jd-opensource/joycode-agent
Repository-level Repair Agent Based on SWE-Bench—JoyCode Agent
It employs a multi-agent architecture with specialized roles for testing, patching, and decision-making, operating within a React-based "Observe-Think-Act" loop. The pipeline collaboratively generates and validates patches and tests using containerized Docker environments, integrating with various LLM providers (e.g., OpenAI, Anthropic) for different stages of the process.
325 stars.
Stars
325
Forks
20
Language
Python
License
MIT
Category
Last pushed
Oct 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/jd-opensource/joycode-agent"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TracecatHQ/tracecat
AI-native automation platform for security teams. Purpose-built for agents. Open source for builders.
coze-dev/coze-loop
Next-generation AI Agent Optimization Platform: Cozeloop addresses challenges in AI agent...
j3ssie/osmedeus
A Modern Orchestration Engine for Security
SWE-agent/SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It...
AgentOps-AI/agentops
Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with...