Alternatives and similar repositories for debug-gym

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

• 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.
  ☆388Updated this week
• LLMSELECTOR / LLMSELECTOR
  ☆79Updated 2 months ago
• bentoml / llm-optimizer
  Benchmark and optimize LLM inference across frameworks with ease
  ☆141Updated 2 months ago
• alexzhang13 / rlm
  Super basic implementation (gist-like) of RLMs with REPL environments.
  ☆278Updated last month
• ScalingIntelligence / codemonkeys
  ☆59Updated 10 months ago
• invariantlabs-ai / explorer
  A better way of testing, inspecting, and analyzing AI Agent traces.
  ☆40Updated last month
• safety-research / petri
  An alignment auditing agent capable of quickly exploring alignment hypothesis
  ☆696Updated 2 weeks ago
• scaleapi / SWE-bench_Pro-os
  SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
  ☆223Updated 2 weeks ago
• All-Hands-AI / openhands-aci
  Agent computer interface for AI software engineer.
  ☆114Updated 2 months ago
• SWE-bench / SWE-smith
  [NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents
  ☆479Updated last week
• facebookresearch / matrix
  Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…
  ☆225Updated last week
• huggingface / skills
  ☆124Updated this week
• Aider-AI / polyglot-benchmark
  Coding problems used in aider's polyglot benchmark
  ☆194Updated 11 months ago
• google / lmeval
  ☆234Updated last week
• OpenHands / software-agent-sdk
  A clean, modular SDK for building AI agents with OpenHands V1.
  ☆224Updated last week
• laude-institute / harbor
  ☆152Updated this week
• teilomillet / retrain
  a Python library that uses Reinforcement Learning (RL) to train LLMs.
  ☆41Updated 4 months ago
• evalops / cognitive-dissonance-dspy
  A multi-agent LLM system for detecting and resolving cognitive dissonance.
  ☆269Updated last month
• invariantlabs-ai / playwright-computer-use
  Let Claude control a web browser on your machine.
  ☆39Updated 6 months ago
• avbiswas / context-engineering-dspy
  Context Engineering Course with DSPy
  ☆202Updated 4 months ago
• darinkishore / codex_dspy
  DSPy module for OpenAI Codex SDK - signature-driven agentic workflows
  ☆140Updated this week
• OpenHands / ToM-SWE
  The theory of mind module for the SWE agent
  ☆47Updated 2 weeks ago
• NVlabs / UniversalDeepResearch
  Code to accompany the Universal Deep Research paper (https://arxiv.org/abs/2509.00244)
  ☆450Updated 3 months ago
• janhq / verifiers-deepresearch
  Verifiers for LLM Reinforcement Learning
  ☆79Updated 2 months ago
• Ziems / arbor
  A framework for optimizing DSPy programs with RL
  ☆293Updated 3 weeks ago
• huggingface / smol2operator
  ☆123Updated 2 months ago
• SalesforceAIResearch / MCP-Universe
  MCP-Universe is a comprehensive framework designed for developing, testing, and benchmarking AI agents
  ☆507Updated last week
• ibm-granite / granite-guardian
  The Granite Guardian models are designed to detect risks in prompts and responses.
  ☆122Updated 2 months ago
• willccbb / claude-code-mcp
  Letting Claude Code develop his own MCP tools :)
  ☆123Updated 9 months ago
• SakanaAI / treequest
  A Tree Search Library with Flexible API for LLM Inference-Time Scaling
  ☆494Updated 2 weeks ago