🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman - JuliusBrussee/caveman
An agentic skills framework & software development methodology that works. - obra/superpowers
Main agent plans and reviews; cheaper sidekick edits. Devin Fusion pattern for OpenCode - mihneaptu/opencode-fusion
A desktop reader for OpenSpec projects - browse changes, trace how requirements evolved, and comment on specs, all from local folders - dansreis/speclens
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
Join LLM360 in advancing community-owned AGi with open-source resources for transparent and ethical LLM development. Explore pretraining suites and more.
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
Collaborate with your remote team to improve what you do, guided by a simple workflow. And for free!
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.
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
Zero-dependency, token-efficient database MCP server for Postgres, MySQL, SQL Server, MariaDB, SQLite. - bytebase/dbhub