Havuz

DeepSeek Harness 的执行迷宫——看 Agent 真实怎么干活：迷宫时间轴 · 数据轨道 · 确定性执行分析 · 多会话对比 | The execution maze for DSH agents: maze timeline, per-step data trac

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

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

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

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

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

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

Multi-Agent AI Task Orchestrator 2026

Carefully human hand written llm jailbreaks for the latest models that are available on the market. GPT-6 Astra, GPT-6.1 SoL, Opus 4.7, Opus

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

Turn your repos into a team of Claude Code agents with persistent memory, coordinated tasks, and a live dashboard.

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

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

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

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

Offline-first Python AI agent that runs a tiny research business: quotes each job against its own costs, collects via Stripe, fulfils with N

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

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

A task conductor for Claude Code that gets better the more you use it. Multi-agent orchestration with an evidence contract that BLOCKS inste

Project memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress, and next steps in local proj

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

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.

Agentic text-to-SQL SDK: hand the LLM one execute_sql tool and let it explore the schema, test queries, and self-correct — no RAG, no semant

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

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

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

Code repository for World Model From Scratch book

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

Official Repo for "AgenticASR: Refining Speech Recognition in Real-World Scenarios via an Agentic Approach"

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

Agent Deck

SimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no targ

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

Reusable multi-round research skill for evidence-backed product, market, technical, open-source, and investment-style surveys.

A minimal local coding agent built on the CloudWeGo eino framework — the framework-variant sibling of mini-coding-agent-go.

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

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

Online-adaptive multi-agent framework for enterprise API orchestration. Adaptive circuit breakers, SLA-driven routing, hybrid LLM+rule inten

AI framework for Ruby/Rails developers

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

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

Built from the ground-up for agents, Vessel Browser is an open source AI browser for Linux/Mac/Windows that provides a durable state, MCP co

Local outcome-loop + reward layer for coding agents — remember what worked, ship the next move, measure how it landed. Docs at nimroboai.com

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

Reliability harness for long-running OpenClaw agents: persistent state, strict task contracts, scheduled execution, and external validation.

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 ）

The Open-Source AI Career Operating System. 167 Specialized AI Agents across 19 Divisions, Spoken Voice Lab (27 Languages), AI job search ,A

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

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.