Local AI harness for coding agents: local-first, any OpenAI-compatible engine or cloud model. Tuned for AMD Strix Halo (Qwen3.8 125B on the iGPU), NPU side-jobs, crash recovery, logged benchmarks.
☆38Nov 9, 2026Updated this week
Alternatives and similar repositories for local-ai-harness
Users that are interested in local-ai-harness are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- GPU + XDNA2 NPU inference for AMD Strix Halo (gfx1151): Qwen3.6-35B-A3B, Qwen3.8-27B, Qwen3.8 Flash-Next, Flint and GLM-5.3 Flash (321B M…☆93Updated this week
- Two-rank tensor-parallel LLM serving over USB4v2 between AMD Strix Halo hosts: a custom Linux thunderbolt stream transport, self-healing …☆17Updated this week
- The Open Source Strix Halo AI engine. Qwen 3.8 Flash Next Q4_K_XL: 1,801.01 pp, 73.17 tg single user, 194.37 tok/s 8 users; Qwen 3.8 27B…☆1,123Updated this week
- Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthrop…☆1,261Updated this week
- A two-day, non-expert guide to running local LLMs on an AMD Strix Halo (Ryzen AI Max+ 395) box — full ~120GB memory pool, ROCm backend, N…☆32Jul 25, 2026Updated 3 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆111Aug 28, 2026Updated 2 months ago
- LLM inference engine written from scratch in HIP for AMD Strix Halo (gfx1151) and Qwen3.8-Flash-Next - ~50 tokens/s out to 492k context☆100Updated this week
- Run Qwen3.8-Flash-Next on a single AMD Strix Halo using Halogen Flash Server☆25Nov 2, 2026Updated last week
- A secure, local-first Python framework for orchestrating complex multi-agent think tanks with dynamic expertise-weighted routing.☆20Sep 4, 2026Updated 2 months ago
- Reproducible, evidence-backed llama.cpp serving recipes for Strix Halo class machines — annotated parameters, ▏ multi-witness results, a…☆21Oct 3, 2026Updated last month
- Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; port…☆224Oct 25, 2026Updated 2 weeks ago
- Qwen 3.8 27B ROCmFP4 on AMD Strix Halo (Ryzen AI Max+ 395). Up to 36 tok/s via MTP Speculation, TurboQuant & Mesa RADV Wave64.☆268Sep 7, 2026Updated 2 months ago
- Kyojin: open-source engine that runs 100 GB-class open models (GLM-5.3, Qwen3.8, DeepSeek V4.1) on one desktop machine. AMD Strix Halo, N…☆234Updated this week
- Qwen 3.8 Next Flash toolbox utilizing pwilkin's strix-halo llama.cpp fork☆13Sep 16, 2026Updated last month
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- opencode plugin that hard-blocks hallucinated file-proxy artifact URLs before any tool dials out.☆26Oct 27, 2026Updated 2 weeks ago
- Portable optimized ROCm and Qwen3.8-27B setup for AMD Strix Halo☆85Sep 16, 2026Updated last month
- MoE expert compression toolkit — prune, merge, and forge specialist models for local inference.☆13Updated this week
- A geometric, squared sans-serif typeface from Nebiolo S. A. foundry. Eurostile was designed (by Novarese and Butti in 1952) to complement…☆13Oct 3, 2026Updated last month
- Resources for the Document Visual AI with FiftyOne—When a Pixel is Worth a Thousand Tokens Workshop☆19Nov 14, 2025Updated 11 months ago
- ☆93Oct 23, 2026Updated 2 weeks ago
- Qwen 3.8 Flash NVFP4 with PLE NVFP4 quantized to run on a single DGX Spark☆15Aug 28, 2026Updated 2 months ago
- LLM inference in C/C++☆260Updated this week
- FastFlow-SDK is a software stack for running and developing applications on AMD XDNA Neural Processing Engines (NPUs).☆14Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- llama.cpp modified to work with Strix Halo + dGPU as an accelerator, Dual Strix Halo Machines, or both☆59Updated this week
- NPU-accelerated speech transcription & speaker diarization on AMD Strix Halo: Whisper-v3-turbo on XDNA 2 + pyannote, OpenAI-compatible AP…☆14Aug 31, 2026Updated 2 months ago
- ☆2,019Updated this week
- rust binding for lean4☆12Jul 1, 2023Updated 3 years ago
- self-hosted workspace for Google's Jules AI agent☆18Jul 4, 2026Updated 4 months ago
- A TUI for viewing your Strava run data☆13Apr 17, 2026Updated 6 months ago
- Run any large transformer model on consumer GPUs. No quantization. No compromise.☆10Sep 23, 2026Updated last month
- DGX Spark EC fan speed override / rollback tool☆25Aug 23, 2026Updated 2 months ago
- ☆21Sep 28, 2026Updated last month
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- The fastest way to run Qwen3.8 27B on Strix Halo (gfx1151)☆157Sep 14, 2026Updated last month
- ☆29Oct 11, 2026Updated 3 weeks ago
- reverse engineering https://pomofocus.io/☆10Feb 11, 2021Updated 5 years ago
- llama.cpp setup on dedicated AMD Strix Halo machine☆14Jul 26, 2026Updated 3 months ago
- Local AI setup for AMD Strix Halo APU - Lemonade + Vulkan + kyuz0☆88Updated this week
- Rust LLM inference engine tuned for AMD Strix Halo (gfx1151): a fork of Strata with ggml/llama.cpp-derived HIP kernels. Five models on on…☆39Updated this week
- Active Windows 10/11 gratuitement en utilisant un serveur KMS.☆21Jul 28, 2022Updated 4 years ago
Are these results useful?