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 16 public repositories matching this topic...
AI-native resume workspace — chat with an agent that edits your resume, design layouts with live preview, and practice mock interviews.
html resume agent tex job-search faiss rag fastapi mock-interview vitejs ai-agent llm function-calling agent-loop
-
Updated
Jun 5, 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
Jun 1, 2026 - Python
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
AI-curated, self-updating directory of MCP servers. Discovered from GitHub & the official registry, analyzed and ranked by AI weekly.
agent ai mcp loop awesome-list github-models model-context-protocol mcp-servers agentic-loop ai-curated agent-loop
-
Updated
Jun 9, 2026 - Python
Structured runtime for AI agent loops — safety ceilings, deterministic resume, human approvals, and full tracing built in.
-
Updated
Jun 11, 2026 - Python
POC: self-improving agent-loop pattern (trace -> eval -> handoff) applied to Danish tax deduction classification. Reference implementation inspired by OpenAI/Thrive Tax AI.
-
Updated
May 28, 2026 - Python
Production-grade Python LLM agent harness AND a framework-design case study. Tool loop, MCP, sandbox, sub-agents. 17 phases in 23 days.
python cli ai mcp sandbox multi-agent case-study tool-use llm llm-agent model-context-protocol vibe-coding claude-code agent-harness agent-loop
-
Updated
Jun 9, 2026 - Python
Pure Python implementation of a ReAct agent loop, vector routing, memory tracking, and cost analytics from first principles. Mirrors a 6-page "AI by Hand" worksheet with handwritten scans, programmatically verifying sequential reasoning tokens, tool matching via explicit cosine similarity, and context explosion costs without frameworks.
first-principles cosine-similarity pure-python causal-inference react-agent ai-by-hand llm-mechanics agent-loop
-
Updated
Jun 9, 2026 - Python
金融研报 Agent - 覆盖全部A股和公募基金
-
Updated
Jun 8, 2026 - Python
Learn how AI agents work by building them from scratch. Two working Python agents: interactive (agent.py) and autonomous (daily_digest.py). Uses Claude API with Gmail, calendar, files, and web search.
-
Updated
May 26, 2026 - Python
[DEPRECATED] Codex skill for strict atomic-step execution; no longer maintained.
-
Updated
Apr 21, 2026 - Python
Mochu (磨杵) — an autonomous product-team iteration loop for Claude Code. One invocation runs a full cycle: competitive recon, gap analysis, verifier authoring, implementation, verified shipping. Zero human prompting.
regression-testing test-driven-development product-management claude autonomous-agent ai-agent ai-coding-tools claude-code claude-skills agent-loop
-
Updated
Jun 10, 2026 - Python
Ouroboros bounded-recursion runtime — agentic loops, dual-witness emitters, governance budgets. Doctrine v11 LOCKED (749/14/163)
runtime convergence compliance airgap governance uds formulas apache-license dsse agentic-ai defense-tech bounded-recursion agent-loop proof-chain szl-holdings dual-witness bekenstein doctrine-v11 slsa-l1
-
Updated
Jun 12, 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
Jun 12, 2026 - Python
Book-grounded coding agent. Orient, Retrieve, Plan, Execute, Verify loop with citations from a Librarian index. Claude Code skill plus CLI.
python verify citation nuclide librarian rag engineering-principles ai-agent anthropic anthropic-claude llm-agent plan-tree hybrid-rag claude-code coding-agent claude-code-skill agent-loop orient-retrieve-plan-execute-verify
-
Updated
Jun 8, 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."