Havuz

A top for local LLMs: memory, paging, GPU and tokens/s for oMLX, Ollama, llama.cpp, vLLM and more

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。

许愿特化器 · Wish Specializer — DSH 插件：让模型更出色地，不误解你的意思地，完成你的“愿望”。在短提示词+自带的Wish预设（PTC也可以）+重度的情况下，可以起到巨大的表现增益

Open source AI-assisted Instagram publishing for newsrooms - draft, review, and post breaking-news content fast, with a human always in the

AI-powered data-to-video generation. Upload a table, get a narrated animated data story.

Tell Morse what to add, remove, or change. It writes the code and applies it to the app. Even if it's closed source.

UFO, ekiplerin kendi altyapılarında AI agents çalıştırıp iş atayabileceği bir runtime, server, terminal client ve SDK sunuyor.

Neden yükseliyor · Repo yalnızca 1 günlük ve 60 yıldızlı; son 28 günlük commit ve farklı yazar verisi ölçülmemiş. Bu nedenle ilginin nedenini veya sürdürülebilir topluluk etkinliğini mevcut verilerle belirlemek mümkün değil.

Open Source Agentic Security Scanner

End-to-end AI-powered academic paper writing system — from idea generation and literature search to experiment execution, result backfill, a

可扩展到各个领域的多 Agent 协作平台：自动分析任务，动态组建由不同角色组成的 AI 团队，协同完成复杂任务。

飲食熱量日誌 App。核心思想：讓 LLM 負責辨識品名與份量自動拆項後輸出結構化 JSON，並在後端接上可以成長的資料庫；熱量一律來自可核對的資料並由程式計算，每個數字都查得到出處。設計決策參考食物辨識研究及相關論文，以 Claude Code（Opus 5.5）協作開發。原為

Relate, sohbetleri yerelde düzenleyip bunlardan hatırlatmalar, taahhütler ve aranabilir bir kişisel hafıza oluşturan self-hosted bir AI asistanıdır.

Neden yükseliyor · Kesin yükseliş nedeni bu verilerden anlaşılamıyor; ancak kişisel sohbetleri hafızaya ve uygulanabilir hatırlatmalara dönüştürme fikri, self-hosted kullanım ve MCP entegrasyonu dikkat çekici bir ürün birleşimi sunuyor. Dört günde 112 yıldız ilgiye işaret etse de yalnızca 3 commit ve 1 farklı yazar, bu ilginin sürdürülebilirliğini veya projenin olgunluğunu henüz kanıtlamıyor.

Agentic quant research workbench with CSV data inspection, local Codex and compatible APIs, predictive models, independent reviews, and repr

Open-source app builder engine — intent to working app

Reverse engineered Deepseek chat into an OpenAI compatible API. Access V4 and R1 models through a simple REST interface without API keys or

Secure memory management for AI Agents • Ensures data integrity • Reduces hallucinations • Maintains consistent long-term context

Open source agentic SAST. The engine behind hundreds of disclosed zero-days. 100+ AI security agents, any repo or PR diff, bring your own mo

Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.

Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.

An easy-to-use, fast toolkit to scale up RL post-training on a single node.

Taking the pi coding agent to Claude Code-level performance: 0.539 → 0.773 pass@1 on Terminal-Bench 2.1 with the same self-hosted 27B model,

🐳 whalegate — OpenAI-compatible gateway into DeepSeek web sessions (Rust): account pool, failover, SSE, native-style tool calling (tool_choi

Local AI for Omarchy: the model validated for your GPU, one button on the bar. Start serves it, any coding agent opens on it, one click shar

collabosm, kullanıcının Google Colab hesabında GPU başlatıp Qwen3.8 modellerini yerel uygulama ve OpenAI uyumlu API üzerinden kullanmasını sağlar.

Neden yükseliyor · 3 günlük bir repoda 87 yıldız dikkat çekici bir başlangıç; ancak yıldızların neden geldiği ve kullanıcıların uygulamayı gerçekten çalıştırıp çalıştırmadığı mevcut verilerden anlaşılamıyor. Son 28 günlük commit ve farklı yazar ölçümleri de yok.

梨园 Liyuan — 以 rp agent为主体的ai角色扮演应用

Give your AI agent a brain that remembers. Local memory system for Claude Code — 100% private, GPU-accelerated, zero cloud dependency.

Self-hosted private chat channel between you and your AI companion — PWA, Claude Code, or any LLM.

Hermes Agent plugin: say 'make me a <role>' and your agent builds a complete, working Bot — name, face, SOUL.md, memory, tools, skills, rout

简明技术中文 / Simplified Technical Chinese: a controlled language for Chinese technical writing, modelled on ASD-STE100. 40 rules, a one-meaning-

Codex/Claude Code/Cursor的开源增强版，专注一句话实现复杂长程任务（教育、编程、办公、生活、娱乐、游戏）。部署在你自己的服务器上，团队用浏览器打开就能编程——包括手机。CLI & Web UI 双入口，Multi-Agent 协作，原生直连千问/DeepSe

Mine your Claude Code and Codex logs into a local you.md agent profile.

Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/a

⚒️ Open-source game wiki template. Astro + Cloudflare Pages. Free, fast, beginner-friendly. Static-first, zero-JS, AI-native content workflo

The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of

A local-first coding agent that works in your repository and leaves reviewable changes

Honey (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — write less code, les

Draw a store, generate LLM personas, and watch them shop — an isometric 3D sandbox for synthetic-consumer experiments.

Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interven

Rust-native, library-first coding-agent runtime and terminal CLI inspired by Pi, with composable LLM providers, tools, sessions, and plugin

🧠 The memory that dreams — cross-session memory for DeepSeek Harness. Local SQLite + Markdown mirrors, autoDream consolidation, 4-way recall

An evolving AI brain for Home Assistant

A dependency-free C inference engine for Liquid AI's LFM2 / LFM2.5 models. Terminal chat, an OpenAI-compatible server, a web agent and a ter

Plugin-first long-term memory for agent platforms — reference implementation of AMP (Agent Memory Protocol).

Feel how fast a local LLM runs before you buy the hardware

📊 电商数仓智能问数 AI Agent，最适合用于系统学习 LangGraph 的实战项目：基于 LangGraph、FastAPI、Qdrant、Elasticsearch、MySQL 与 React，完整实现元数据知识库、混合检索、自然语言生成 NL2SQL 生成校验、SQL

jevals, agent trace'lerini eval ve guardrail kontrollerinden tek istekte geçirerek production veya agent loop içinde değerlendirmeyi amaçlayan bir Python kütüphanesidir.

Neden yükseliyor · 7 günlük bir repoda 97 yıldız, 5 commit ve 4 farklı yazar erken ilgi ve katkı işareti. Tek istekte birden fazla kontrol, düşük maliyet ve agent loop'a uygun hız iddiaları dikkat çekiyor; performans ve maliyet rakamları README'de verilmiş, bağımsız doğrulama olarak kabul edilmemeli.

High-performance Go proxy gateway for 9Router LLM routing — 32K RPS, 42MB RAM, CGO-free

Multi-agent pipeline that turns a research topic into a draft paper grounded in real literature, with citation hallucination detection and c

Self-hosted dashboard for all your AI plans. Track limits, resets and spend across Claude, Codex, Cursor, Copilot, Grok and more.

Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option.