Havuz

Spec-Driven Development framework that enables humans and AI agents to build better software by giving them small, local instructions right

Your own design studio inside the coding agent you already use.

Autoresearch agents that improve your benchmark: independent re-measurement, enforced budgets, results as pull requests

A constitution generator for autonomous, agent-run projects: an interview-driven meta system prompt (and installable skill) that scaffolds a

BuildArena: Physics-grounded Besiege Building for LLMs

Companion repo for Agentic Graph RAG (O'Reilly, Anthony Alcaraz & Sam Julien) — 50 runnable skills + 8 pedagogical notebooks covering all ei

AgentBehaviorBench (ABB): A benchmark for evaluating AI agents’ ability to test other agents and detect behavioral defects.

SWE-Serve: an agentic benchmark of 53 production inference-engineering tasks derived from merged SGLang pull requests, run with Harbor.

Portable AI memory powered by knowledge graphs. Transform conversations into a persistent, explorable knowledge graph and give any LLM long-

The control layer for agentic AI. A protocol-aware proxy that applies identity, policy, trust and payment controls to A2A, MCP and DIDComm t

Lossless context folding for the Pi coding agent: only the oldest context changes; the fresh window stays untouched.

Open-source AI interior design agent. Turn room photos into scaled floor plans, wall elevations, photoreal renders and a design report where

SciPIvot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents

An MCP server built on top of Huawei Training Camp (HTC) APIs, enabling AI agents to access and analyze Huawei Health training data.

WikiSkill, agent oturumlarından kalıcı wiki bilgisi derleyip skill değişikliklerini doğrulama testleriyle kabul veya geri alan bir Python aracıdır.

Neden yükseliyor · Agent'lar için kalıcı bilgi ve self-improvement ilgisinin yüksek olduğu bir dönemde, araştırma makalesindeki döngüyü gerçek agent çalıştırmalarıyla uygulanabilir bir araca dönüştürdüğünü öne sürüyor. 29 günlük yaşına göre 250 yıldız ve son 28 günde 22 commit dikkat çekici; ancak yalnızca 2 farklı yazar var ve yıldızlar kullanım ya da etkinin kanıtı değil.

deedchain, browser agent raporlarındaki iddiaları kaydedilmiş ground truth ile karşılaştırarak rapor doğruluğunu ölçen bir benchmark ve Python kütüphanesidir.

Neden yükseliyor · Repo yalnızca 23 günlük ve 28 yıldızlı; son 28 gün commit ve farklı yazar verisi ölçülmediği için yükselişin arkasındaki aktivite veya benimsenme düzeyi doğrulanamıyor. Rapor doğruluğunu ayrı bir değerlendirme konusu yapması dikkat çekici olsa da README'deki “first benchmark” iddiası bağımsız olarak doğrulanmış değil.

IvyClaw, yazılım geliştirme görevlerini birden fazla AI agent, araç ve sandbox kullanarak uçtan uca yürütmeyi hedefleyen Python tabanlı bir sistemdir.

Neden yükseliyor · Repo 15 günlükken 61 yıldız almış; bu, kısa sürede ilgi gördüğünü gösteriyor. Ancak son 28 günde 4 commit ve 1 farklı yazar var. İlginin kaynağına veya benimsemeye dair ek kanıt yok; yıldızlar tek başına üretim olgunluğunu doğrulamıyor.

More is Different. A multi-agent world engine where AI agents live, talk, compete, ally.

verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.

[Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluatio

Open protocol for AI agent work contracts and verifiable execution — authorization, evidence, and acceptance for multi-agent systems

A living AI-agent office on your desktop wallpaper — Claude Code agents that walk, work, delegate, learn & hold meetings. Per-agent swappabl

Open-source alternative to Claude Co-Work built by Claude. with BYOK

AI World Generator 2026: Create Self-Evolving Maps & Stories

Drop-in prompt-caching fixes for the LLM agent harness you use. Point your AI coding agent at this repo and it ships the patches.

Self-hosted AI workspace with agents, skills, and tools (Gmail, Calendar) that runs entirely on your own provider API keys (BYOK). Bring you

SDK, skills, and examples for Inkbox: give AI agents a persistent identity with email, phone number, and internet address

EurekAgent: an autonomous research system for metric-driven tasks, built with Claude Code. Define the problem and metric. Get breakthrough r

Self-hosted personal AI agent with a WebUI, memory, tools, MCP, sub-agents and automations. Connect local or cloud LLMs.

A git-native, review-gated knowledge base for AI agents: they propose writes, you approve them. Every claim cites a source, every change is

Jetpack Compose & Kotlin AI agent skills for Cursor, Claude Code, Codex, Gemini & 27+ agents. Strict MVI · Kotlin 2.x K2 · Compose 2026 · CI

Claude Code plugin for autonomous AI research — multi-agent loops take a bare topic all the way to running experiments, with no human-writte

Kit is a coding agent runtime. Claude Code but faster, cheaper and more to the point 🎯

Where agents build agents. An open-source Rust framework for complex agentic systems: ontology-grounded, auditable, one binary.

给AI伴侣增强时间感的小器官（电脑端专用）

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

Benchmarking data agents for verifiable analytics over heterogeneous workspaces.

Reproduction package for "Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity" — ten agent arms across AppWorld an

RimZ is a realtime dashboard and control room for harnessing agentic coding, build on tmux and Zellij.

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

Writ: An AI agent skill that catches AI writing tells and clichés using a self-edit checklist drawn from Wikipedia's Signs of AI Writing gui

The agent that evolves with you 𖤍

Model-agnostic output control for LLM agents: concise, action-first answers with proof and risk preserved. Native install paths for Claude C

The agent loop for Python. Your harness, any model.

F.R.I.D.A.Y — a secure self-improving personal AI agent. Local-first, with memory, tools, voice, MCP, automation, and verified self-extensio

AI for tactical cycling intelligence: Predictive mud logic, S-Scale terrain analysis, and powered GPX routing

Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.

Open-source Android assistant that replaces Gemini. Summon it by gesture, bring your own API key, and it reads the screen, taps through apps

Personal collection of Agent Skills for AI coding agents (Claude Code, Gemini CLI, Cursor, Codex, etc.)

A React + TypeScript spatial canvas and node-board library for whiteboards, visual editors, and graph interfaces.