Reverse-engineering Claude Code's 512K LOC TypeScript source: agent loop, tool system, permission model, Grove training pipeline, anti-distillation defense
-
Updated
May 1, 2026 - Python
#
agent-loop
Here are 5 public repositories matching this topic...
Autonomous agent loop for Claude Code — decomposes a spec into tasks, executes them one per iteration with crash recovery and handoff context
-
Updated
Feb 6, 2026 - Python
[DEPRECATED] Codex skill for strict atomic-step execution; no longer maintained.
-
Updated
Apr 21, 2026 - Python
Build lightweight agent infrastructure for tool use, skills, memory, and multi-agent coordination with OpenHarness and ohmo
typescript ai interactive-learning ai-agent llm shadcn-ui ollama ai-infrastructure coding-agent agent-harness openclaw agent-loop harness-engineering ai-harness openharness
-
Updated
May 20, 2026 - Python
Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — DeepSeek gets its own 7-tool agent loop in a sandboxed workspace, not just a single LLM call.
mcp ai-agent deepseek llm-orchestration model-context-protocol claude-code token-optimization codex-cli agent-loop sub-agent
-
Updated
May 11, 2026 - Python
Improve this page
Add a description, image, and links to the agent-loop topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the agent-loop topic, visit your repo's landing page and select "manage topics."