Top Finds

Persistent KV cache with content-hash addressing for tool-augmented LLMs

Triton‑style kernel toolkit for MLX plus a small upstream incubator: prototype, benchmark, and upstream fusions for Apple Silicon

Steerable Harnesses for DeepAgents — Orchestra🪶

Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)

Vizro is a low-code toolkit for building high-quality data visualization apps.

The best ChatGPT that $100 can buy.

Multi-language debugger with real-time web UI and LLM integration via MCP

Interactive brainstorming UI for OpenCode agents - multi-question forms, decisions, and real-time feedback

A memory system for AI applications that preserves ground truth, tracks confidence, and prevents hallucinations.

Teacher-forced confidence analysis for language models. pip install confidence-cartography

Slides about my Windsurf Productivity Setup

🚀 Strapi is the leading open-source headless CMS. It’s 100% JavaScript/TypeScript, fully customizable, and developer-first.

any llm browsing for you in chrome

Webscout is the all-in-one search and AI toolkit you need. Discover insights with Yep.com, DuckDuckGo, and Phind; access cutting-edge AI models; transcribe YouTube videos; generate temporary emails and phone numbers; perform text-to-speech conversions; and much more!

@md2docx/md2docx — The simplest way to convert Markdown to DOCX. Batteries-included wrapper around all @m2d/* packages and Unified. One import, one call — full Markdown → Word conversion with HTML, images, math, tables, and more.

Rapid development of self-documenting APIs

pip install gptmed

Unified Emacs interface supporting OpenAI Codex, GitHub Copilot CLI, Claude Code, Gemini CLI, Opencode, and more

A role-playing game with an LLM dungeon master

Resilient multi-LLM orchestration with in-built failure handing, rate limits, retries, and circuit breaker.

LiteLLM for Go, the easiest way to write LLM-based programs in Go

Rest API that returns a bunch of color names for a given color-value

One command brings a complete pre-wired LLM stack with hundreds of services to explore.

The AI-Native Search Database. Unifies vector, text, structured and semi-structured data in a single engine, enabling hybrid search and in-database AI workflows.

Django middleware and utils that add `Server-Timing` header