self-correcting

An open, natural-language DSL for self-correcting AI coding loops — say what an AI coding agent should build and how to verify it in plain English, and it loops until the check passes. Runs in Claude Code, Cursor, and Copilot.

oh-my-fable — Fable 5's way of working a long task (plan first, self-correct, never lose the thread), as a model-agnostic agent harness. The run lives in one serializable RunContext, checkpointed every step, so a crash is a pause. Zero deps, deterministically testable.

Self-correcting memory for LLM agents. A Claude Code plugin that learns from sessions, surfaces relevant memories, measures whether they're actually followed, and fixes the ones that aren't.

React hook for using self-correcting setInterval, augmented by management methods (start, stop, isActive)

Ultimate vibe coding plugins for Hermes AI agent — Effect-ts, LSP, Semble code search & Graphify knowledge graph + t/s status bar. 23 tools, 5 plugins, stdlib core.

CodegniPy is a groundbreaking Python library that elevates AI to a first-class citizen of the language. It introduces a cognitive computing engine where deterministic code and non‑deterministic LLM reasoning coexist seamlessly, enabling you to write Python with intent rather than just instructions.

Adaptive vector search with self-correcting embeddings. Fixes semantic collapse in RAG systems via spectral chelation, dynamic dimension masking, and neural adaptation.

A deterministic pipeline that diagnoses, explains, and safely auto-fixes failures in LLM agent systems.

GraphNews is a multi-agent system that acts as a self-correcting editorial team, generating newsletters

Agentic forecasting application with autonomous model selection, multi-indicator prediction, and self-correcting pipelines

🧬 ScienceProves.Me - A RAG-powered assistant that answers questions with high precision using scientific evidence.

Most AI writing is fluent slop. Writing Agent turns a topic into a publishable, well-sourced article or book that argues a real thesis and self-critiques until it isn't slop - autonomous, model-agnostic, local-first.

The simplest autonomous AI-agent loop that provably halts: goal, an unfakeable check, three hard stops, durable memory, in ~110 lines of bash. A foundation for loop engineering with Claude or any coding agent.

A self-directing agent loop that rehearses the conversation you're dreading — plan, act, observe, self-correct until it decides you're ready. Built for the Loop Engineering Hackathon.

Self-correcting data-analyst agent: ask a dataset a question in plain English and get runnable Python, SQL, or an Excel formula. Built on LangGraph + a local Qwen2.5-Coder LLM, with a generate→execute→reflect loop that fixes its own errors (measured: 75%→94% success).

📰 Automate news research and curation with GraphNews, a multi-agent system that ensures high-quality, factual content through self-correction.

Self-correcting Python coding agent: plan → generate → execute tests → fix → repeat. LangGraph loop with sandboxed subprocess execution. Supports Claude and GPT-4o.

Comparative study of two Agentic AI architectures for automated data science: hidden-tool agents vs transparent code-generating agents. Built with CrewAI, OpenAI GPT-4o, tested on Titanic & House Prices datasets.

A self-correcting multi-agent system that audits and actively fixes Kaggle notebooks. Powered by LangGraph and Gemini 2.5, it uses an autonomous feedback loop to improve code quality, documentation, and reproducibility scores in minutes.

An autonomous AI agent that writes Python code, catches its own errors, and self-corrects.