llm-tooling

RushDB is a graph + vector database and memory layer for AI agents. Push any JSON, get typed, searchable, relationship-aware records back — no schema, no migrations. Built on Neo4j.

Train your AI coders the way you'd train a vine — discover your codebase's actual patterns, then encode them as Claude Code rules, skills, agents, hooks, and a guided pipeline so generated code lands inside your conventions on the first try, not the fifth.

Better AI Predictions ⚡

A Claude Code skill that bridges Claude Code to the Codex CLI: externalizes plan, files, conversation and conventions into an on-disk bundle, runs codex exec, validates the JSON response with jq.

A budget-aware context compiler for coding agents - scan, grade, spark-test for secrets, and pour a hard-budget context pack with a stamped manifest.

Artifact-first agent framework — disciplined skill chain for AI-driven multi-step engineering tasks. MIT.

Self-hosted control plane for AI coding agents (Claude Code, Codex, Gemini, Ollama). Shared MCPs, reusable workflows, AI audit that makes any repo AI-friendly. Engineering, not prompting : smaller prompts, fewer hallucinations, lower token bill.

AI agent skills library built by OpenSite AI. A single git repo that keeps Claude, Codex, Cursor, Copilot, and Perplexity Computer in perfect skill sync, with persistent cross-session memory and automated cloud upload via Playwright.

An orientation protocol for LLM sessions — plus a curated Claude skills collection

A curated collection of WorkBuddy agent skills — academic pipeline, frontend slides, PPTX generator, tool-call repair, and more.

用 AI 开发 GEE 的免干预工作流：AI 写完 GEE 脚本后自己在本机连真服务器跑、看反馈、自己改，调通了再交付。适配 Claude Code / Codex / Cursor / Gemini CLI 等主流 AI 工具。

Template-aware development workflow plugin for Claude Code.

Stop fighting broken PDF tool calls. This watches a folder and converts any PDF to clean Markdown in seconds — fully local, no API key, no rate limits, no cloud dependency. Built for Obsidian "second brain" setups paired with Claude or any LLM assistant with filesystem access. Free forever.

A customized Claude Code fork for routed models, multi-agent orchestration, and dense terminal control.

A protocol for agent work that survives session boundaries — plan, implement, verify in sealed contexts, with proof bundles as the only currency between them.

A powerful Model Context Protocol (MCP) server and Omni-AST engine. It empowers AI agents to seamlessly parse complex codebases, execute secure cross-project operations, and dynamically fetch token-optimized rules.

Spec-driven development workflows for Claude Code — 14 commands, 6 agents, 3 hooks. Immutable specs, hard gates, phased pipelines for auditable AI-assisted coding.

The toolchain that stops AI coding agents from writing broken, deprecated code.

Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.

A Claude Code skill that turns every AI request into a clear, constrained and verifiable prompt before execution.