{"id":31959440,"url":"https://github.com/huggingface/meshgen","last_synced_at":"2025-10-14T15:32:22.480Z","repository":{"id":264939285,"uuid":"872581121","full_name":"huggingface/meshgen","owner":"huggingface","description":"Use AI Agents directly in Blender.","archived":false,"fork":false,"pushed_at":"2025-04-14T20:00:02.000Z","size":16080,"stargazers_count":655,"open_issues_count":12,"forks_count":40,"subscribers_count":17,"default_branch":"main","last_synced_at":"2025-09-30T18:02:29.612Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/huggingface.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-10-14T17:28:53.000Z","updated_at":"2025-09-30T07:03:57.000Z","dependencies_parsed_at":"2025-04-01T16:39:12.441Z","dependency_job_id":"cabdd6a6-bace-4f45-9415-cf8f12ede591","html_url":"https://github.com/huggingface/meshgen","commit_stats":null,"previous_names":["dylanebert/meshgen","huggingface/meshgen"],"tags_count":7,"template":false,"template_full_name":null,"purl":"pkg:github/huggingface/meshgen","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huggingface%2Fmeshgen","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huggingface%2Fmeshgen/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huggingface%2Fmeshgen/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huggingface%2Fmeshgen/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/huggingface","download_url":"https://codeload.github.com/huggingface/meshgen/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huggingface%2Fmeshgen/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279019322,"owners_count":26086711,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-14T02:00:06.444Z","response_time":60,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-10-14T15:31:01.847Z","updated_at":"2025-10-14T15:32:22.472Z","avatar_url":"https://github.com/huggingface.png","language":"Python","funding_links":[],"categories":["MCP Servers for Creative Work"],"sub_categories":["3D \u0026 Game Engines"],"readme":"# MeshGen\n\nUse AI Agents to control Blender with natural language.\n\n![meshgen](docs/meshgen.gif)\n\n## Features\n\n-   Focused on AI as a tool, not replacement\n-   Multiple backend options:\n    -   Local inference with [llama.cpp](#local-backend) or [Ollama](#ollama)\n    -   Remote inference with [Hugging Face](#hugging-face), [Anthropic](#anthropic), or [OpenAI](#openai)\n-   Optional [LLaMA-Mesh](#llama-mesh) integration for local mesh understanding and generation\n-   Optional [Hyper3D](#hyper3d) integration for high-fidelity 3D mesh generation\n\n## Installation\n\n1. Go to the [Latest Release](https://github.com/huggingface/meshgen/releases/latest) page\n2. Download the addon ZIP file for your platform\n3. In Blender, go to `Edit` -\u003e `Preferences` -\u003e `Add-ons` -\u003e Top-Right Arrow -\u003e `Install from Disk...`\n4. Select the downloaded ZIP file\n\n## Setup\n\n1. In blender, go to `Edit` -\u003e `Preferences` -\u003e `Add-ons` -\u003e `meshgen`\n2. Select either [`Local`](#local-backend) or [`Remote`](#remote-backend) and follow instructions below\n\n### Local Backend\n\n![local-backend](docs/local.png)\n\nRun models free locally directly in Blender.\n\nOnly select this option if you:\n\n1. Have a powerful NVIDIA GPU with at least 8GB of VRAM\n2. Installed a `cuda` version of the addon during [Installation](#installation)\n3. Prefer running the model directly in Blender instead of a local [Ollama](#ollama) server\n\nTo set up the local backend, you can either:\n\n1. Click `Download Recommended Model` to download [Meta-Llama-3.1-8B-Instruct-GGUF](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF)\n2. Manually download a `.GGUF` model and put it in the models folder (located by clicking the folder icon)\n\n### Remote Backend\n\n![remote-backend](docs/remote.png)\n\nMeshGen supports a variety of remote backends.\n\n1. [Ollama](#ollama) to run models in a free local server\n2. [Hugging Face](#hugging-face), [Anthropic](#anthropic), or [OpenAI](#openai) to run powerful models via API\n\n[Hugging Face](#hugging-face) is recommended for most users, providing limited free use of powerful models.\n\n#### Ollama\n\nRun models free locally with an Ollama server.\n\n1. Install [Ollama](https://ollama.com/)\n2. Run `ollama serve` in the terminal\n3. Select `Ollama` in the `Provider` dropdown\n4. Enter your `Ollama` server endpoint and model name (the defaults should work for most users)\n\n#### Hugging Face\n\nRun a wide variety of models such as Llama, DeepSeek, Mistral, Qwen, and more via the Hugging Face API.\n\n1. Create an account on [Hugging Face](https://huggingface.co/)\n2. Go to [hf.co/settings/tokens](https://hf.co/settings/tokens) and create a new token\n3. Select `Hugging Face` in the `Provider` dropdown\n4. Enter your `Hugging Face` token in the `API Key` field\n5. Optionally, change the `Model ID` to the model you want to use (e.g. `meta-llama/Llama-3.3-70B-Instruct`)\n\n#### Anthropic\n\nRun Anthropic models (i.e. Claude) with the Anthropic API.\n\n1. Create an account on [Anthropic](https://console.anthropic.com/)\n2. Go to [console.anthropic.com/settings/keys](https://console.anthropic.com/settings/keys) and create a new key\n3. Select `Anthropic` in the `Provider` dropdown\n4. Enter your `Anthropic` key in the `API Key` field\n5. Optionally, change the `Model ID` to the model you want to use (e.g. `claude-3-5-sonnet-latest`)\n\n#### OpenAI\n\nRun OpenAI models (i.e. ChatGPT) with the OpenAI API.\n\n1. Create an account on [OpenAI](https://platform.openai.com/)\n2. Go to [platform.openai.com/api-keys](https://platform.openai.com/api-keys) and create a new secret key\n3. Select `OpenAI` in the `Provider` dropdown\n4. Enter your `OpenAI` secret key in the `API Key` field\n5. Optionally, change the `Model ID` to the model you want to use (e.g. `gpt-4o-mini`)\n\n## Optional Integrations\n\n![integrations](docs/integrations.png)\n\nTo enable optional integrations, go to `Edit` -\u003e `Preferences` -\u003e `Add-ons` -\u003e `meshgen` -\u003e `Integrations`.\n\nWhen these are enabled, the agent will automatically be given access to these tools, depending on the context.\n\n### LLaMA-Mesh\n\nUse [LlamaMesh](https://github.com/nv-tlabs/LLaMA-Mesh) local mesh understanding and generation.\n\nOnly select this option if you:\n\n1. Have a powerful NVIDIA GPU with at least 8GB of VRAM\n2. Installed a `cuda` version of the addon during [Installation](#installation)\n3. Are using a remote API backend (e.g. [Hugging Face](#hugging-face), [Anthropic](#anthropic), or [OpenAI](#openai)), as LLaMA-Mesh will load locally on your machine\n\nTo enable LLaMA-Mesh, click `Load LLama-Mesh` and wait for the model to load.\n\n### Hyper3D\n\nUse [Hyper3D](https://hyper3d.ai/) for high-fidelity 3D mesh generation.\n\nTo enable:\n\n1. Check `Enable Hyper3D`\n2. Enter your Hyper3D API key in the `API Key` field (free use is currently provided with the `awesomemcp` key)\n\nThis may take several minutes per mesh.\n\n## Usage\n\n-   Press `N` -\u003e `MeshGen` (or `View` -\u003e `Sidebar` -\u003e Select the `MeshGen` tab)\n-   Enter a prompt, for example: `Create a snowman`\n-   Click `Submit`\n\n## Troubleshooting\n\n-   Find errors in the console:\n    -   Windows: In Blender, go to `Window` -\u003e `Toggle System Console`\n    -   Mac/Linux: Launch Blender from the terminal\n-   Report errors in [Issues](https://github.com/huggingface/meshgen/issues)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhuggingface%2Fmeshgen","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhuggingface%2Fmeshgen","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhuggingface%2Fmeshgen/lists"}