Stars
A dataset & lightweight training framework that teaches small models to think like financial analysts.
A collection of agent skills for development of Streamlit apps.
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tri…
Skills for Real Engineers. Straight from my .agents directory.
An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides.
Distributed task queue with full async support
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with C…
Claude Code skills for Obsidian | Claude Code x Obsidian Lab, 4 weeks live, starts Nov 10
Persistent memory for Claude Code — 3-5x longer sessions, 60-80% fewer wasted tokens. Branch-aware, self-healing, token-efficient.
Karpathy's LLM-Wiki vision, fully realized — wiki-centric full-lifecycle AI research platform powered by Claude Code
Run multiple AI models against the same research, design, or coding task. Surface disagreements before you ship.
A straightforward Python library that lets you query pandas DataFrames in plain English instead of writing complex pandas code. Your data never leaves your machine when using local models.
Run Qwen3.5-35B-A3B with 1 million token context on a single NVIDIA L4
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCod…
Garry's Opinionated OpenClaw/Hermes Agent Brain
mini cli search engine for your docs, knowledge b 3C70 ases, meeting notes, whatever. Tracking current sota approaches while being all local
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more