Alternatives and similar repositories for SWE-Dev

Users that are interested in SWE-Dev are comparing it to the libraries listed below

• evalplus / repoqa
  RepoQA: Evaluating Long-Context Code Understanding
  ☆113Updated 9 months ago
• R2E-Gym / R2E-Gym
  Official repository for R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents
  ☆139Updated 3 weeks ago
• aorwall / moatless-tree-search
  ☆100Updated 2 months ago
• InternLM / SWE-Fixer
  ☆109Updated 3 months ago
• CodeEditorBench / CodeEditorBench
  ☆51Updated last year
• aorwall / moatless-testbeds
  Moatless Testbeds allows you to create isolated testbed environments in a Kubernetes cluster where you can apply code changes through git…
  ☆14Updated 4 months ago
• facebookresearch / cruxeval
  CRUXEval: Code Reasoning, Understanding, and Execution Evaluation
  ☆151Updated 9 months ago
• Yu-Fangxu / FoR
  [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
  ☆103Updated 2 weeks ago
• MLE-Dojo / MLE-Dojo
  ☆61Updated 2 weeks ago
• qishenghu / InstructCoder
  InstructCoder: Instruction Tuning Large Language Models for Code Editing | Oral ACL-2024 srw
  ☆62Updated 10 months ago
• SWE-bench / SWE-smith
  Scaling Data for SWE-agents
  ☆342Updated this week
• gonglinyuan / safim
  ☆36Updated 3 months ago
• amazon-science / llm-code-preference
  Training and Benchmarking LLMs for Code Preference.
  ☆34Updated 8 months ago
• scaleapi / plansearch
  e
  ☆39Updated 3 months ago
• open-compass / DevEval
  A Comprehensive Benchmark for Software Development.
  ☆111Updated last year
• r2e-project / r2e
  r2e: turn any github repository into a programming agent environment
  ☆129Updated 3 months ago
• THUDM / T1
  RL Scaling and Test-Time Scaling (ICML'25)
  ☆109Updated 6 months ago
• AlexCuadron / ThinkingAgent
  Systematic evaluation framework that automatically rates overthinking behavior in large language models.
  ☆91Updated 2 months ago
• Ablustrund / APPS_Plus
  StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback
  ☆67Updated 11 months ago
• microsoft / agent-lightning
  A server-client framework to train any AI agent with rollouts and feedbacks
  ☆207Updated this week
• Open-Source-O1 / o1_Reasoning_Patterns_Study
  ☆103Updated 8 months ago
• microsoft / SWE-bench-Live
  🚀 SWE-bench Goes Live!
  ☆104Updated 2 weeks ago
• ScalingIntelligence / Archon
  Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.
  ☆175Updated 5 months ago
• chr26195 / PENCIL
  This is the official implementation for paper "PENCIL: Long Thoughts with Short Memory".
  ☆58Updated 2 months ago
• HKUNLP / critic-rl
  [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning
  ☆105Updated 3 months ago
• THU-KEG / Agentic-Reward-Modeling
  [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
  ☆99Updated last month
• THUDM / NaturalCodeBench
  NaturalCodeBench (Findings of ACL 2024)
  ☆68Updated 9 months ago
• thunlp / Optima
  Code for paper "Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System"
  ☆59Updated 8 months ago
• QwenLM / CodeElo
  CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings
  ☆47Updated 6 months ago
• WHGTyen / BIG-Bench-Mistake
  A dataset of LLM-generated chain-of-thought steps annotated with mistake location.
  ☆81Updated 11 months ago