Stars
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
A Python port of Pi’s minimalist coding agent.
Turn your coding agents into research agents
Local-first search across your workspace, built for humans and AI agents.
Detecting and interpreting genetically-driven heterogeneous treatment effects.
A curated collection of AI agent skills for biomedical research, covering genomics, proteomics, single-cell analysis, clinical AI, and protein design.
Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alternative built on Tauri + MCP + agent skills.
One Forge, All Skills: A curated skill collection for academic writing and research. 点开即用，按需配置的一站式学术研究skills平台。
The agent that grows with you
Realistic examples of building evals and optimizing agents with Harbor
Turn any repository into verifiable RL environments for coding agents - Harbor tasks you can train on, evaluate and share on the Hugging Face Hub
你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.
autonomous nanogpt optimizer speedrun
An app to monitor the (Codex) situation
The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.
Archived — ML Intern is no longer maintained. Continue with HuggingChat.
Make humans and AI agents work as one team — open-source and self-hostable.
The best-benchmarked open-source AI memory system. And it's free.
Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Train the smallest LM you can that fits in 16MB. Best model wins!
Benchmarking approaches to fine-tune AlphaGenome on MPRA across distributional shifts
AI agents running research on single-GPU nanochat training automatically
⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA
AI agents running research on single-GPU nanochat training automatically