model-agnostic

Open Science by AIPOCH is an open-source, local-first, model-agnostic AI research workbench for macOS, Windows, and Linux, with scientific agents, Python/R notebooks, data connectors, and reproducible provenance.

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

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]

Your AI friend right in your browser

clawdcursor compiles whatever's on screen into one UI map — accessibility tree and OCR fused into stable, addressable elements, with a screenshot only when needed — then drives apps through reusable scripts, verifying every action and routing it through a single safety gate.

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

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.

Open-source, model-agnostic coding agent CLI with subagents, skills, MCP, and plugins.

Local-first runtime for project-scoped AI coding-agent sessions, with durable state, authority boundaries, and multi-harness interoperability.

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

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

The orchestration layer under your coding agent. Turns work into a typed graph, runs one model per node, and takes the verdict from outside the model — exit codes, write-set checks, and a cross-family verifier. MCP server, 50 tools, bring your own models.

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

Open-source marketing skills that run on any model — with a hosted brand-memory engine. No coding agent required.

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

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

An AI Chief of Staff in plain markdown, in an Obsidian vault. Version two: torn down, rebuilt smaller, works better. Model agnostic, ADHD-first, open to anyone.

Approximate Inverse Model Explanations (AIME): model-agnostic XAI through an approximate inverse operator.

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.