From a goal to a task DAG, automatically. TypeScript-native multi-agent orchestration.

Welcome to the official repository of SINQ! A novel, fast and high-quality quantization method designed to make any Large Language Model smaller while preserving accuracy [ICML 2026]

OpenSail is the open-source alternative to Codex App, Claude Desktop, Cursor, and Cowork for agentic software work.

Your AI friend right in your browser

MCP-powered fallback layer that lets AI agents execute tasks through the GUI when APIs, tools, or direct integrations are unavailable. Cross-OS, accessibility-first, local-only.

The scaffold for your multi-model, personalized Natural Language AI Harness (NLAH) .

Sovereign, depth-adaptive AI memory. Open source. Local-first. Model-agnostic.

This is an official repository for "LAVA: Data Valuation without Pre-Specified Learning Algorithms" (ICLR2023).

Dragon Brain — persistent long-term memory for AI agents via MCP (Model Context Protocol). Knowledge graph (FalkorDB) + vector search (Qdrant) + CUDA GPU embeddings. Works with Claude, Gemini CLI, Cursor, Windsurf, VS Code Copilot. 30 tools, 1121 tests.

Contrastive Explanation (Foil Trees), developed at TNO/Utrecht University

[ICLR24] "AutoVP: An Automated Visual Prompting Framework and Benchmark" by Hsi-Ai Tsao*, Lei Hsiung*, Pin-Yu Chen, Sijia Liu, and Tsung-Yi Ho.

✨ Official code for our paper: "Uncertainty-o: One Model-agnostic Framework for Unveiling Epistemic Uncertainty in Large Multimodal Models".

Official implementation of FedGAT: Generative Autoregressive Transformers for Model-Agnostic Federated MRI Reconstruction (https://arxiv.org/abs/2502.04521)

Local harness substrate for project-scoped agent sessions.

Your all-in-one skills-as-a-service platform to manage your skills, auto-generate skills and use agent skills as simple as calling an API.

Official project website for the AAAI 2022 paper "Stereo Neural Vernier Caliper"

Operational Ontology Framework by FSTech — public reference for D+L+A, stateful AI governance and auditable operations. No production code.

NeurIPS 2025: Graph Your Own Prompt

GEMEX is a novel, model-agnostic Explainable AI (XAI) library grounded in Riemannian information geometry and differential geometry. It treats a trained model as defining a statistical manifold equipped with the Fisher Information Metric and derives all explanations from the intrinsic geometry of that manifold.

A model-agnostic library for generating explanations of machine learning predictions, supporting diverse XAI methods like CEM and LIME.