Entity-level semantic merge driver for Git. Resolves conflicts that git can't by understanding code structure via tree-sitter. 31/31 clean merges vs git's 15/31.

Kernel-enforced agent sandbox. Capability-based isolation with secure key management, atomic rollback, cryptographic immutable audit chain of provenance. Run your agents in a zero-trust environment.

AI agents running research on single-GPU nanochat training automatically

mimalloc is a compact general purpose allocator with excellent performance.

DSPy: The framework for programming—not prompting—language models

Implementation of Forward Laplacian algorithm in JAX

Office Compound Engineering plugin for Claude Code, Codex, and more

A command-line benchmarking tool

A microbenchmark support library

Game Boy emulator written in Python

A GPU-Accelerated First-Order LP Solver

Native PC gaming with Steam, Epic, GOG and Amazon integrations on Android

Tree-sitter-powered code indexing server that gives LLM agents precise, on-demand access to symbols, implementations, callers, tests, and grep across multi-language projects - so they explore codeb…

Recursive Language Models (https://arxiv.org/abs/2512.24601)

RLM for coding agent

Agent Zero AI framework

Memory engine and app that is extremely fast, scalable. The Memory API for the AI era.

omo; the best agent harness - previously oh-my-opencode

Skill + MCP server to turn your agent into an RLM. Load context, iterate with search/code/think tools, converge on answers.

Claude code setup as an RLM scaffhold Implemented by Brainqub3

Pythonic task management & command execution.

General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.

🧡 Everything is RSSible

nanobind: tiny and efficient C++/Python bindings

Wrapper around tool using LLMs for agentic workflows

Exploitability calculation for imperfect-information game benchmarks

Knowledge Engine for AI Agent Memory in 6 lines of code

Documentation: