AI Agents
autoresearch
karpathy/autoresearch
An autonomous research setup that lets AI agents experiment overnight on single-GPU LLM training to find better models.
Related projects
claw-code194.9kA Rust-built terminal coding agent that reads codebases, edits files, and runs tasks autonomously.
TradingAgents121.3kA multi-agent LLM trading system that mirrors a real firm with analysts, researchers, traders and risk managers.
pi121.2kA minimal extensible coding agent CLI with unified LLM access that reads code, edits files and runs tasks.
strix75kAn open-source agentic pentesting platform where teams of AI hackers find, exploit, and help fix app vulnerabilities.
cline71.5kAn open-source coding agent for IDE, terminal, and desktop that reads and edits code, runs commands, plans work, and coordinates multi-agent teams.
MetaGPT71.2kA multi-agent software development system that turns a one-line requirement into PRDs, designs, and a complete code repo.