Havuz

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

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。

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

Harness-Zero: Harness Distillation via Agent-as-Harness

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

This 14 MB Agentic LLM(Cactus Needle 2) can control your phone completely.

Evolutionary multi-agent runtime that breeds, evaluates, and improves autonomous agents across reproducible epochs to converge on optimizati

Stateful ride-support agent: versioned claims, evidence-backed RAG, durable memory and guarded MCP tools.

A local, Git-native review + feedback layer for existing LaTeX projects.

A direction in development: a model drafts an ontology from business tables or a document, code checks the draft against the data, a person

Code-only runtime toolkit for cost-aware multi-agent organization and control

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

Evidence-backed retrospectives for AI coding-agent histories. Offline indexing, scoped workflow improvements, and bilingual documentation.

Robinhood Agentic Trading agent — a fully automated AI trading bot placing real orders through Robinhood's Agentic Trading MCP, under mechan

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

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

Any research. One Claw. 🦞 From any materials to research with fully autonomous & skill-driven researcher.

Autonomous trading agents with deterministic execution. The agents propose; the system decides.

把 dsh 会话变成合规、可复现、可追责的 AI 投研工作台：ai-hedge-fund 回测 + risk-gate 风控 + cron 盯盘 + 记忆复盘 | compliance-first AI investment desk

Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses).

The why layer of repo-native project memory: the reasoning behind a codebase as Markdown in the repo, versioned by Git, for coding agents an

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

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

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

Vigil SOC: The leading open source AI SOC. Apache 2.0. Runs against your own LLM, local or remote.

先进且稳定的企业级智能分析平台；面向企业问数、洞察分析的Data Agent，基于数据分析方法论打造可审计、可治理、可复现workflow

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

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

Universal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one set

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

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

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

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

A minimal, readable agent-framework kernel — understand how LangGraph/ADK work under the hood. 1800行代码的 agent 框架内核，理解 LangGraph/ADK 底层的工作原理

Compact operational charter that turns LLM coding agents into disciplined principal engineers. Eleven rules + one meta-rule.

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

Python toolkit for PowerPoint ↔ HTML, built for AI. Round-trip fidelity preserves formatting across every edit loop — ideal for RAG ingestio

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

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

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

Agent Execution Partnership AEE is an open-source control plane that ensures every AI agent action is authorized before it runs, observable

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

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

Loop until it's better — drop-in agentic loops (autoresearch, scientific writing, data analysis, code/SQL/prompt optimization, red-teaming)

Find the best AI models you can run

A minimal local coding agent in Go — a faithful port of Sebastian Raschka's mini-coding-agent, with no LLM framework.

Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code

CyberGuard, AI agent’larla güvenlik soruşturmalarını yürütmek ve müdahale kararlarını onay, denetim izi ve sonuç kontrolleriyle yönetmek için bir SOC uygulaması sunuyor.

Neden yükseliyor · 10 günlük bir repoda 54 yıldız ve son 28 günde 58 commit bulunması erken ilgi ve yoğun geliştirme sinyali veriyor. Ancak farklı yazar sayısının 1 olması, bu hareketliliğin topluluk katkısı veya bağımsız benimsemeyle desteklendiğini göstermiyor.

An agent skill that plays ARC-AGI-3. One rule: say what an action will do before you spend it. Claude Code on Opus 5 finished all 25 public

Paper artifacts, figures, aggregate data, and share cards for the DXRG paper: What LLM Trading Agents Actually Do in Production (six months,