Havuz

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.

Waku, yerel SQLite memory, agent loop ve eval araçlarını bir araya getiren, Python tabanlı kişisel AI assistant uygulamasıdır.

Neden yükseliyor · 79 günlük bir repo için 1.849 yıldızın yanında son 28 günde 30 commit ve 7 farklı yazar bulunması görünür ilgi ve devam eden geliştirme gösteriyor. README'nin sade, okunabilir agent loop ve entegre memory/eval yaklaşımı da projeyi agent harness arayan geliştiricilere çekici kılıyor; bu metrikler benimsenme veya üretim başarısını tek başına kanıtlamıyor.

Joy — a local-first personal assistant. Rust core (loop / memory / tools / graph / evals), TypeScript gateways + dashboard, Python thin SDK.

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.

Transcript analysis for long-horizon agent evaluations

🧪💥 Evaluation framework based on Vitest, the testing framework you familiar with, for agents, models, and more.

Run your real agent with and without your skills, MCPs, and rules. See which ones actually help, and what they cost in tokens. Supports Clau

Research-backed, eval-driven skills for AI agents

Behavioral eval lab (Quorum) for the superpowers project that drives real coding-agent CLIs (Claude, Codex, Gemini, Kimi, and more) through

Run Inspect AI evals in the cloud

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.

neatroots: see, check and replay your AI agent's runs on your machine while you build it. Local-first, by Neatlogs.

A composable framework for reproducible evaluation of long-running agents.

Open-source test harness for AI agents. Stress-test production agents with adversarial multi-turn scenarios in CI

Teach your agent to work with evals: WHEN you actually need an eval or benchmark, HOW to build one that holds up, and how to read what it te

Developer and product skills for Claude Code, Cursor and Codex: 1-file AI evals and Chrome extension store assets.

Mutation testing for your LLM evals — degrade the system under test and check whether your evals would actually catch a regression.

Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity re

Make AI agents aim higher without losing control: a Claude Code skill with two bars per task, a cheap gate check before expensive work, and

Cairn runs your AI and ML pipelines behind budgets, policy, approvals and an audit trail.

My Pi coding agent setup: secret redaction, LSP, searchable context, recall, telemetry, observability, and team mode. Toggle with /extension

Reproducible voice-AI benchmarking — TTS / STT / S2S latency and accuracy.

Benchmark, evaluate, and optimize skills to ensure reliable performance across all LLMs

Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

AI evaluators CLI for your AI apps and Agents - Dynatrace AI Observability

Benchmark coding agents and models on your own repository with private Harbor-formatted evals built from its merged pull requests.

CI for your coding-agent setup (CLAUDE.md, skills, hooks): pinned baselines, a canary on every Claude Code release, model and version matrix

Type-aware, evidence-backed delivery contract for AI coding harnesses. Different agents in. One predictable human handoff out.

Blind A/B testing for AI agent skills, .cursorrules, CLAUDE.md, and system prompts. Detects placebo and harmful instructions.

Benchmark LLMs head-to-head on your own prompts.

Your Evals Are Lying To You: a hands-on TypeScript curriculum for LLM evals, from a five-line assertion to a live diagnostic console. By Tej

Evidence-grounded evaluation for AI agents — verifies each claim against the agent's real tool outputs (constrained, evidence-grounded model

Two Claude Code skills for adversarial code review (single-model PAR and multi-model MMAR with cross-critique to catch hallucinations), plus

Personal AI agent on Cloudflare Workers: Durable Object per conversation, markdown memory in R2, vector recall in SQLite, fan-out deep resea

How do you KNOW if a 'skill' is any good - deterministically? This runs controlled skill-vs-no-skill experiments. It doesn't just ask, “Did

Claude Code/Codex skills, evals, harnesses/context tools, and learning resources that make it easy to build with Jev, TypeSafe's System One

Agent trace and tool-use safety evaluation lab.

Same model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open model

Phoenix-native LLM evaluation, prompt testing, model comparison, red teaming, and observability for Elixir

Make Claude Opus 4.8 behave like Claude Fable 5 — doctrine output style, drift-catching hooks, and an eval loop against golden Fable transcr

Skills for your skills. Create, test, audit, package, and visualize Agent Skill libraries—locally.

Catch AI agents that say "done" when the task isn't. Checks agent-trace/v1 traces with claim-evidence rules, LLM judges and a trained classi

Methodology and deterministic evaluation tools for iterative improvement of skills, repositories and agent workflows, with independent revie

Practical LLM evaluation for teams that ship to production. Deterministic + LLM-as-judge evaluators, dataset support, CI/CD integration.

Diff your AI agent's behavior between two runs. See exactly which tool calls, args, costs and outputs changed when you swap models or edit p

Canonical memory infrastructure: BM25 recall over trusted files for AI agents.

Eval-driven multimodal agent for identifying trees, logs, bark, leaves and wood from photographs. Dendrology is the reference domain; the e

A coding agent that builds it's own tools and mines it's own skills and always ships with receipts.

Red Team AI Benchmark: Evaluating LLMs for authorized offensive-security tasks

Fast, typed Python framework for Jev-as-a-Judge/Decision-model evaluation for LLMs, RAG, and AI agents along with human-label calibration.