Starred repositories
A survey of Code Agents / Foundation Models for improving development productivity. Become 10x SWE, MLE, etc.
A design system for AI applications. Material, physical, tactile, technical.
Benchmarking Chat Assistants on Long-Term Interactive Memory (ICLR 2025)
A test of the ability of the Fossil DVCS to mirror to GitHub
A curated list of AI Agent Swarm frameworks, multi-agent orchestration, swarm intelligence, and collaborative agent systems.
The open-source agent harness - the runtime layer that turns an LLM into a working agent.
Ephemeral Workspaces, durable shared history. LayerFS gives every agent a complete, writable filesystem Workspace over shared committed history, without copying the base. Agents work in parallel, c…
Mount PostgreSQL as a filesystem. Build apps with files, explore databases with ls and cat. Every write is logged and undoable.
Official Codebase of "Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine"
A curated map of reinforcement learning for agents: systems that learn through interaction with environments, tools, APIs, users, other agents or the physical world.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Slurps webpages and saves them as clean, uncluttered Markdown. Think Pocket, but better.
Pi extension for async subagent delegation with truncation, artifacts, and session sharing
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…
Fast, indexed regexp search over large file trees
"When in doubt, use brute force." ― Kenneth Lane Thompson
"UNIX is basically a simple operating system, but you have to be a genius to understand the simplicity." ― Dennis M. Ritchie
A new kind of language for a new kind of computer
RSI Bench is an ongoing effort to evaluate whether AI agents can develop the capabilities required to advance AI R&D.
Microsoft PowerToys is a collection of utilities that supercharge productivity and customization on Windows
hardware implementation of transformers running microgpt at 50k+ tkps
Fast as FUCK nvim completion. SQLite, concurrent scheduler, hundreds of hours of optimization.
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
Machine Learning Systems: Foundations, Scaling, Agentic AI, and Physical AI (Vols I–IV) • Harvard CS249r | https://mlsysbook.ai
The simplest, fastest repository for training/finetuning medium-sized GPTs.