Havuz

The graph based agentic IDE

Build your own LLM-native WIKI (knowledge library). Search, extract, summarize, Q&A with contextual RAG, layered knowledge graph, and reinfo

A deterministic privacy boundary between your data and AI.

NEWTON: Agentic Planning for Physically Grounded Video Generation

CrewOS 是一个关于企业 Agent 产品形态的公开实验。 我正在尝试回答一个问题： 当 AI 已经能够完成任务以后，它能否进一步接住长期、复杂、持续变化的真实业务？ 这里会持续记录产品原型、设计实验、思考过程以及失败的假设。 如果你也在研究类似问题，欢迎一起讨论。

Local-first, governed documentation for humans and AI agents—mirror Office, PDF, and GitHub sources into linked Markdown knowledge workspace

Self-hosted AI workspace where chat becomes visual workflows, multi-agent operations, and reviewable automations. Local memory; local or clo

🍊 Akka（阿卡）- Self-learning, 24/7 Creator AI Agent

Local Claude Code and Codex plugin that bounds oversized and repeated tool output, preserving complete redacted artifacts. Runs locally, mak

Open-source AI-powered subtitle generation and natural language translation platform for video and audio.

Claude and ChatGPT now log into your app as your customers. OneHuman decides what they can see and do. Join our community: https://discord.g

Welcome to cerbere-agent guard, originally just agent guard, then rebranded after the mythical hound of the underworld. Our mission? Guardin

AI-agent toolkit for structural biology: design binders, map structures, screen candidates, rank results, and prepare cloud-scale runs.

M-flow, bilgiyi katmanlı bir graph yapısında düzenleyip RAG sorgularında kanıt bağlantılarını izleyerek ilgili anı veya bilgi paketlerini bulmayı amaçlayan bir memory engine'dir.

Neden yükseliyor · 180 günde 4509 yıldız, projeye belirgin ilgi olduğunu gösteriyor; agent memory ve Graph RAG alanlarına yönelik ilgi bunun olası bağlamı. Ancak son 28 günde commit ve farklı yazar sayısı sıfır, bu nedenle ilginin güncel geliştirme faaliyetine veya sürdürülebilir benimsemeye dönüştüğü söylenemez; yıldız artışının nedeni de verilen ölçümlerden belirlenemiyor.

Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, c

本地优先的 AI 投资研究工作台（AI investment research workbench），支持深度调研、证据化投资论点、投资组合风险分析、自选股与 Pi Agent 副驾驶。

面向 DeepSeek Harness 的 Claude Code 风格终端界面，支持 Windows、macOS 与 Linux，兼容透明终端、VS Code 主题和自定义配色。

Graph-Orchestrated Agent Loop — a production-grade framework on LangGraph. Combine workflow graphs and agent loops, transpile Dify DSL to ru

AtlasAgent - an auditable AI agent control plane: evidence-backed memory, governed tool runtime, checkpoint DAG recovery, and a 55-chapter e

CoDA-Bench is a benchmark for code agents on data-intensive tasks. 🎈代码智能体能搞定数据密集型任务吗?

A modular local AI agent built with Python and Ollama, featuring tool calling, memory, web search, document processing, embeddings, and RAG.

Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing

Semantix, AI coding agents için oturumlar arası bellek, semantic caching ve prompt cache kullanımını destekleyen Go tabanlı bir agent/kernel sunuyor.

Neden yükseliyor · 59 günlük bir repoda 821 yıldız dikkat çekiyor; agent belleği ve inference maliyetlerini düşürme iddiası güncel ve yaygın bir ihtiyaca sesleniyor. Ancak son 28 günlük commit ve farklı yazar verisi ölçülmediğinden geliştirme temposu ve katkı genişliği hakkında hüküm verilemiyor.

Self-healing infrastructure for AI agent payments. 90.3% auto-recovery.

From ticket to reviewed pull request. Free and open-source, on your machine.

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

AgentScope Java, Java ile uzun süre çalışan ve dağıtık ortamlara taşınabilen agent uygulamaları geliştirmek için bir framework sunuyor.

Neden yükseliyor · 13 günlük yaşına rağmen 108 yıldıza ve son 28 günde 12 commite ulaşmış; Java tarafında üretim odaklı agent altyapısı arayanların ilgisini çekmiş olabilir. Ancak yıldız ve README özellikleri benimseme ya da üretim başarısının kanıtı değil; farklı yazar sayısının 1 olması katkı tabanının şimdilik dar olduğunu gösteriyor.

Local-first Agent Runtime connecting LLMs to controlled tools, Chrome, desktop automation, MCP, context governance, and verifiable memory

A stateful AI operating system for serious, long-horizon work.

Free, AI PR reviewer that runs entirely in GitHub Actions. No hosting required.

Observe AI agent runs and control consequential actions. Signed policies, exact-action approvals, AuthZEN API vetoes and evidence. MCP gatew

Agentlens is a trusted agent trading platform. Here, you can quickly find the Agent that meets your needs, and you can also publish your ow

Govern: one Decionis verdict before a workflow step runs — a deploy, a migration, an infrastructure change, an agent's action — with a signe

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, go

🦅 Multi-platform agentic AI harness — runs on Telegram, Discord, Teams & Terminal with a pluggable backend (Claude, Kilo, OpenCode, Codex, O

An open-source travel agent that works on real websites: plan trips, book in a browser beside the chat, stop at the payment page. Desktop ap

Open source memory infrastructure for AI and humans. Turn scattered knowledge into AI-ready context across Claude, Cursor, ChatGPT, and any

Voice-first desktop assistant for Windows — talk to your PC and it works inside real apps, safely. By VORNEX.

Agent skills for designing, training, evaluating and improving application-specific decision systems. Primitive/model selection, data assemb

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

Govern consequential AI agent actions in Docker with deterministic policy, human approval, and signed Decision Dossiers.

DeepSeek++، DeepSeek web sürümüne MCP araçları, memory, Skills ve otomasyon özellikleri ekleyen bir tarayıcı eklentisidir.

Neden yükseliyor · 153 günde 1.871 yıldız alması kayda değer bir ilgi sinyali. Ancak son 28 günde commit ve farklı yazar sayısı sıfır; bu nedenle ilginin güncel geliştirme temposuyla desteklendiği söylenemez. README kapsamlı özellikler sunuyor, fakat bu metrikler özelliklerin kullanımını veya kalitesini doğrulamıyor.

Self-Improving Agents -- A Progression Four levels of self-improving code agents, from the simplest loop to a full adversarial arena with se

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

An AI agent for running, testing, and hardening GitHub Docker Compose apps.一个用于运行、测试和加固 GitHub Docker Compose 应用的 AI Agent。

Multi-agent exploratory data analysis system with autonomous insights, visualization, preprocessing, and reporting workflows.

Open source release of Data Science Agents that can analyze and transform datasets as well as train and infer models to augment your data sc

Bilingual graduate textbook on LLM post-training: SFT, RLHF, DPO, GRPO, RLVR, reasoning, agents, systems, evaluation, and safety.

Guard rails for Claude Code: workspace boundaries, protected branches, production targets, lost exit status, and foreground time.