Havuz

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

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

A long-horizon CRPG benchmark for frontier agents. Raw 320x200 frames, Traditional Chinese, isometric navigation, twelve books to find.

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

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

A high-performance, private, on-device AI chat client built with Flutter. AstraLM runs Large Language Models (LLMs) and Vision models 100% l

Error gates for AI coding agents: detects recurring tool-call failures and promotes them into enforced gates - remind first, hard-block on s

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

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

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:0.2.2 rc1 ）（如果您对此项目感兴趣，请加

0, tarayıcı, terminal ve MCP üzerinden güvenlik iş akışları çalıştırıp bulguları iş etkisine göre önceliklendiren açık kaynak bir güvenlik platformudur.

Neden yükseliyor · 46 günde 492 yıldız ve son 28 günde 677 commit dikkat çekici bir ivmeye işaret ediyor; YC desteği ve browser, CLI, MCP birleşimi de görünürlüğü artırabilir. Ancak commitlerin tek farklı yazardan gelmesi, hareketliliğin geniş topluluk katkısı anlamına gelmediğini gösteriyor.

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

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

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

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

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

Claude Code ve Codex ile AI destekli geliştirmeyi yapılandırmak için promptlar, şablonlar ve kalite kontrol pratikleri sunan bir toolkit.

Neden yükseliyor · 44 günlük bir repoda 729 yıldız ve son 28 günde 14 commit dikkat çekiyor. AI coding agent'lar için uygulanabilir iş akışı ve kalite kapıları sunması ilgi çekebilir; ancak commit'lerin tek yazardan gelmesi bağımsız katkı ve doğrulama kanıtını sınırlıyor.

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

Production-ready Claude Code decision intelligence marketplace with adversarial routing, evidence-driven analysis, specialized agents, bench

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

Human as Agent（人即智能体）· Human-as-LLM 人工代理网关：把工程师变成模型，OpenAI 兼容 /v1 接入 Agent 调度池，涉密/需人工任务路由给真实工程师。为 AI Agent 提效、为平台/运维收集工单。Human-as-LLM Gate

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.

🌃 Capri — Edgerunners-inspired AI agent for your desktop. Works with Claude Code, Codex, Antigravity & more.

Open-source agentic software development platform for building, orchestrating and monitoring autonomous AI coding agents.

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

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

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

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

Adversarial LLM Reversal for hermes-agent

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

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

Browser-native multi-agent playground: drop LLM personas on a 3D map, watch them live, and talk to them. OpenAI, Gemini, Claude, Ollama. No

Zero-token long-term memory for Claude Code. Indexes your own session transcripts and retrieves evidence deterministically — entity-context

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

An end-to-end framework for Agentic Reinforcement Learning.

Cambium, LLM agent’larıyla sürdürülen bilgi depolarındaki işleri kurallar, durum kayıtları ve doğrulanabilir kanıtlarla yöneten bir governance standardı ve Python araç setidir.

Neden yükseliyor · 55 günde 457 yıldız ve son 28 günde 81 commit ilgi ve yoğun geliştirme sinyali veriyor; ancak farklı yazar sayısının 1 olması katkı tabanının dar olduğunu gösteriyor. Yıldızların ne zaman kazanıldığı verilmediği için yükselişin hızını veya nedenini doğrulayamıyorum; LLM agent’ları, auditability ve MCP kesişiminin ilgi çekmesi olası bir açıklama.

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

给AI伴侣增强时间感的小器官（电脑端专用）

Local-first, LLM-agnostic memory system — hybrid retrieval (vector + lexical + graph), multi-signal ranking. Runs on 4GB RAM, CPU-only, no c

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

Supervisor/Lead/Peer governance for multi-agent coding — one policy core enforced identically on Pi and Claude Code, brief-scoped authority,

An agentic LLM-powered knowledge assistant that enhances RAG capabilities through automated entity extraction, structured data analysis, and

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

面向"面试官 × 简历主人公"场景的个人简历 RAG 问答 Agent：把简历、证书、荣誉、项目介绍放进知识库，面试官可对简历任意提问（自我介绍、项目深挖、技术八股、HR 素质、简历细节），系统以第一人称自然作答。核心设计是"宽松推理 + 诚实标注"——硬事实（数字/日期/证书名

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

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

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

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

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

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