Havuz

AI Harness Engineering Template — guardrails, gates, and boundaries for AI coding agents. One-command install. Zero dependencies.

Self-hosted LLM security proxy. PII redaction, prompt injection defense, KVKK/GDPR/PCI-DSS compliance. Sub-millisecond latency

Public SDKs and integration contracts for Armorer Guard.

When Claude says “tests pass”, makoto checks the record — every claim held against the agent's own logged deeds; fakes blocked, not warned.

Fast, deterministic verifier and gate for AI agents: exact math, claim and citation checks, shell/write policy, hash-chained step ledger and

Agent observability and guardrails for OpenClaw — risk scoring, audit trails, dashboard.

Safe runtime for Claude Code, built to be yours.

A custom coding harness for TypeSafe AI's Jev: an LLM proposes, Jev answers narrow questions, code decides, every step leaves a receipt.

Lightweight RAG provenance middleware. Verifies every claim in an LLM response is grounded in a retrieved source - without an LLM call.

Validate and retry LLM outputs for ruby_llm. Describe the JSON response you expect, fall back to a stronger model when the cheaper one fails

AI makes users productive — but also cognitively lazy. Lucid detects cognitive dependency in real-time and adapts AI responses to keep users

The gate between an AI agent and real money. Runtime authorization for financial AI agents: structured intent, deterministic policy, human a

Self-hosted decision model (selfjev-4b) with a Jev-compatible API: Python SDK, server, fine-tuning and RLCD.

Local-first MCP policy proxy. Tool-block, SQL-mutation gate, PII redact, audit, rate-limit, OpenTelemetry, vault secrets, first-use quaranti

Python SDK for LLM guardrails with safety classification, PII detection, prompt injection defense, and grounding checks. Protect AI applicat

Workflow-agnostic guardrails for AI coding agents: spec sync + risk-triggered engineering discipline for Claude Code and Codex.

Bounded loops for coding agents: test gates, held-out acceptance checks, hard stops, git-backed resume

A lightweight, zero-dependency Python checkpoint layer for structured LLM output reliability.

⚖️ Kadı — a calibrated judge in front of your frontier LLM. Routine decisions answered locally with a conformal-prediction guarantee (≤ α di

Six skills tell coding agents how to work. Two guards enforce the parts that should not depend on judgment.

Make your specs actually comprehensive. Pair your specs with tests to make your coding agent stop improvising bad code

Guardrails for AI coding agents — block catastrophic tool calls before they run. Semantic, agent-neutral, near-zero false positives.

Command-line tool for TypeSafe's Jev AI model

Open-source control plane for private, governed enterprise AI — one gateway for every model, composable governed pipelines, and apps your wh

Framework-neutral control contract for AI agents: eight interception points, three verdicts, and a conformance kit.

Privacy and security guardrails for Spring AI: request-scoped PII tokenization, least-privilege disclosure to tools, and tool authorization

Real-time guardrail runtime for AI agents.

Budget caps, runaway-loop detection and circuit breakers for AI agents. Zero dependencies, framework agnostic.

Guardian Runtime sits securely on your machine, acting as a bodyguard for your code. Whenever you use AI tools like Cursor or Claude Code, i

Decisions, not essays: a choice, a yes or no, or a score with a calibrated probability. Open weights, Jev-compatible API, adaptive thinking.

SHACKLE — a governance protocol and policy-decision daemon for autonomous AI agents. Enforces guardrails, budget/loop limits, and policy con

NeuralForge is an end-to-end LLM fine-tuning & serving platform. It leverages LoRA (PyTorch/Hugging Face) for domain adaptation, cutting err

Open-source guardrails for AI agents powered by decision models like Jev; checks prompts, retrieved content, tool calls and responses for pr

A governance layer for Claude Code sessions: hooks that check an agent's commands before they run, a spec-first workflow, and project memory

Open-source AI gateway for LLM and agent traffic — multi-provider routing, guardrails, semantic caching and MCP support. Written in Go.

An MCP server that lets AI agents operate a multi-cluster Kubernetes fleet through an Open Cluster Management hub, with policy, approval, an

A lightweight toolkit for building secure AI systems with built-in middleware, protected memory, and AI safety models that mitigate prompt i

🛡️ Runtime guardrails for AI agents. Intercept and block unsafe tool calls caused by prompt injection.

Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing

a DSL for automated deterministic rules. Built for AI agents and quantitative Trading systems.

Coding-agent tools on TypeSafe's Jev, measured in public. review-router: caught 13 of 13 CVE fixes a filename rule sent to a quick review. j

Guardrails para desenvolver com agentes de IA: gate de CI bloqueante, hooks determinísticos, supply chain travada e fluxo de task com evidên

Score any AI for trust — Eval, Monitor, Govern. 10 trust dimensions, one free API key (5 credits / $500).

Smriti (स्मृति): private, local-first agentic RAG with System 1 + System 2 thinking over your notes, books and documents. Guardrails, tracin

Zero-dependency guardrail framework for AI agents. Stops runaway loops, prompt injection, hallucination and unsafe tool calls before they ex

Lightweight, agent-friendly AI security toolkit for Node.js & TypeScript. Check if your agent has loaded the skill, Stop prompt injection, a

x402 risk-check provider: signed pre-payment verdicts — OFAC, phishing feeds, transaction simulation, drainer-kit code, and our own EIP-7702

AI Agent watcher that helps developers/Agencies build from idea to launch while reducing token usage, preserving context,using 140 skills, a

3x more usage on your coding agent, same quality. Have an multi-agent setup in mind? Bello already supports it. Mix models, run agents in pa

Free local guardrail for AI coding agents: every tool_call judged on-device (regex + Laya), allow/review/block