Havuz

Find the best AI models you can run

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

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

An unattended maintainer for one repository. It reviews, files, prunes, and merges only against proof that a guard bites.

A framework for discovering, compiling, and validating reusable skills for scientific agents.

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

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

Self-aware cognitive AI agent with a persistent soul: reads, modifies & verifies its own code, plans autonomously, dreams in idle time, reme

面向 LLM 交易 Agent 的抗污染回测、确定性回放与训练轨迹生成，支持 A 股研究｜Leakage-resistant backtesting, deterministic replay & training trajectory generation for LLM tr

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

Code repository for World Model From Scratch book

Pre-inference tool and agent routing for MCP, A2A and tool-rich LLM systems. Reduce candidate tools before model inference with policy-aware

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

Build & prompt Qwen3.x agents in their native dialect — extracted from qwen-code & Qwen-Agent

核弹，椅子，瘫坐！DSH新预设模式“工程模式”，只需要你说出“请帮我完成一个机械臂”，你的AI模型靠内部的工作流，按照要求完成对应机械的设计，完全实现“AI设计机械，无需人工干预”的场景！(测试版本：SW ：2025 DSH:0.2.1 rc3 ）

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

Async Python bot that scrapes YouTube trends, analyzes viral strategies with Gemini LLM, and dispatches HTML reports to Telegram.

Framework for building continuous-loop autonomous AI agents.

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

Always-on 2D lidar SLAM with named places, as a spatial memory for LLM agents

Coding Agent Runtime & Evaluation Harness for controlled repository-level software repair

A pure-Python system that automatically discovers, verifies, and applies relevant historical requirements for coding agents — no embeddings,

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.

An Automated project operating system, called PhanOS. It Combines Phanes as the Orchestrator, Cyphor(to be released) as the Documentation, C

BuildArena: Physics-grounded Besiege Building for LLMs

Open-source, self-hostable platform that turns agents into co-workers. Start with Software Factory: delegate GitHub issues and review pull r

Benchmarking data agents for verifiable analytics over heterogeneous workspaces.

Overnight experiment: can an AI agent make money, and can you trust what it reports? The agent produces claims; a separate verifier it canno

DrugTargetWorld: a synthetic biobank for training and benchmarking AI scientists on end-to-end drug target discovery. Paper: arXiv:2610.0955

Official codebase for the paper "Sharpening Tax in Post-Training"

PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents

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

A skill library that teaches Claude Opus the working disciplines of Claude Fable 5. Move the checkpoints, not the capacity.

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

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

Give any AI agent its own disposable Linux machine. Firecracker microVM sandboxing with millisecond boot times, full network access, and nat

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

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

A phase-aware operating system for coding agents that helps them explore, ship, harden, and verify without losing the plot.

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

🔥 CogitoAgent — An autonomous AI agent, cloud-driven but locally executed. It continuously thinks, automatically analyzes, and integrates pr

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

OpenCode agent configuration — a read-only orchestrator delegates to 6 specialized subagents. Expert model plans, fast models execute. Isola

A minimal, language-agnostic harness for Claude Code and AGENTS.md-compatible coding agents. | Claude Code와 AGENTS.md 호환 에이전트를 위한 미니멀·언어

Semantic UI automation and lightweight accessibility snapshots for LLM agents to interact with Web and Desktop applications.

Audit any agent decision across its past, present, and future, on one typed graph.

Per-step LLM routing benchmark with 970 static labels, live SWE-bench evaluation, an open data pipeline, and a public leaderboard.

Swap, lend, trade perps, add liquidity, move SOL, read the market. One binary your agent calls, across every venue.