Havuz

Local-first personal OS: mood, sleep, habits, tasks, day planning and a memory that connects the dots. Works with Ollama, OpenAI, Anthropic

A 7×6 framework for agent architecture. 28 patterns, each placed at a coordinate, runnable Python code with verified engineering slices from

Local-first YOLO workbench for annotation, training, evaluation, and AI assistance.

Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server.

Your coding agents forget. Graft doesn't. Persistent local memory that brings back fixes, decisions and project knowledge when they matter —

Find the best AI models you can run

A minimal coding-agent harness built to measure what context management actually costs: constraint survival after compaction (8%→83%), def

AI coding agent for Visual Studio 2022/2026 — chat, inline completion, and five autonomous agents that explore, plan, patch, and verify buil

Cubicle: a live pixel-art office for your AI agents (Paperclip, Claude Code, Codex, Gemini CLI). See who works, who needs you, who failed; K

An audit agent that proves whether a person's data is really gone: resolves identity across systems, judges state at the audit cutoff, finds

🔥🔥 Accelerating decision inference with exact state forking

An AI agent plays Baldur's Gate 3 on Linux through a Lua mod and an MCP server, seeing only what a player sees. Includes a model benchmark a

Connect and benchmark finance agent systems in one open-source platform, then trade on them. TradingAgents and AI Hedge Fund today, your own

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

A linked-list discipline for knowledge, memory and pointer hygiene in large projects: five laws plus portable Python engines (declarative ru

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.

An automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters us

Agents for Role Play. Agents for Game. Agents as a Game. An orchestrator-agents engine for living worlds — file-backed, event-sourced.

Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction

神经元记忆网络 让 DSH 记住「为什么这么决定」，而不只是结论。思维链记忆插件：8 个池分级遗忘、每轮注入、神经元 3D 星云浏览、夜巡自动整理。

Lemmalog, LLM agent’ların belleğini Datalog kurallarıyla temsil edip kaynak izlenebilir ve artımlı biçimde sorgulayan bir Rust motorudur.

Neden yükseliyor · Agent memory ve MCP konularına yönelik ilgiyle örtüşüyor; 31 günlük repo için 324 yıldızın yanı sıra son 28 günde 27 commit ve 4 farklı yazar var. Bu hareketlilik erken geliştirme temposuna işaret ediyor, ancak yükselişin nedenini doğrudan kanıtlamıyor.

Give AI agents ambitious work without losing the plot. nac is an open-source harness for long-running tasks, using a central orchestrator, t

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

Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict.

An open-source research system for autonomous investigation, recursive self-improvement, and human–AI collaboration. Run experiments, refine

:dog: Beagle is designed to be the unified platform for the broader Recursive Self-Improvement (RSI) ecosystem. Think of it as Hugging Face

Context optimization for AI coding agents — lower token cost and latency without sacrificing accuracy.

A shared, git-backed wiki your team's AI agents maintain but can't break — Claude Code, Codex, OpenCode and any MCP client.

Automate your real iPhone from Safari with a $2 ESP32. No Mac, no APP, and no jailbreak. Local conversations, your choice of AI, and communi

Instant context compaction for Hermes Agent. Builds the compaction summary in milliseconds with no LLM call, keeping the exact commands, exi

SkillCorpus, dağınık SKILL.md dosyalarını agent'lar için seçilmiş, aranabilir skill corpus'larına dönüştüren ve retrieval ile evaluation araçları sunan açık kaynak bir altyapıdır.

Neden yükseliyor · Agent'lar için paylaşılan ve göreve göre seçilen skill katmanına ilgi var; repo kısa sürede 667 yıldıza ulaşmış ve son 28 günde 9 commit ile 3 farklı yazar katkı vermiş. README ayrıca birden fazla benchmark'ta iyileşme bildiriyor; bu sonuçları bağımsız olarak doğrulayamıyorum.

AI 执行与监察体系（Agent Oversight Framework）：分层治理规范 + L2 运行时监察参照实现——证据分级、自校正、边界诚实。A layered governance spec for AI agents, plus a runnable referenc

Can coding agents build the agent you actually want? A benchmark of 25 agent software engineering tasks across creation, editing and optimiz

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

Asking for What Was Never Requested: horizontal and vertical proactivity in LLM agents. Need-graph metrics (no LLM judge) and Q&D, which tra

Manipulation benchmarks test acting to change; EmbodiedLab tests acting to know. Given only an objective and the apparatus, a robot runs its

Official code for the paper "Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity"

22 production-grade skills for AI coding agents — setup, scope, discipline, code review, security, session management, governance, ops, and

Local-first agent platform: board + role agents + agent CLI runs (Claude Code, Cursor, Antigravity, OpenCode) or local and API models (Ollam

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

241 evaluated academic Claude/agent skills across 18 research domains — bioinformatics, cheminformatics, data science, databases, clinical,

Live trading arena for LLM agents: public reasoning, real market data, virtual capital

An open-source, coding agent harness designed specifically for local LLMs. Designed as everything a user needs to jumpstart their own harnes

十三希诺 Agent 工作流 · 中文源库：把工程纪律做成可机检门禁的元工作流 Skill 家族——三级跑道／判级／GATE 12 字段可复跑证据／405 条细则库／五包交付（核心+流程+角色+产品工程+单文件蒸馏），五平台注入适配。docs/ 为开发工作区，实验数据已归档。En

Let Claude Code, Codex and Pi talk to each other: cross-session messaging that wakes AI agents on one machine or across your LAN (macOS/Linu

A recursive self-improvement (RSI) workflow that evolves both target agents (e.g., Pi and DeepSeek Harness) and the RSI system itself.

Claude Code skill + 18 AI agents for Android & iOS mobile app security audits. OWASP MASVS/MASTG-aligned, with adversarial exploitation conf

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

Agent Skills lifecycle toolkit: mine repeated coding-agent workflows, audit and personalize skills, and generalize personal skills for publi

Autonomous multi-agent pentest framework — plans, exploits, verifies (proof-required), CVSS-scores and writes client-ready reports. 104/104