thinkingbox is a framework for defining tool as MCP servers, running LLM agents against them, and evaluating agent behavior — for offline training-data generation, reinforcement-learning training l…

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

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.

#1 Persistent memory for AI coding agents based on real-world benchmarks

The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

Secure, cross-platform Git credential storage with authentication to GitHub, Azure Repos, and other popular Git hosting services.

An agentic evaluation framework

Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.

Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

Readymade evaluators for agent trajectories

A Docker sandbox template for running GitHub Copilot CLI in an isolated environment, similar to how Docker supports Claude Code and Gemini CLI via docker sandbox run

Zotero MCP: Connects your Zotero research library with Claude and other AI assistants via the Model Context Protocol to discuss papers, get summaries, analyze citations, and more.

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

LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratc…

AI agents running research on single-GPU nanochat training automatically

TypeScript AI agent orchestration framework with dynamic workflows. Describe the goal, not the graph: a coordinator plans the task DAG at runtime and runs it on any LLM (Claude, ChatGPT, Gemini, De…

Open-source Claude Code skills and Codex skills for AI-first work. Audit, re-engineer, and bootstrap projects with AI-first design principles.

The Multilingual Entity Linking of Occupations (MELO) Benchmark

WorkRB: Work Research Benchmark

SKILLSPAN: Competences as Spans for Skill Extraction from Job Postings

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Late Interaction Models Training & Retrieval

GitHub Mirror of RecPack: Experimentation Toolkit for Top-N Recommendation (see https://gitlab.com/recpack-maintainers/recpack)

State-of-the-Art Embeddings, Retrieval, and Reranking

The code used to evaluate embedding models on the Massive Legal Embedding Benchmark (MLEB).

MTEB: State-of-the-art evaluation of embeddings across languages and modalities

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL

In this codebase we establish a benchmark for egocentric user adaptation based on Ego4d.First, we start from a population model which has data from many users to learn user-agnostic representations…

PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.