OpenAutoCoder / AgentlessLinks
Agentless🐱: an agentless approach to automatically solve software development problems
☆1,986Updated last year
Alternatives and similar repositories for Agentless
Users that are interested in Agentless are comparing it to the libraries listed below
Sorting:
- ☆617Updated 3 months ago
- LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step (ACL'24)☆572Updated last year
- Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhan…☆1,502Updated last year
- [ICLR 2025] Automated Design of Agentic Systems☆1,477Updated 10 months ago
- AgentCoder: multi-agent code generation framework.☆368Updated last month
- AIDE: AI-Driven Exploration in the Space of Code. The machine Learning engineering agent that automates AI R&D.☆1,099Updated last month
- Code and Data for Tau-Bench☆1,033Updated 4 months ago
- End-to-end Generative Optimization for AI Agents☆699Updated 2 weeks ago
- Agent driven automation starting with the web. Try it: https://www.emergence.ai/web-automation-api☆1,195Updated 6 months ago
- A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 37.3% tasks (pass@1) in SWE-be…☆3,044Updated 8 months ago
- OO for LLMs☆883Updated last week
- An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickl…☆863Updated last year
- An agent benchmark with tasks in a simulated software company.☆611Updated last month
- [NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"☆637Updated 9 months ago
- An self-improving embodied conversational agent seamlessly integrated into the operating system to automate our daily tasks.☆1,713Updated last year
- 👩⚖️ Agent-as-a-Judge: The Magic for Open-Endedness☆693Updated 7 months ago
- Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024☆1,661Updated 2 months ago
- MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering☆1,236Updated last week
- Streamlines and simplifies prompt design for both developers and non-technical users with a low code approach.☆1,129Updated 2 months ago
- SWE-bench: Can Language Models Resolve Real-world Github Issues?☆4,017Updated last week
- The #1 open-source SWE-bench Verified implementation☆843Updated 6 months ago
- Code for "WebVoyager: WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models"☆985Updated last year
- Optimizing inference proxy for LLMs☆3,250Updated this week
- 🌎💪 BrowserGym, a Gym environment for web task automation☆1,046Updated last week
- ☆434Updated last year
- Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.☆396Updated this week
- This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software E…☆1,438Updated 5 months ago
- Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.☆802Updated 7 months ago
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆607Updated 4 months ago
- [NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments☆2,411Updated this week