTION' but have received a new message. Decide whether to 'respond' immediately or 'ignore' it and wait for your current action to finish. Be conservative and only respond when necessary, like when you need to change/stop your action, or convey necessary information. Example 1: You:Building a house! !newAction('Build a house.').\nOther Bot: 'Come here!'\nYour decision: ignore\nExample 2: You:Collecting dirt !collectBlocks('dirt',10).\nOther Bot: 'No, collect some wood instead.'\nYour decision: respond\nExample 3: You:Coming to you now. !goToPlayer('billy',3).\nOther Bot: 'What biome are you in?'\nYour decision: respond\nActual Conversation: $TO_SUMMARIZE\nDecide by outputting ONLY 'respond' or 'ignore', nothing else. Your decision:" - -} From c6acdf43f6336b7e61701fb3280c1c3714058b82 Mon Sep 17 00:00:00 2001 From: Sweaterdog Date: Thu, 26 Mar 2026 02:22:50 -0700 Subject: [PATCH 3/7] Update profile name and model structure for andy-4.2 --- profiles/andy-4.2.json | 9 +++++++++ profiles/andy-4.json | 7 ------- 2 files changed, 9 insertions(+), 7 deletions(-) create mode 100644 profiles/andy-4.2.json delete mode 100644 profiles/andy-4.json diff --git a/profiles/andy-4.2.json b/profiles/andy-4.2.json new file mode 100644 index 000000000..dd77b283d --- /dev/null +++ b/profiles/andy-4.2.json @@ -0,0 +1,9 @@ +{ + "name": "andy_4.2", + + "model": { + "api": "openai", + "model": "andy-4.2", + "url": "http://127.0.0.1:1234/v1" + } +} diff --git a/profiles/andy-4.json b/profiles/andy-4.json deleted file mode 100644 index 2048a80d9..000000000 --- a/profiles/andy-4.json +++ /dev/null @@ -1,7 +0,0 @@ -{ - "name": "andy_4", - - "model": "ollama/sweaterdog/andy-4:micro-q8_0", - - "embedding": "ollama" -} From 6d770243da73caf5a58b4ab88a1035b8e5fa3f65 Mon Sep 17 00:00:00 2001 From: Sweaterdog Date: Thu, 26 Mar 2026 02:23:13 -0700 Subject: [PATCH 4/7] Update profile reference in settings.js --- settings.js | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/settings.js b/settings.js index e59457db6..b6724316b 100644 --- a/settings.js +++ b/settings.js @@ -20,7 +20,7 @@ const settings = { // "./profiles/mistral.json", // "./profiles/deepseek.json", // "./profiles/mercury.json", - // "./profiles/andy-4.json", // Supports up to 75 messages! + // "./profiles/andy-4.2.json", // using more than 1 profile requires you to /msg each bot indivually // individual profiles override values from the base profile From d18647c7350f0d08a95ab427829133abab83f159 Mon Sep 17 00:00:00 2001 From: Sweaterdog Date: Thu, 26 Mar 2026 02:24:12 -0700 Subject: [PATCH 5/7] Update recommendation for local models usage Added a note to avoid using Ollama with local models. --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 0fdc0250b..479b050b2 100644 --- a/README.md +++ b/README.md @@ -81,7 +81,7 @@ You can configure the agent's name, model, and prompts in their profile like `an For more comprehensive model configuration and syntax, see [Model Specifications](#model-specifications). -For local models, we recommend you use **LM Studio** for the Andy series of models. +For local models, we recommend you use **LM Studio** for the Andy series of models. Ollama breaks current models, and should be avoided. Please see our [huggingface page for more info.](https://huggingface.co/collections/Mindcraft-CE) ## Online Servers From bbeb003d45d3b019204610012917372ad1ac7c3f Mon Sep 17 00:00:00 2001 From: Sweaterdog Date: Sun, 29 Mar 2026 22:45:31 -0700 Subject: [PATCH 6/7] Update profiles/andy-4.2.json Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --- profiles/andy-4.2.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/profiles/andy-4.2.json b/profiles/andy-4.2.json index dd77b283d..e6e68f927 100644 --- a/profiles/andy-4.2.json +++ b/profiles/andy-4.2.json @@ -1,5 +1,5 @@ { - "name": "andy_4.2", + "name": "andy_4_2", "model": { "api": "openai", From 8b7a5939d44d1148c6d647cbbf4be63940c6fa09 Mon Sep 17 00:00:00 2001 From: riqvip <95001376+riqvip@users.noreply.github.com> Date: Sun, 3 May 2026 15:47:33 -0700 Subject: [PATCH 7/7] Update andy-4.2.json --- profiles/andy-4.2.json | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/profiles/andy-4.2.json b/profiles/andy-4.2.json index e6e68f927..51e298259 100644 --- a/profiles/andy-4.2.json +++ b/profiles/andy-4.2.json @@ -1,9 +1,11 @@ { "name": "andy_4_2", - "model": { - "api": "openai", - "model": "andy-4.2", - "url": "http://127.0.0.1:1234/v1" + "api": "lmstudio", + "model": "andy-4.2" + }, + "embedding": { + "api": "lmstudio", + "model": "text-embedding-nomic-embed-text-v1.5" } }