Data/All products
Search and sort every AI product collected from the connected sources. Each row keeps its numbers in the source's own unit. Open a row to see its tags, timeline and original listings.
Products in view
390
Matching your filters, last 30 days
Classified
3,267
of 3,838 collected products
Awaiting classification
571
Picked up by the next pipeline run
Sources collecting
5/6
Product Hunt not connected
Filters apply to the table below and stay in the link when you share it.
Ranked by attention: votes, points or stars compared only within the same source, then averaged. Products with no source metric are left out.
| # | Product | Technology | Industry | Traction signal | Launched | |
|---|---|---|---|---|---|---|
| 226 | H HaloLab-Yee HaloLab-Yee is an SGLang decode-side Recall speculative-draft acceleration module using token ID history recall with output identical to no acceleration. | AI Infrastructure | Developer Tools | 51 / 100 24 stars on GitHub | Nov 10, 2026 | |
| 227 | E elpis-on-7900xtx Provides a recipe, patches, and benchmarks for running Qwen3.8-27B with EXL3 and DFlash2 speculative decoding on an AMD RX 7900 XTX. | AI Infrastructure | Developer Tools | 50 / 100 23 stars on GitHub | Nov 1, 2026 | |
| 228 | L libstrix Provides a Docker command to run Qwen, Gemma, LFM and more with optimized vLLM on AMD Strix Halo. | AI Infrastructure | Developer Tools | 50 / 100 23 stars on GitHub | Oct 28, 2026 | |
| 229 | P pgvectorfast pgvectorfast is a Postgres extension for vector search with performance enhancements built on Calico buffer pool. | AI Infrastructure | Developer Tools | 49 / 100 22 stars on GitHub | Nov 15, 2026 | |
| 230 | E essun Is a specification-driven, multi-fidelity simulator for scale-up GPU fabrics with manifests traced to immutable run records. | AI Infrastructure | Developer Tools | 49 / 100 22 stars on GitHub | Oct 29, 2026 | |
| 231 | L longcap-code longcap-code provides inference code with custom vLLM server, CPU client and Docker image for hour-scale timestamped audio captioning and diarization. | Voice AI | Developer Tools | 47 / 100 21 stars on GitHub | Oct 26, 2026 | |
| 232 | A Agentest Agentest provides offline tests for AI agents from OpenTelemetry traces. | AI Infrastructure | Developer Tools | 46 / 100 2 points on Hacker News | Oct 23, 2026 | |
| 233 | P punchtape punchtape helps AI complete entire jobs with every claim proven. | AI Agents | Developer Tools | 46 / 100 1 vote on Uneed | Nov 15, 2026 | |
| 234 | C Cheetah Cheetah is a single-binary local LLM inference server in Rust and C supporting Safetensors and an OpenAI-compatible gateway. | AI Infrastructure | Developer Tools | 45 / 100 20 stars on GitHub | Oct 30, 2026 | |
| 235 | R roboworm roboworm evaluates movement realism, consistency, and acceleration effects in embodied video world models. | AI Infrastructure | Developer Tools | 44 / 100 19 stars on GitHub | Oct 29, 2026 | |
| 236 | H halocline Enables the Qwen4 sparse and dense family to run on one RTX 4090 (sm_89 only). | AI Infrastructure | Developer Tools | 42 / 100 18 stars on GitHub | Nov 16, 2026 | |
| 237 | P pico-dgx-qwen38 Provides a TensorFold recipe with 29 patches to run Qwen3.8-Flash-Next with official NVIDIA FP4 weights on one DGX Spark. | AI Infrastructure | Developer Tools | 36 / 100 15 stars on GitHub | Nov 15, 2026 | |
| 238 | X XeMaya Provides native inference for Qwen3.8-Flash-Next, GLM-5.3-Flash and DeepSeek-V4.1-Flash on Intel Arc GPUs using SYCL, Level Zero and XMX, in alpha as a fork of XeStrata. | AI Infrastructure | Developer Tools | 36 / 100 15 stars on GitHub | Nov 10, 2026 | |
| 239 | V voice-containers voice-containers provides production-ready voice-container images for NVIDIA Jetson edge GPUs with a streaming voice stack and benchmark harness. | Voice AI | Developer Tools | 36 / 100 15 stars on GitHub | Nov 6, 2026 | |
| 240 | R ruvllm ruvllm provides governed neural weight editing and coding model adaptation with Rust patches, rollback, LoRA, routing, and benchmarks. | AI Infrastructure | Developer Tools | 36 / 100 15 stars on GitHub | Nov 3, 2026 | |
| 241 | A AIEngineOnSmallUniMem AIEngineOnSmallUniMem is a streaming inference engine for running large language models on a Linux environment on a PS5 console. | AI Infrastructure | Developer Tools | 33 / 100 14 stars on GitHub | Nov 16, 2026 | |
| 242 | C cmp100-100-unlock Unlocks the NVIDIA CMP 100-100 mining card from 6GB to full 12GB HBM2 on Linux for use with local LLMs. | AI Infrastructure | Developer Tools | 33 / 100 14 stars on GitHub | Nov 1, 2026 | |
| 243 | T toollens toollens is a Rust MCP gateway providing dependency-aware tool discovery and policy-checked execution for agents. | AI Agents | Developer Tools | 33 / 100 14 stars on GitHub | Oct 29, 2026 | |
| 244 | I inference-bench inference-bench compares inference providers on speed and cost for agentic research tasks. | AI Infrastructure | Developer Tools | 29 / 100 13 stars on GitHub | Nov 8, 2026 | |
| 245 | S sparkscore sparkscore runs typed calibrated decisions with d3-ultra 27B NVFP4 on Atlas on one NVIDIA DGX Spark in one engine pass per question. | AI Infrastructure | Developer Tools | 29 / 100 13 stars on GitHub | Nov 6, 2026 | |
| 246 | S system-d-monitor system-d-monitor is a Btop-style ESP32-S3 touchscreen dashboard for vLLM and TensorFold inference servers. | AI Infrastructure | Developer Tools | 29 / 100 13 stars on GitHub | Nov 2, 2026 | |
| 247 | P playground-serve Provides open source serving for robot policies and LLM agents to run VLAs on serverless GPUs or language models through OpenRouter. | AI Agents | Developer Tools | 26 / 100 12 stars on GitHub | Nov 14, 2026 | |
| 248 | C CUDA_GPT2_Inference CUDA_GPT2_Inference is a pure CUDA implementation of GPT2 inference with per-operator optimization for faster single-request speed than vLLM. | AI Infrastructure | Developer Tools | 26 / 100 12 stars on GitHub | Nov 10, 2026 | |
| 249 | W woodcock woodcock provides lossless speculative decoding for Apple Silicon via MLX to make Qwen3 generation 2x faster with a trained hidden-state drafter. | AI Infrastructure | Developer Tools | 24 / 100 11 stars on GitHub | Oct 22, 2026 | |
| 250 | R roomr roomr is a media edge and server for voice AI that takes calls in, mixes audio in rooms and streams it to your app. | Voice AI | Developer Tools | 24 / 100 11 stars on GitHub | Oct 22, 2026 |