microsoft / Trace
End-to-end Generative Optimization for AI Agents
☆561Updated last week
Alternatives and similar repositories for Trace:
Users that are interested in Trace are comparing it to the libraries listed below
- xLAM: A Family of Large Action Models to Empower AI Agent Systems☆425Updated 3 weeks ago
- ☆404Updated last week
- OO for LLMs☆720Updated this week
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆450Updated last month
- Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"☆512Updated last month
- AWM: Agent Workflow Memory☆269Updated 3 months ago
- Agentless🐱: an agentless approach to automatically solve software development problems☆1,656Updated 4 months ago
- TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle☆264Updated this week
- AIDE: AI-Driven Exploration in the Space of Code. State of the Art machine Learning engineering agents that automates AI R&D.☆884Updated 3 weeks ago
- AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and re…☆322Updated this week
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆437Updated 7 months ago
- Recipes to scale inference-time compute of open models☆1,066Updated 2 months ago
- Code for Quiet-STaR☆731Updated 8 months ago
- An agent benchmark with tasks in a simulated software company.☆340Updated this week
- ☆594Updated 3 months ago
- Code and Data for Tau-Bench☆472Updated 3 months ago
- ☆1,017Updated 4 months ago
- An intuitive LLM prompting framework for multifunctional agents, by explicitly constructing a complex "thought process" from simple natur…☆447Updated 4 months ago
- LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step☆525Updated 7 months ago
- Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"☆464Updated last year
- Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.☆170Updated last week
- MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering☆692Updated 3 weeks ago
- Code for Husky, an open-source language agent that solves complex, multi-step reasoning tasks. Husky v1 addresses numerical, tabular and …☆341Updated 10 months ago
- [ICLR 2025] Automated Design of Agentic Systems☆1,283Updated 3 months ago
- An Awesome list of curated DSPy resources.☆313Updated 2 months ago
- Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhan…☆1,126Updated 11 months ago
- Automatic evals for LLMs☆376Updated this week
- Tutorial for building LLM router☆202Updated 9 months ago
- MLGym A New Framework and Benchmark for Advancing AI Research Agents☆487Updated 3 weeks ago
- Attribute (or cite) statements generated by LLMs back to in-context information.☆229Updated 7 months ago