Full page

Captured 7 days ago. Click for the whole screenshot.

Looks similar

Octomind – open-source AI harness that saves your tokens, static rust(github.com)

41 points by donk8r 10 days ago | 32 comments

GitHub repository for Octomind, an open-source Rust AI coding agent and runtime that works with any model, is MCP-native, and runs in terminal, CI, or as a daemon.

ai-coding-agentrustmcpllm

Zebkit – Chromium as an embeddable library(github.com)

107 points by Riiiiichard 4 days ago | 40 comments

GitHub repository for zebkit, a slim cross-platform library that embeds Chromium's browser engine into applications, with Rust and Python bindings.

chromiumbrowser-engineembeddingrust

Show HN: Spindle – a full-featured, type-safe web framework for OCaml 5(github.com)

51 points by zaiev 8 days ago | 8 comments

GitHub repository for Spindle, a type-safe, multicore, Eio-native web framework for OCaml 5 with OpenAPI, Zod and Melange client generation and MCP support.

ocamlweb-frameworkeioopenapi

6-11X speedup running Qwen3.6 on my RTX 4090, full repo.(github.com)

10 points by AI4Science 6 hours ago | 0 comments

GitHub repository for Lightreason, a Python/CUDA project claiming LLM token-generation speedups for Qwen models on consumer GPUs, with benchmarks and a demo chat.

llm-inferencespeculative-decodingqwenrtx-4090

Show HN: SafeScript, a safe version of JavaScript for executing untrusted code(github.com)

4 points by EGreg 5 days ago | 0 comments

GitHub repository for SafeScript, a safe subset of JavaScript that compiles to JS and PHP for sandboxed execution of untrusted code.

javascriptsandboxingsafescriptuntrusted-code

Show HN: Klad, a paint app your coding agent can drive (source-available)(github.com)

59 points by ambewas 2 days ago | 26 comments

GitHub repository for Klad, a source-available Rust paint and animation app with editable brush strokes that AI coding agents can control via a CLI.

kladrustai-agentsdrawing-app

Related stories

DeepSeek: DeepSeek v4.1 Flash 1017(openrouter.ai)

499 points by theanonymousone 27 days ago | 264 comments

OpenRouter model page for DeepSeek V4.1 Flash 1017, a sparse mixture-of-experts LLM snapshot with pricing, 1M context, and API access details.

deepseekopenrouterllmmixture-of-experts

DeepSeek V4.1 Flash 1017 (Max)(artificialanalysis.ai)

159 points by theanonymousone 25 days ago | 58 comments

Artificial Analysis model page benchmarking DeepSeek V4.1 Flash 1017 (Max) on intelligence, speed, and price.

deepseekllm-benchmarksopen-weightsartificial-analysis

DeepSeek-Prover-V2(github.com)

359 points by meetpateltech 1 year ago | 74 comments

GitHub repository for DeepSeek-Prover-V2, DeepSeek's model for formal theorem proving, containing a paper PDF, README, model license, and miniF2F solutions.

deepseektheorem-provinglean-4llm

DeepSeek-V4-Flash Update(api-docs.deepseek.com)

657 points by dnhkng 3 months ago | 313 comments

DeepSeek API docs changelog entry announcing the DeepSeek-V4-Flash API public beta with improved agent benchmark results.

deepseekdeepseek-v4llmapi

DeepSeek V4 Flash 0731 Intelligence, Performance and Price Analysis(artificialanalysis.ai)

530 points by theanonymousone 3 months ago | 289 comments

An Artificial Analysis page meant to benchmark DeepSeek V4 Flash's intelligence, performance and price, which returned a 404 Page not found error.

deepseekdeepseek-v4llm-benchmarksartificial-analysis

DeepSeek v4.1 Flash(twitter.com)

919 points by Liwink 2 months ago | 505 comments

DeepSeek's X post announcing DeepSeek-V4.1-Flash, a small model with native visual understanding, shown with benchmark comparisons against rival models.

deepseekdeepseek-v4-1-flashllmopen-weights