Rails

Your AI coding agent is only as reliable as the harness around it. Measure that harness in seconds with harness-score.

Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deterministic spec passes, and there is no "done" without live acceptance evidence. Spec-first, verification-gated, forbidden-paths enforced.

Skill repository to enforce Engineering disclipline in coding assistants

fak — the Fused Agent Kernel: one Go binary that turns a tool-using agent (Claude Code, Codex, Cursor, any OpenAI/Anthropic/MCP client) into a managed agent: cache-stable model traffic, context compaction + crash resume, nanosecond tool-call policy, local GGUF serving with SSD expert offload.

Real-time secret-leak guardrails for AI coding agents (Claude Code, Codex), Git hooks, and CI.

🧭 Let your coding agent off the leash — not off the rails. Guardrails, a hard budget cap & a self-fixing PR loop for Claude Code / Codex / Gemini. Eval-gated 100/100, you always merge.

Drop-in replacement for Sidekiq + Pro + Enterprise. 100% API-compatible, free forever, fork-based multi-core swarm. Mountable Rails engine.

A managed, orchestrated harness for running Claude Code as a safe, repeatable agent: hooks, guardrails, slash commands, a Jira CLI, and a cross-session handover system.

Secure MCP server for safe, read-only DB access by AI agents, with SQL guardrails, table allowlists, PII masking, and audit logs

Hands-on Generative AI: 15 RAG modules from document loaders to guardrails, plus Papeer — a research paper assistant with citations and claim verification. Also LangGraph workflows and LangSmith tracing.

LidRun keeps your Mac awake with the lid closed — so Claude Code, Cursor, Docker and Ollama keep running with timers, charging-only mode, low-battery stop and battery/thermal guardrails.

Install LidRun Free with Homebrew — the macOS menu-bar app that keeps AI agents and long-running dev jobs alive on a Mac even with the lid closed (clamshell), with battery + thermal guardrails so nothing cooks or drains.

Stateful agentic engineering workflow for local coding agents

An Agentic RAG-powered chatbot delivering intelligent, fact-grounded and context-aware answers for the DIEM Department at the University of Salerno.

A structured Claude Code agent setup with guardrails — drop in your requirements, get production-ready code that follows your standards every time.

Starter AGENTS.md - conventions and guardrails for AI agents working on your codebase

EvalBot — local-first chatbot security & quality evaluation (FastAPI + Next.js). Evaluate chatbot answers against your own docs & guidelines with ML/NLP + AI-judge scoring. Apache-2.0.

Claude Code plugin marketplace: opinionated workflows for code (dev-workflow — Rails & Python, TDD + pre-commit gate) and non-code (craft-workflow — design, content, research).

The trust control plane for enterprise AI agents — real-time policy verdicts in under 800ms and litigation-grade evidence of every decision. Pharos decides. Pharos proves.

One config for every AI coding agent — cross-tool config + a cognitive substrate (memory, blast-radius, guardrails) for Claude Code, Codex, Cursor, Gemini, Aider, and more.

The authorization layer for AI agents — allow/deny/ask policy, human approvals, and tamper-evident receipts on every tool call. Zero-dep, framework-neutral, no SaaS.

An audit gate for AI agent outbound messaging: hold the draft, let a senior agent review it (no private-data leak, prompt-injection resistance), then release. Reference implementation.

Evidence router & policy engine for coding agents — enforces source choice and proof-of-use through Claude Code hooks, including routes to MCP tools. Local-first; no LLM in the hook loop.

AI Guardian Firewall — a local, user-space, agent-agnostic firewall that mediates an autonomous AI agent's actions (files, shell, network, services) with a deterministic policy boundary, a tamper-evident audit log, and a human-in-the-loop approval cockpit. No kernel modules. Apache-2.0.

AI-powered multi-agent clinical decision support system built with Azure OpenAI, Semantic Kernel, RAG, and FHIR — enabling intelligent diagnosis, treatment planning, and healthcare workflow automation

Building smart, scalable AI agent systems. Harness AI. Reclaim Time. Amplify Impact.

A practical workbench of tools + methodology for solo devs driving an AI coding agent (Claude Code, Cursor, Copilot): safety hooks, secrets crypto, invariant + test-selection tooling, leak scanner, plus skill & memory system templates.

A drop-in CLAUDE.md starter and a guide to getting better HTML artifacts out of coding agents. HTML, not Markdown — that's the point.

Fonctionnalité : Analyser et transformer des récits — qu'ils soient personnels (récit de soi bloquant) ou collectifs (discours, organisation, situation stratégique) — en identifiant les structures narratives sous-jacentes, les archétypes actifs, et en produisant soit une réécriture symbolique du récit, soit des scénarios d'évolution prospectifs.

experimenting with claude guard rails and skills