Bookmarks

GitHub - JustVugg/colibri: Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦 · GitHub https://github.com/JustVugg/colibri

Mon Jul 13 15:32:17 2026

Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦 - JustVugg/colibri

Ai2: Truly open breakthrough AI https://allenai.org/

Sat Jul 11 13:39:59 2026

Higgsfield AI — AI-native creative suite https://higgsfield.ai/

Sat Jul 11 12:17:14 2026

git-spice https://abhinav.github.io/git-spice/

Fri Jul 10 12:27:15 2026

LLM360 | Open-Source LLMs towards Community-Driven AGI 🚀 https://www.llm360.ai/index.html

Fri Jul 10 08:20:54 2026

Join LLM360 in advancing community-owned AGi with open-source resources for transparent and ethical LLM development. Explore pretraining suites and more.

karpathy/llm-council: LLM Council works together to answer your hardest questions https://github.com/karpathy/llm-council

Tue Jul 7 08:11:27 2026

GitHub - multica-ai/andrej-karpathy-skills: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. · GitHub https://github.com/multica-ai/andrej-karpathy-skills/tree/main

Tue Jul 7 08:08:05 2026

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. - multica-ai/andrej-karpathy-skills

Retro tool | Simple and effective retrospectives for your team https://www.retrotool.app/

Tue Jun 30 08:00:39 2026

Collaborate with your remote team to improve what you do, guided by a simple workflow. And for free!

Recursive Language Models | Alex L. Zhang https://alexzhang13.github.io/blog/2025/rlm/

Mon Jun 29 10:39:04 2026

We propose Recursive Language Models (RLMs), an inference strategy where language models can decompose and recursively interact with input context of unbounded length through REPL environments.

GitHub - affaan-m/ECC: The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. https://github.com/affaan-m/ECC

Mon Jun 15 14:08:35 2026

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. - affaan-m/ECC