Three trap-laden fix-it tasks with hidden graders for testing an AI coding agent's judgment. Sandbox setup, prompts, answer key, and results for Qwen3.8-Flash, Qwen3.6-35B and Claude Opus 5.
☆43Sep 5, 2026Updated 2 months ago
Alternatives and similar repositories for spec-wins
Users that are interested in spec-wins are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Browser playground and game for llama-server's /v1/decision (Jev-style parallel constrained decisions)☆30Sep 19, 2026Updated last month
- LLM inference in C/C++☆364Oct 30, 2026Updated last week
- Self-hosted test suite for local LLMs — deterministic, agentic (real curl tool-calls), and blinded-subjective evals. React/Vite/TS + Fast…☆12Jul 1, 2026Updated 4 months ago
- Spec-driven architecture validation for microservices☆16Sep 23, 2026Updated last month
- Self-hosted LLM/RAG stack in one command — AMD Strix Halo / x86_64 (ROCm/Vulkan, Docker Compose)☆28Sep 27, 2026Updated last month
- 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.
- Deterministic PyGhidra extraction, triage, and local LLM compiler-backend pipeline for C reimplementation.☆11Oct 18, 2026Updated 3 weeks ago
- The starter template for Google Apps Script by clasp and deno☆16Dec 1, 2025Updated 11 months ago
- Qwen3.8-27B on One RTX 3090: 14 hours of measurements. Vision crash fix, VRAM math, MTP tuning, quantisation comparison, and 9 pieces of …☆13Aug 17, 2026Updated 2 months ago
- OpenAI-compatible proxy that makes local LLMs serving easy and reliable. Sits between your client and any OpenAI-compatible backend, add…☆14Oct 19, 2026Updated 3 weeks ago
- Covert Coder — a local-first sovereign AI development environment for governed models, workflows, execution, evidence, and verification.☆53Oct 26, 2026Updated 2 weeks ago
- ☆11Mar 10, 2022Updated 4 years ago
- A professional post-production, color grading, and sharpness suite for ComfyUI☆16Jun 9, 2026Updated 5 months ago
- Real-time monitoring for llama.cpp inference servers: a read-only host agent plus a web dashboard for hardware, health and inference tele…☆32Oct 31, 2026Updated last week
- A comprehensive web application for calculating Large Language Model (LLM) memory requirements and performance metrics for various GPU co…☆17Jun 21, 2025Updated last year
- 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.
- Self-hosted infrastructure deployment and management automation.☆23Nov 2, 2026Updated last week
- ☆17Mar 21, 2026Updated 7 months ago
- Persistent memory for Claude Code, Claude Desktop, and Codex — save once, recall across sessions, shared across all your AI CLIs.☆17Oct 22, 2026Updated 2 weeks ago
- ☆16Jul 17, 2026Updated 3 months ago
- ☆16Aug 10, 2026Updated 3 months ago
- Плагин интеграции API GigaChat для OpenCode☆22Oct 6, 2026Updated last month
- Multi-GPU (tensor-parallel) CUDA megakernel for Qwen3.8-27B GGUF (Q4_K_M, Q5_K_M, Q6_K, Q8_0) with on-device MTP speculative decoding. Fo…☆16Oct 23, 2026Updated 2 weeks ago
- SGLang for cool dudes using V100☆84Updated this week
- High-performance universal media optimizer for images, video, and audio. Built with Nuitka and Go, with auto-GPU acceleration and crash-s…☆21Sep 13, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Library of AI Agent Personas☆14Aug 12, 2025Updated last year
- ComfyUI - Adobe After Effects Script Panel Integration☆12Aug 22, 2026Updated 2 months ago
- The chef's standard for AI agent work: twelve rules, a critique gate, and project memory. One skill. Craftsman's taste. Zero AI slop.☆21Aug 26, 2026Updated 2 months ago
- Private-first, self-hostable knowledge base. Your data, your server, your control. No cloud, no telemetry, no trust required.☆22Oct 4, 2026Updated last month
- Deploy Your Swarm In One Click with FastAPI, Uvicorn, and more ;)☆10Oct 13, 2025Updated last year
- Independent experimental ScaleQ-style compression for Qwen3.5, with tests and original paper☆29Nov 4, 2026Updated last week
- Experiments with DSPy — declarative, trainable LLM pipelines. Notebooks and demos for evaluating, composing, and optimizing LLM workflows…☆11Jun 24, 2026Updated 4 months ago
- A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.☆13Apr 9, 2026Updated 7 months ago
- File-based named channels for talking between AI coding agents (Claude Code, Codex, OpenCode) across sessions — zero-server, kqueue-backe…☆26Sep 11, 2026Updated 2 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Маршрутизация через Cloudflare WARP и не только на сервере с AntiZapret VPN☆25Oct 27, 2026Updated 2 weeks ago
- AI-powered sandbox environment with ephemeral Docker sub-agents for compute, browser, and app deployment☆44Jul 27, 2026Updated 3 months ago
- Matrix multiplication and LLM serving kernels for RK3588 RKNPU2. (like FlashInfer but for RKNPU2!)☆21Nov 4, 2026Updated last week
- A second brain for your business or personal needs☆13Jan 21, 2026Updated 9 months ago
- FUSE file system for archives and compressed files (ZIP, RAR, 7Z, ISO, TGZ, XZ...)☆17Oct 12, 2026Updated 3 weeks ago
- Engineer's vibe coding companion with 2.16" AMOLED ESP-32-S3 touch device, it has coding buddy for approval, usage limits, weather and li…☆24Updated this week
- RTX 6000 96GB/Spark 128GB vLLM Recipe for Qwen 3.8 Flash Next☆23Sep 8, 2026Updated 2 months ago
Are these results useful?