Havuz

AI 文献检索与综述 Agent：支持多源检索、代码仓库定位、开放 PDF 下载、证据链与中英双语报告。

Dataflow-Oriented Reinforcement Learning for (Multi-)Agentic LLMs

Pluggable extension packages for the Pi AI-agent runtime. Each package exposes LLM-callable tools via MCP — covering IM workspace integratio

Self-hosted meeting transcription portal — speech-to-text, speaker diarization, LLM-corrected transcripts, structured summaries and Word min

Self-hosted PaaS for private infrastructure. Deploy 200+ services on any server in one click. GPU monitoring, AI model management, VRAM c

基于本地 RAG 与大模型人格蒸馏的多平台聊天记忆系统。通过 FTS5 检索、语料清洗与长期报告生成，将聊天记录转化为高拟真的数字分身。

إطار مفتوح المصدر لتكييف مساعدات الذكاء الاصطناعي وسير العمل القانوني مع البيئة القانونية السعودية. Open-source framework for adapting AI as

RoR engine that enables natural language queries over your database using RAG and LLMs.

TradingAgents mimarisini A股 piyasasına uyarlayarak birden fazla AI analyst ve risk rolünden araştırma raporu, tartışma ve yatırım planı üreten bir Python framework’üdür.

Neden yükseliyor · 138 günde 3563 yıldız ve son 28 günde 27 commit ile 7 farklı yazar, belirgin ilgi ve yakın dönem geliştirme faaliyetine işaret ediyor; ilginin kesin nedenini mevcut verilerden saptamak mümkün değil. A股’ye özel agent rolleri ve veri bağlantıları dikkat çekici olabilir, ancak yıldız sayısı kalite veya yatırım performansı kanıtı değildir.

Native Linux desktop control for AI agents (MCP, Pi, CLI): semantic AT-SPI trees, screenshots, window targeting, and input across GNOME, KDE

Learn any journal's writing conventions from its published papers, then revise your manuscript to match — section by section.

[NeurIPS 2026 Spotlight] Fast, lossless LLM inference via dual-view diffusion decoding.

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

Official code for the paper "Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity"

Use 30+ AI models (DeepSeek, Kimi, GLM, Claude, GPT-5.5, Gemini, Grok) in GitHub Copilot Chat - free via BYOK. No Copilot Pro needed.

Proxy API OpenAI-compatible que usa automação com Playwright para rotear requisições para modelos do Qwen com suporte a múltiplas contas, to

Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server

AI assistant for international trade — 45 B2B skills (lead gen, OSINT, email, docs, compliance). End-to-end customer development pipeline. R

Universal AI behavior rule framework — pin your 5-10 rules so AI doesn't drift in long tasks. Dev-scenario preset built in; switch to any sc

Agentic IDE with custom harness

Distribute AI Skills as Composer dependencies

Run AI models on Apple Silicon and Raspberry Pi

SGLang Docker image for AMD Strix Halo (gfx1151 / Radeon 8060S)

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

"Does this actually work with my agent?" An open, versioned registry of AI-agent artifacts: skills, plugins, MCP servers, models, etc. with

The AI-native JupyterLab — open-source Cursor for notebooks. Cmd+K inline edit, multi-step agent with cell-level tools (read/edit/run), chat

zerostack, Rust ile yazılmış; birden fazla LLM sağlayıcısını ve kodlama iş akışlarını destekleyen hafif bir coding agent’tır.

Neden yükseliyor · 138 günlük yaşına kıyasla 1692 yıldız ve son 28 günde 75 commit ile dikkat çekiyor; Rust tabanlı hafiflik iddiası ve geniş özellik kümesi ilgiyi açıklayabilir. Yıldız artışının zaman içindeki hızı elimizdeki ölçümlerden doğrulanamıyor.

Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark,

Compact operational charter that turns LLM coding agents into disciplined principal engineers. Eleven rules + one meta-rule.

Fast, AI-agent-native code search in Rust — hybrid BM25 + semantic, Tree-sitter AST chunking, dependency & impact analysis. Drop-in replacem

Find and govern AI attack surfaces in application code, at PR time and inside your AI coding tool (MCP server, Claude Code hook). Free, OSS,

An open-source cost controller for AI agent loops — stops a loop when it's actually converged and rolls back before it degrades, instead of

Local-first CLI for benchmarking LLMs on real hardware — quality, speed, reliability, and a real multi-turn agent loop.

Production-grade Kubernetes operator for nousresearch/hermes-agent: declarative spec, security defaults, S3 backups, OCI auto-update with ro

Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining (ICML2026)

BYOK AI content moderation API. Plug in your own AI key, moderate messages, track repeat offenders with a 5-strike pipeline. FastAPI + Postg

自托管家庭资产管理 · 每月10分钟,全家资产全局图 + 真实年化(XIRR/TWR)+ AI 资产体检 · 数据自托管, 不泄密

PhyAI is a high-performance framework for running Physical AI models (VLA, WAM, and beyond), supporting both cloud-based serving and on-devi

Open-source, self-hostable social listening.

Zero trace. Full answer. — Transparent Claude API proxy that anonymizes PII and sensitive data before it leaves your environment. From pente

Turn scattered knowledge, operational data, and history into source-linked context that your agents can inspect, explain, and reuse.

Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini, OpenCode, Aider, Copilot, OpenClaw, and any AGENT

Terminal-native AI assistant built specifically for Termux and Android development.

Translate books and documents with LLMs, featuring glossary extraction, review, and polishing pipelines.

NullFlux — 本地部署的中文 CFD / 科学计算智能体（OpenFOAM · MFIX · LBM · ParaView · 视觉核验 · 论文复现），by LZF

LLM-powered conversation summarisation service for OCTO — turns group chats and threads into structured briefs with key decisions, open ques

ktx, şirket verisi ve iş kurallarını agent’ların analitik veritabanlarını daha tutarlı sorgulaması için kullanılabilir bir context layer’a dönüştürür.

Neden yükseliyor · Agent’ların şirket verisi üzerinde doğru ve onaylı metriklerle çalışması güncel, yaygın bir ihtiyaç; README geniş veri kaynağı ve agent entegrasyonları sunuyor. 140 günde 1603 yıldız dikkat çekiyor, ancak son 28 günde commit ve farklı yazar olmaması güncel geliştirme faaliyetine dair kanıt sunmuyor; yükselişin sebebi veya gerçek benimsenme düzeyi bu verilerle doğrulanamıyor.

Autonomous AI agent that plays Minecraft on its own — a server-side Fabric mod (MC 1.21.3) where a DeepSeek / OpenAI-compatible LLM drives a

Auditable bioinformatics workflow compiler: Catalog-bound planning, Workflow IR, and validated WDL 1.0.

Yosuri — LESS CHAT, MORE AUTOMATIC. A 24H self-evolving AI agent that aggregates free models into one OpenAI & Anthropic-compatible API, pic