SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

An Open-Source Asynchronous Coding Agent

Checks whether Kubernetes is deployed according to security best practices as defined in the CIS Kubernetes Benchmark

A simple SWE style browser agent framework that achieves SOTA results on long horizon web tasks.

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

A FREE pragmatic DevOps learning to kickstart your DevOps career and knowledge in the Cloud Native era following the Agile MVP style! ⭐ (2026 plans for DevOps, Cloud, Platform, SRE, SWE)

A self-learning skill layer for Claude Code that automatically distills, merges, updates, and prunes skills from real sessions.

Kodezi Chronos is a debugging-first language model that achieves state-of-the-art results on SWE-bench Lite (80.33%) and 67% real-world fix accuracy, over six times better than GPT-4. Built with Adaptive Graph-Guided Retrieval and Persistent Debug Memory. Model available Q1 2026 via Kodezi OS.

A Claude Code plugin that automates a multi-agent software development pipeline from feature spec to reviewed PR.

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.

Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.

Measuring frontier coding agents on original, long-horizon engineering tasks