Havuz

Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they exe

Future AGI, LLM ve AI agent uygulamalarını değerlendirme, izleme, simüle etme ve koruma işlerini self-host edilebilen tek bir platformda birleştiriyor.

Neden yükseliyor · Konu, agent uygulamalarında evaluation ve observability ihtiyacının artmasıyla örtüşüyor; 157 günlük repo yaşına karşılık 2.081 yıldız ve son 28 günde 597 commit geliştirme temposuna işaret ediyor. Farklı yazar sayısı 6; bu veriler ilginin nedenini tek başına kanıtlamaz ve yıldızlar benimseme ya da kalite ölçüsü değildir.

FailproofAI, farklı AI agent harness’lerindeki çalıştırmaları izleyen ve tehlikeli tool çağrılarını yürütülmeden önce policy ile engelleyebilen bir araçtır.

Neden yükseliyor · 175 günlük bir repo için 5.166 yıldız ve son 28 günde 84 commit ile 8 farklı yazar, hem belirgin ilgiye hem de yakın dönem geliştirme faaliyetine işaret ediyor. Çok sayıda harness için ortak observability ve enforcement sunma iddiası, agent araçlarının çeşitlendiği dönemde dikkat çekici; yıldızlar tek başına benimseme veya kalite kanıtı değil.

Stop That Shit, AI coding agent’ların izinsiz kapsam genişletmesini ve gereksiz savunma kodu eklemesini Skill kuralları ve platform Hook’larıyla sınırlamaya çalışır.

Neden yükseliyor · AI coding agent’ların gereksiz iş üretmesi ve kullanıcıların sınır koyma ihtiyacı güncel, anlaşılır bir sorun. Repo 47 günde 2304 yıldız almış; son 28 günde 37 commit ve 3 farklı yazar aktiviteye işaret ediyor. Yıldızlar ilgi göstergesidir, gerçek kullanım veya etkililik kanıtı değildir.

An opinionated, curated list of tools for enforcing software development standards: one recommended tool per job, with limits.

Open-source AI gateway for LLMs & AI agents, built in Rust. One OpenAI-compatible API for OpenAI, Anthropic, Gemini, Bedrock & more — routin

jevals, agent trace'lerini eval ve guardrail kontrollerinden tek istekte geçirerek production veya agent loop içinde değerlendirmeyi amaçlayan bir Python kütüphanesidir.

Neden yükseliyor · 7 günlük bir repoda 97 yıldız, 5 commit ve 4 farklı yazar erken ilgi ve katkı işareti. Tek istekte birden fazla kontrol, düşük maliyet ve agent loop'a uygun hız iddiaları dikkat çekiyor; performans ve maliyet rakamları README'de verilmiş, bağımsız doğrulama olarak kabul edilmemeli.

The open-source trading harness for Claude Code / Codex agents.

jevmem saves the decisions, rules and failed approaches from your Claude Code chats to JEVMEM.md in your repo, and brings the relevant ones

🕷️ The fastest open-source AI Gateway and LLM Gateway — one binary with built-in console to route, secure, budget and observe every LLM call

Deterministic safety solutions for probabilistic AI agents

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

白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。

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

Open-source platform for AI chat agents that answer from your own knowledge base. Hybrid RAG search in PostgreSQL, MCP and custom tools, gua

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

Coding agent’lara TypeSafe AI Jev ile typed decisions ve calibrated confidence kullanmayı öğreten, topluluk projeleri ve code sketch’leri içeren bir agent skill’idir.

Neden yükseliyor · İki günlük yaşında 69 yıldız almış; bu erken ilgiye işaret ediyor. Ancak son commit ve farklı yazar verisi ölçülmediğinden ilginin kaynağı ve proje aktivitesi hakkında daha güçlü bir çıkarım yapılamaz.

DodoGuard: Take AI Agents to Production. Test, validate, and operate AI Agents before and after deployment.for Dify, Coze, FastGPT, n8n, Ten

Context bomb strings

Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger,

Zero-leak online detection of LLM decoding corruption and Free Web Search for your AI agents! Catch repetition loops, language drift and gar

Runtime enforcement boundary for AI agents: a local sidecar that gates every outbound call against Cedar policies you own. Deterministic, ca

AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」（网安法·PIPL·等保2.0·数据出境·AI标识），并给出境内模型替代建议；可作运行时防护拦截注入与数据外泄 · 中文优先 · 零依赖 · 开源

NeMo Helix: Make the agents you ship faster, more accurate, and safer.

Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

An orchestration runtime for multi-agent AI systems. Declare agents, tools, and policies as YAML; Orloj schedules, executes, routes, and gov

Automated Proof-of-Carrying Change Management for AIOps 2026

Offline-first Python AI agent that runs a tiny research business: quotes each job against its own costs, collects via Stripe, fulfils with N

Composable data security plane for Model Context Protocol. Pluggable layers — collect, analyze, guard — across 50+ enterprise providers. Ope

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.

A Claude Code mod that holds subagent fan-out, heavy-context prompts and retry loops before they spend your usage window. It reads your plan

Provenance-aware runtime security for AI agents with deterministic ALLOW / REVIEW / BLOCK enforcement.

Don't make LLMs honest. Make every factual claim auditable. — An LLM Claim Auditing Layer with T1-T7 truth gradients. 98.1% business effecti

Deterministic telemetry & control plane for multi-agent AI systems. Atomic POSIX JSONL event bus, W3C/OpenTelemetry DAG reconstruction, and

Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo: an

Knowledge-enhanced multimodal Fire Safety Agent with two-hop reasoning, evidence-tree RAG, open-set guardrails, and four-layer memory.

Open source authorization engine for AI agents. Confidence-aware gating · Human-in-the-loop review · Policy-as-code · Full audit trail

Radicalbit AI Gateway

Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero dep

Hook-driven multi-agent CLI — one prompt to specs, code, tests, and a shipped release.

Code samples for building AI applications on AWS with Amazon Bedrock, including Converse API, tool use, RAG with Knowledge Bases, guardrails

The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.

Self-hosted PII redaction proxy for LLM APIs and agent CLIs. Scrubs names, emails and secrets from Claude Code, Codex and any OpenAI-compati

Clyro is a governance platform for AI agents. While most tools let you watch agents fail, Clyro stops failures before they happen, catching

Get Claude Code and other AI agents approved for use at work — deterministic guardrails on every tool call, tamper-evident audit logs, and a

Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate,

DeepSeek Harness gate - per-turn persistent-operation counter: remind, instruct the model to stop, then ask for confirmation. Steps aside un

AI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacks

Fable-style spec + evidence gate for Claude Code + Codex. Makes Opus/Codex work under Fable-like discipline: blocks every edit until a deter