mlfoundations / GelatoLinks
🍨 Gelato — From Data Curation to Reinforcement Learning: Building a Strong Grounding Model for Computer-Use Agents
☆37Updated last month
Alternatives and similar repositories for Gelato
Users that are interested in Gelato are comparing it to the libraries listed below
Sorting:
- AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents☆37Updated 4 months ago
- Proteus is an experimental platform that combines the power of Large Language Models with the Genesis physics engine☆25Updated last year
- The official repo for “Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem” [EMNLP25]☆34Updated 5 months ago
- Computer Agent Arena: Test & compare AI agents in real desktop apps & web environments. Code/data coming soon!☆53Updated 10 months ago
- ⚔️ [ICLR 2026] Official code of "Search Arena: Analyzing Search-Augmented LLMs".☆49Updated 2 weeks ago
- [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆102Updated 5 months ago
- ☆17Updated last year
- GPT-4 Level Conversational QA Trained In a Few Hours☆65Updated last year
- Code for Paper: Harnessing Webpage Uis For Text Rich Visual Understanding☆53Updated last year
- Code for the paper "Coding Agents with Multimodal Browsing are Generalist Problem Solvers"☆97Updated 3 months ago
- The Library for LLM-based multi-agent applications☆102Updated 6 months ago
- ☆18Updated 9 months ago
- The theory of mind module for the SWE agent☆73Updated 3 weeks ago
- Tcurtsni: Reverse Instruction Chat, ever wonder what your LLM wants to ask you?☆23Updated last year
- ☆87Updated last year
- Challenges for general-purpose web-browsing AI agents☆67Updated 8 months ago
- Lightweight OpenHands CLI in a binary executable☆100Updated this week
- ScreenSuite - The most comprehensive benchmarking suite for GUI Agents!☆137Updated 4 months ago
- ☆57Updated last year
- LIMI: Less is More for Agency☆160Updated 3 months ago
- ☆39Updated last year
- ☆67Updated 10 months ago
- Visual Tagger is a JavaScript tool that visually highlights HTML elements for AIs, aiding in identifying interactive components on web pa…☆11Updated last year
- [NAACL2025] LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications☆143Updated 7 months ago
- ☆88Updated 8 months ago
- Yet another frontend for LLM, written using .NET and WinUI 3☆10Updated 4 months ago
- entropix style sampling + GUI☆27Updated last year
- C^3-Bench: The Things Real Disturbing LLM based Agent in Multi-Tasking☆37Updated 7 months ago
- Get aid from local LLMs right in your PowerShell☆15Updated 9 months ago
- ☆19Updated 11 months ago