The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across disciplines: CAD, circuits, robots, games and music.
TypeScript 3d-modelingagent-frameworkagent-harnessai-agentscadclaude-codecodexcoding-agentsdeveloper-toolsesp32game-developmentmcp-servermulti-agentopen-hardwareopencodeopenharnesspcbroboticsterminaltmux
{
"retrieved_at": "2026-09-20T01:30:33.007932+00:00",
"source": "GitHub REST API; stars are an interest proxy, not active user counts",
"repositories": [
{
"full_name": "ollama/ollama",
"html_url": "https://github.com/ollama/ollama",
"description": "Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.",
"stargazers_count": 181281,
"forks_count": 17939,
"created_at": "2023-06-26T19:39:32Z",
"pushed_at": "2026-09-19T20:41:40Z",
"updated_at": "2026-09-20T01:15:15Z",
"archived": false,
"default_branch": "main",
"license": "MIT"
},
{
"full_name": "ggml-org/llama.cpp",
"html_url": "https://github.com/ggml-org/llama.cpp",
"description": "LLM inference in C/C++",
"stargazers_count": 128863,
"forks_count": 23461,
"created_at": "2023-03-10T18:58:00Z",
"pushed_at": "2026-09-20T00:31:42Z",
"updated_at": "2026-09-20T01:16:48Z",
"archived": false,
"default_branch": "master",
"license": "MIT"
},
{
"full_name": "vllm-project/vllm",
"html_url": "https://github.com/vllm-project/vllm",
"description": "A high-throughput and memory-efficient inference and serving engine for LLMs",
"stargazers_count": 92191,
"forks_count": 22423,
"created_at": "2023-02-09T11:23:20Z",
"pushed_at": "2026-09-20T00:16:45Z",
"updated_at": "2026-09-20T01:11:41Z",
"archived": false,
"default_branch": "main",
"license": "Apache-2.0"
},
{
"full_name": "sgl-project/sglang",
"html_url": "https://github.com/sgl-project/sglang",
"description": "SGLang is a high-performance serving framework for large language models and multimodal models.",
"stargazers_count": 36178,
"forks_count": 8993,
"created_at": "2024-01-08T04:15:52Z",
"pushed_at": "2026-09-20T01:30:25Z",
"updated_at": "2026-09-20T01:17:33Z",
"archived": false,
"default_branch": "main",
"license": "Apache-2.0"
},
{
"full_name": "ml-explore/mlx",
"html_url": "https://github.com/ml-explore/mlx",
"description": "MLX: An array framework for Apple silicon",
"stargazers_count": 28484,
"forks_count": 2267,
"created_at": "2023-11-28T23:33:45Z",
"pushed_at": "2026-09-17T21:11:19Z",
"updated_at": "2026-09-20T00:41:54Z",
"archived": false,
"default_branch": "main",
"license": "MIT"
},
{
"full_name": "ml-explore/mlx-lm",
"html_url": "https://github.com/ml-explore/mlx-lm",
"description": "Run LLMs with MLX",
"stargazers_count": 7069,
"forks_count": 1059,
"created_at": "2025-03-11T16:38:30Z",
"pushed_at": "2026-09-18T15:27:36Z",
"updated_at": "2026-09-19T23:04:04Z",
"archived": false,
"default_branch": "main",
"license": "MIT"
},
{
"full_name": "jundot/omlx",
"html_url": "https://github.com/jundot/omlx",
"description": "LLM inference server with continuous batching & SSD caching for Apple Silicon \u2014 managed from the macOS menu bar",
"stargazers_count": 21930,
"forks_count": 1899,
"created_at": "2026-02-13T14:13:27Z",
"pushed_at": "2026-09-19T13:50:34Z",
"updated_at": "2026-09-20T00:47:03Z",
"archived": false,
"default_branch": "main",
"license": "Apache-2.0"
},
{
"full_name": "exo-explore/exo",
"html_url": "https://github.com/exo-explore/exo",
"description": "Run frontier AI locally.",
"stargazers_count": 47531,
"forks_count": 3527,
"created_at": "2024-06-24T18:36:22Z",
"pushed_at": "2026-08-25T18:59:53Z",
"updated_at": "2026-09-20T00:54:13Z",
"archived": false,
"default_branch": "main",
"license": "Apache-2.0"
},
{
"full_name": "waybarrios/vllm-mlx",
"html_url": "https://github.com/waybarrios/vllm-mlx",
"description": "High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.",
"stargazers_count": 1587,
"forks_count": 222,
"created_at": "2025-12-06T18:26:08Z",
"pushed_at": "2026-09-19T18:11:07Z",
"updated_at": "2026-09-19T18:11:11Z",
"archived": false,
"default_branch": "main",
"license": "Apache-2.0"
},
{
"full_name": "lemonade-sdk/lemonade",
"html_url": "https://github.com/lemonade-sdk/lemonade",
"description": "Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk",
"stargazers_count": 5748,
"forks_count": 505,
"created_at": "2025-05-15T19:17:39Z",
"pushed_at": "2026-09-19T10:27:47Z",
"updated_at": "2026-09-19T22:14:42Z",
"archived": false,
"default_branch": "main",
"license": "Apache-2.0"
},
{
"full_name": "EricLBuehler/mistral.rs",
"html_url": "https://github.com/EricLBuehler/mistral.rs",
"description": "Fast, flexible LLM inference",
"stargazers_count": 7709,
"forks_count": 710,
"created_at": "2024-02-26T22:30:06Z",
"pushed_at": "2026-09-08T03:18:32Z",
"updated_at": "2026-09-20T00:58:27Z",
"archived": false,
"default_branch": "master",
"license": "MIT"
},
{
"full_name": "qualcomm/GenieX",
"html_url": "https://github.com/qualcomm/GenieX",
"description": "Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code",
"stargazers_count": 8380,
"forks_count": 1054,
"created_at": "2024-08-16T20:13:07Z",
"pushed_at": "2026-09-18T18:27:43Z",
"updated_at": "2026-09-19T03:57:23Z",
"archived": false,
"default_branch": "main",
"license": "BSD-3-Clause"
},
{
"full_name": "mudler/LocalAI",
"html_url": "https://github.com/mudler/LocalAI",
"description": "LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.",
"stargazers_count": 49177,
"forks_count": 4458,
"created_at": "2023-03-18T22:58:02Z",
"pushed_at": "2026-09-20T00:05:21Z",
"updated_at": "2026-09-20T01:18:26Z",
"archived": false,
"default_branch": "master",
"license": "MIT"
},
{
"full_name": "janhq/jan",
"html_url": "https://github.com/janhq/jan",
"description": "Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.",
"stargazers_count": 44564,
"forks_count": 3040,
"created_at": "2023-08-17T02:17:10Z",
"pushed_at": "2026-09-19T04:55:33Z",
"updated_at": "2026-09-20T00:37:40Z",
"archived": false,
"default_branch": "main",
"license": "NOASSERTION"
},
{
"full_name": "mozilla-ai/llamafile",
"html_url": "https://github.com/mozilla-ai/llamafile",
"description": "Distribute and run LLMs with a single file.",
"stargazers_count": 25997,
"forks_count": 1598,
"created_at": "2023-09-10T21:12:32Z",
"pushed_at": "2026-09-16T09:14:28Z",
"updated_at": "2026-09-19T21:45:35Z",
"archived": false,
"default_branch": "main",
"license": "NOASSERTION"
},
{
"full_name": "mlc-ai/mlc-llm",
"html_url": "https://github.com/mlc-ai/mlc-llm",
"description": "Universal LLM Deployment Engine with ML Compilation",
"stargazers_count": 23169,
"forks_count": 2138,
"created_at": "2023-04-29T01:59:25Z",
"pushed_at": "2026-08-17T20:50:06Z",
"updated_at": "2026-09-20T01:24:05Z",
"archived": false,
"default_branch": "main",
"license": "Apache-2.0"
},
{
"full_name": "mostlygeek/llama-swap",
"html_url": "https://github.com/mostlygeek/llama-swap",
"description": "Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc",
"stargazers_count": 5700,
"forks_count": 472,
"created_at": "2024-10-04T04:06:01Z",
"pushed_at": "2026-09-19T22:01:33Z",
"updated_at": "2026-09-20T01:13:11Z",
"archived": false,
"default_branch": "main",
"license": "MIT"
},
{
"full_name": "LostRuins/koboldcpp",
"html_url": "https://github.com/LostRuins/koboldcpp",
"description": "Run GGUF models easily with a KoboldAI UI. One File. Zero Install.",
"stargazers_count": 11804,
"forks_count": 777,
"created_at": "2023-03-16T02:07:02Z",
"pushed_at": "2026-09-19T15:12:22Z",
"updated_at": "2026-09-19T22:47:22Z",
"archived": false,
"default_branch": "concedo",
"license": "AGPL-3.0"
},
{
"full_name": "turboderp-org/exllamav3",
"html_url": "https://github.com/turboderp-org/exllamav3",
"description": "An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs ",
"stargazers_count": 1464,
"forks_count": 181,
"created_at": "2025-04-06T12:36:08Z",
"pushed_at": "2026-09-19T13:39:07Z",
"updated_at": "2026-09-20T01:12:37Z",
"archived": false,
"default_branch": "master",
"license": "MIT"
},
{
"full_name": "kvcache-ai/ktransformers",
"html_url": "https://github.com/kvcache-ai/ktransformers",
"description": "A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations",
"stargazers_count": 19522,
"forks_count": 1576,
"created_at": "2024-07-26T07:18:28Z",
"pushed_at": "2026-09-19T03:06:55Z",
"updated_at": "2026-09-19T22:59:35Z",
"archived": false,
"default_branch": "main",
"license": "Apache-2.0"
},
{
"full_name": "NVIDIA/TensorRT-LLM",
"html_url": "https://github.com/NVIDIA/TensorRT-LLM",
"description": "TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.",
"stargazers_count": 14673,
"forks_count": 2762,
"created_at": "2023-08-16T17:14:27Z",
"pushed_at": "2026-09-19T23:51:06Z",
"updated_at": "2026-09-20T00:44:05Z",
"archived": false,
"default_branch": "main",
"license": "NOASSERTION"
},
{
"full_name": "huggingface/text-generation-inference",
"html_url": "https://github.com/huggingface/text-generation-inference",
"description": "Large Language Model Text Generation Inference",
"stargazers_count": 10885,
"forks_count": 1288,
"created_at": "2022-10-08T10:26:28Z",
"pushed_at": "2026-03-21T11:34:22Z",
"updated_at": "2026-09-19T11:48:43Z",
"archived": true,
"default_branch": "main",
"license": "Apache-2.0"
},
{
"full_name": "lmstudio-ai/lmstudio-js",
"html_url": "https://github.com/lmstudio-ai/lmstudio-js",
"description": "LM Studio TypeScript SDK",
"stargazers_count": 1781,
"forks_count": 303,
"created_at": "2023-09-15T06:05:04Z",
"pushed_at": "2026-09-18T22:24:27Z",
"updated_at": "2026-09-19T04:08:58Z",
"archived": false,
"default_branch": "main",
"license": "MIT"
},
{
"full_name": "ggml-org/whisper.cpp",
"html_url": "https://github.com/ggml-org/whisper.cpp",
"description": "Port of OpenAI's Whisper model in C/C++",
"stargazers_count": 53782,
"forks_count": 6181,
"created_at": "2022-09-25T18:26:37Z",
"pushed_at": "2026-09-18T10:20:25Z",
"updated_at": "2026-09-20T01:27:44Z",
"archived": false,
"default_branch": "master",
"license": "MIT"
},
{
"full_name": "Comfy-Org/ComfyUI",
"html_url": "https://github.com/Comfy-Org/ComfyUI",
"description": "The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.",
"stargazers_count": 133934,
"forks_count": 15874,
"created_at": "2023-01-17T03:15:56Z",
"pushed_at": "2026-09-20T00:29:57Z",
"updated_at": "2026-09-20T01:16:24Z",
"archived": false,
"default_branch": "master",
"license": "GPL-3.0"
},
{
"full_name": "vllm-project/vllm-metal",
"html_url": "https://github.com/vllm-project/vllm-metal",
"description": "Community maintained hardware plugin for vLLM on Apple Silicon",
"stargazers_count": 1749,
"forks_count": 260,
"created_at": "2025-12-12T20:37:25Z",
"pushed_at": "2026-09-19T23:52:06Z",
"updated_at": "2026-09-20T00:59:06Z",
"archived": false,
"default_branch": "main",
"license": "Apache-2.0"
},
{
"full_name": "containers/ramalama",
"html_url": "https://github.com/containers/ramalama",
"description": "RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.",
"stargazers_count": 3053,
"forks_count": 367,
"created_at": "2024-07-24T19:09:58Z",
"pushed_at": "2026-09-19T00:03:50Z",
"updated_at": "2026-09-19T19:09:18Z",
"archived": false,
"default_branch": "main",
"license": "MIT"
},
{
"full_name": "GradientHQ/parallax",
"html_url": "https://github.com/GradientHQ/parallax",
"description": "Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere",
"stargazers_count": 1381,
"forks_count": 147,
"created_at": "2025-09-22T07:00:51Z",
"pushed_at": "2026-07-01T07:35:43Z",
"updated_at": "2026-09-18T14:55:16Z",
"archived": false,
"default_branch": "main",
"license": "Apache-2.0"
},
{
"full_name": "danveloper/flash-moe",
"html_url": "https://github.com/danveloper/flash-moe",
"description": "Running a big model on a small laptop",
"stargazers_count": 4145,
"forks_count": 513,
"created_at": "2026-03-18T16:13:13Z",
"pushed_at": "2026-03-19T17:21:57Z",
"updated_at": "2026-09-19T22:36:29Z",
"archived": false,
"default_branch": "main",
"license": null
},
{
"repo": "ikawrakow/ik_llama.cpp",
"error": "HTTP Error 403: rate limit exceeded"
},
{
"repo": "google-ai-edge/LiteRT-LM",
"error": "HTTP Error 403: rate limit exceeded"
},
{
"repo": "lightseekorg/chitu",
"error": "HTTP Error 404: Not Found"
}
]
}