Lists (1)
Stars
AutoAdapt: An Automated Domain Adaptation Framework for Large Language Models
Grid-Free Monte Carlo Solvers for Physics Simulations Involving Partial Differential Equations
Official implementation of ACL 2026 paper, "ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation"
A framework for efficient model inference with omni-modality models
Snappy, batteries-included terminal file manager with rich previews, inline images, bulk actions, and trash support
Rust/Wasm-powered SQL transpiler for more than 30 SQL dialects
Evaluate AI agents with Unix-style pipeline commands. Schema-driven adapters for any CLI agent, trajectory capture, pass@k metrics, and multi-run comparison.
🚀 Ultra Recipe for Training Long-Horizon Search Agents - matching frontier AI's search capability with a 20B model
Attention variant with per-channel multiplicative decay
IsUMap is a tool for manifold learning, dimension reduction and data visualization
A 7-layer memory operating system for Hermes Agent — persistent memory with Qdrant, structured facts, fabric recall, auto-curated wiki, and surgical context injection. Runs locally, any LLM provider.
The Common Core Ontology Repository holds the current released version of the Common Core Ontology suite.
GDM Science Skills to speed up agentic scientific workflows with better grounding and higher token efficiency. Integrate insights from AlphaGenome, AFDB, UniProt and 30+ other databases and tools.
Autonomous multi-batch development skill for Claude Code and Codex. They work while you sleep.
SeqUnwinder: a platform for deconvolving motifs associated with genomic labels
[NeurIPS'23 Spotlight] "Mind2Web: Towards a Generalist Agent for the Web" -- the first LLM-based web agent and benchmark for generalist web agents
An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides.
Measuring frontier coding agents on original, long-horizon engineering tasks
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
A library for generating and evaluating synthetic tabular data for privacy, fairness and data augmentation.
nbsynthetic is simple and robust tabular synthetic data generation library for small and medium size datasets
Project to manage Flux tasks needed to standardize kubernetes HPC scheduling interfaces
An Automated AI Agent Tool for Plotting Your Data in Any Paper's Figure Style.
Official Codebase: LT2: Linear-Time Looped Transformers.