let it loop (LIL): Deterministic AI engineer for complex coding. Hybrid LLM+Python with CONTRACT SYSTEM parsing intent, decomposing goals, enforcing checks, deterministic Python orchestration. Durable
let it loop (LIL) is an autonomous macro-task orchestration and verification control loop for AI coding agents. It provides a durable, production-grade execution backbone featuring automated DAG contract planning, crash-resilient supervisor execution (Write-Ahead Logging), deterministic multi-phase verification, multi-lens quality reviews, and universal Model Context Protocol (MCP) support.
- Autonomous DAG Planning: Decomposes natural language objectives into cryptographically scoped, strongly-typed JSON contract dependency graphs with cycle detection. - Fault-Tolerant Supervisor Loop: State journal with WAL (Write-Ahead Logging), crash recovery, Win32/POSIX atomic file-locking, and bounded 3-strike retries with strategy mutation. - Zero-Trust Verification Engine: 8 distinct deterministic acceptance check kinds (AST syntax parsers, command exit-code assertions, regex matchers, file validators, size bounds, and undeclared output detectors). - Multi-Lens Quality Plane: Multi-perspective evaluation with 5 specialized lenses (Code Correctness, Security Hardening, Documentation Fidelity, Test Completeness, Adversarial Architecture Audit) and formal arbitration. - Native Model Context Protocol (MCP) Server: 8 stdio JSON-RPC tools connecting directly with Claude Code, OpenAI Codex, Cursor, Google Antigravity, Hermes Agent, OpenCode, Cline, and Windsurf. - 10 Pluggable Worker Adapters: Native execution interfaces for Claude Code, OpenAI Codex, Google Antigravity (agy), OpenCode, Hermes Agent, Cline, Aider, Omniroute gateways, local scripts, and direct LLMs. - Zero-Subscription In
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/sdageltc--letitloop.html)
Open-source client for Novgraph, Novaya's proprietary hosted code knowledge graph. Gives coding agents recorded intent, related-code context, ranked change impact and architecture context over MCP or
PyModel/jev-judge-mcpTyped judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, o
24KaratAu/openhubTerminal discovery hub and package manager for AI coding tools, MCP servers, and agent skills. Built with Python & Textual
ozankasikci/global-agent-memoryLocal-first, project-aware memory MCP server for Claude Code, Codex, and other AI agents, with Obsidian and an owner dashboard.
vsh5dvsch7-png/yueyingLet AI watch videos: local files or YouTube/Bilibili URLs -> timestamped transcript + keyframes + contact sheets. Offline, no API key. MCP server + CLI + agent skill.
unempyd/revenueosConnect your business. RevenueOS finds opportunities, executes approved revenue work, and measures what happened. Self-hosted, MIT.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.