Alternatives and similar repositories for debug-gym

Users that are interested in debug-gym are comparing it to the libraries listed below

• LLMSELECTOR / LLMSELECTOR
  ☆80Updated 3 months ago
• SWE-agent / SWE-ReX
  Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.
  ☆409Updated last week
• bentoml / llm-optimizer
  Benchmark and optimize LLM inference across frameworks with ease
  ☆155Updated 4 months ago
• ScalingIntelligence / codemonkeys
  ☆59Updated 11 months ago
• All-Hands-AI / openhands-aci
  Agent computer interface for AI software engineer.
  ☆115Updated last month
• google / lmeval
  ☆236Updated last month
• SakanaAI / treequest
  A Tree Search Library with Flexible API for LLM Inference-Time Scaling
  ☆512Updated last month
• invariantlabs-ai / explorer
  A better way of testing, inspecting, and analyzing AI Agent traces.
  ☆40Updated last week
• evalops / cognitive-dissonance-dspy
  A multi-agent LLM system for detecting and resolving cognitive dissonance.
  ☆271Updated 3 months ago
• tom-doerr / mnist_dspy
  ☆36Updated 11 months ago
• facebookresearch / matrix
  Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…
  ☆256Updated last week
• philschmid / code-sandbox-mcp
  ☆195Updated 5 months ago
• MaximeRivest / functai
  ☆85Updated 4 months ago
• microsoft / promptpex
  Test Generation for Prompts
  ☆148Updated this week
• laude-institute / harbor
  Harbor is a framework for running agent evaluations and creating and using RL environments.
  ☆381Updated this week
• METR / eval-analysis-public
  Public repository containing METR's DVC pipeline for eval data analysis
  ☆183Updated this week
• NVlabs / UniversalDeepResearch
  Code to accompany the Universal Deep Research paper (https://arxiv.org/abs/2509.00244)
  ☆458Updated 4 months ago
• microsoft / mcp-interviewer
  Catch MCP server issues before your agents do.
  ☆138Updated last month
• safety-research / petri
  An alignment auditing agent capable of quickly exploring alignment hypothesis
  ☆804Updated last week
• metauto-ai / HGM
  🧬 The Huxley-Gödel Machine
  ☆317Updated last month
• teilomillet / retrain
  a Python library that uses Reinforcement Learning (RL) to train LLMs.
  ☆42Updated 5 months ago
• alexzhang13 / rlm-minimal
  Super basic implementation (gist-like) of RLMs with REPL environments.
  ☆435Updated last week
• OpenHands / software-agent-sdk
  A clean, modular SDK for building AI agents with OpenHands V1.
  ☆432Updated this week
• SWE-bench / SWE-smith
  [NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents
  ☆514Updated last week
• hcompai / surfer-h-cli
  Run Surfer-H agents powered by Holo1 using the Surfer-H-CLI. Includes example tasks, scripts, and configurations.
  ☆146Updated last month
• Aider-AI / polyglot-benchmark
  Coding problems used in aider's polyglot benchmark
  ☆199Updated last year
• OpenHands / ToM-SWE
  The theory of mind module for the SWE agent
  ☆67Updated this week
• darinkishore / codex_dspy
  DSPy module for OpenAI Codex SDK - signature-driven agentic workflows
  ☆148Updated last month
• microsoft / wina
  ☆148Updated 5 months ago
• janhq / verifiers-deepresearch
  Verifiers for LLM Reinforcement Learning
  ☆80Updated 4 months ago