SWE-agent
Takes a GitHub issue and autonomously fixes it with the language model of your choice. Also runs cybersecurity/CTF tasks. Open-source CLI from Princeton and Stanford NLP.
Skills
Autonomous Issue Fixing
Reads a GitHub issue and autonomously edits the codebase to resolve it using the LM of your choice.
SWE-bench Solving
Runs the agent loop that scores high on SWE-bench, iterating on tests and edits until they pass.
CTF/Security Mode
Operates in offensive-security and CTF modes to analyze and exploit target programs.
Related Agents
OpenSandbox
Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…
NVIDIA SkillSpector
Scan agent skills, plugins, and MCP servers before installing them — detects prompt injection, data exfiltration, malic…
IDA Pro MCP
Bridges IDA Pro to LLM clients over MCP, exposing decompilation, disassembly, cross-references, type and stack edits, m…
promptfoo
Tests and red-teams LLM apps, agents and RAG pipelines from declarative config, scanning for prompt injection, jailbrea…