Havuz

Your marketing department, automated. Open-source Grok Bot alternative specialized in marketing, distribution, and sales.

Скажи словами, что построить — получи работающую версию, проверенную до того, как её назовут готовой. Плагин для Claude Code: сам собирает т

Spark-X2.5, yerel çalıştırma ve agent iş akışları için tasarlanmış 1.7B ve 4B boyutlarında açık dil modelleri serisidir.

Neden yükseliyor · Yeni model serisi; uzun context, küçük model boyutu ve agent/coding yeteneklerini aynı anda öne çıkarıyor. README'de 34 günlük yaş, 386 yıldız ve son 28 günde 9 commit ile 2 farklı yazar bilgisi var; bunlar erken ilgi ve güncel çalışma gösteriyor, ancak model performansını bağımsız olarak kanıtlamıyor.

A 14M-parameter LLM keeps a virtual fish tank alive on an $8 ESP32-S3 — distilled from a 26B teacher into 7.56 MB, no network.

Open-source AI business orchestration platform for running governed AI agents across ERP, CRM, Microsoft 365 and other business systems.

🌊 34 free curated AI models (up to 1M context) for Oh My Pi & Pi. Thin by design — model list, relay proxy, tool-call diagnostics — add your

Universal Zero-Refusal Agent Framework - 40+ jailbreak templates (T1-T119), 1128 curated skills, executable framework-core, installer untuk

The AI analyst that shows its work. Runs Python and R on your own machine, and traces every chart back to the code behind it.

Architectural linting for Swift developers and coding agents

Atlas Inference is a dependency free lightweight inference engine meant to run LLMs on YOUR compute seamlessly. Supports GB10 and Strix Halo

Mine GitHub issues for pain points — LLM semantic analysis, severity scoring, topic clustering & one-click market-research reports.

A visual UX configurator and scaffold generator for Agent frontends.

Evaan — a fully local, offline-capable AI companion chatbot built with Python & Hugging Face Transformers, running on Qwen2.5-0.5B-Instruct

Qwen3.8-27B on one laptop CPU: up to 2.52 token/s, 8 GB tested, no runtime accuracy loss. Native OpenAI-compatible API with function tools;

让 AI 帮你做缠论分析：自动画笔、线段、中枢，标出三类买卖点与背驰，每个信号都带失效价位。脚本负责计算，AI 负责讲人话；可复核、不荐股。适配 WorkBuddy / Claude Code / Codex / OpenClaw。Chan Theory (缠中说禅) engin

dst (data serve tool) — open-source semantic layer and MCP server between the AI your team uses and your data warehouse. Governed answers wi

Rome, kalıcı agent’lar, otomasyonlar ve uygulamalar oluşturup çalıştırmaya yönelik self-hosted bir platform sunuyor.

Neden yükseliyor · 35 günlük yaşında 553 yıldızın yanı sıra son 28 günde 223 commit ve 9 farklı yazar görünmesi, erken dönem ilgisine ve kayda değer geliştirme hareketliliğine işaret ediyor; bunlar tek başına kullanım veya ürün olgunluğu kanıtı değil.

Time-shifting task delegation for DeepSeek Harness (dsh): plan tasks at leisure, they run unattended off-peak, come back to a report. Human-

带 AI 精读大型开源仓库的方法论：四阶段流程、可复用模板、28 条踩坑清单，核心是让每个技术论断都可回溯到源码具体行

Console is a private, native Android app for your self-hosted Hermes Agent: chat that shows the agent's work, voice, bots and rooms, cron, t

PyTorch 기반 한국어 LLM 구현 및 학습 프로젝트

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

One Hermes conductor. Many coding CLIs. Zero trust in self-reports. Production multi-harness orchestration patterns: worktree lanes, verific

Run several Claude Desktop accounts side by side on macOS, sharing Claude Code chats between them

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

A repo investigator for Claude Code and Codex. Offload codebase investigation and get up to 2.7× as much work from the same limits.

The same HTTP API in 10 languages at 3 sizes, 30 implementations. Token cost for LLM agents, plus cold start, latency, throughput, CPU and m

Compile your own LLM for the Hailo-10H — an open pipeline from Hugging Face checkpoint to a self-contained HEF, served with hailo-ollama.

I Ran Qwen 3.8 27B on Just 4GB VRAM! (FreeToken Tutorial) - Edge-native MoE serving engine for local LLMs on low VRAM GPUs

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

Real-time 3D digital twin of an autonomous warehouse — 20 AMRs, deterministic simulation, explainable fleet scheduling, failure injection, V

ACL 2026 Code and Skills for “AMA: Adaptive Memory via Multi-Agent Collaboration”.

Turn a GitHub repository or Hugging Face model into a finished vertical reel: video, cover art and per-platform copy.

AI 产品经理知识 wiki / AI Product Manager Knowledge

DeepSeek Harness bundle: the AgentRouter relay as one pi-ai route with a domestic/international endpoint switch, plus the outbound request c

Agent skills for Dart & Flutter SDK versioning, language features, widget migrations, and minSdk lookups

Sentence-level bilingual mix translator — Chrome extension (MV3). Read the web with your two languages mixed sentence by sentence.

A systems language designed so an AI agent can safely write and run backend code: proven no GC/races/overflow, GBNF-constrained generation,

Rotate Claude and GPT subscriptions and API keys seamlessly inside the Claude Code CLI — switch on usage limits without interrupting your se

Who is really behind that API? Fingerprint any OpenAI-compatible endpoint in the browser: 9 infrastructure probes, side-by-side comparison,

Nuphus — 本地优先的 AI Agent：真实桌面执行力 + 手机第二块屏幕。Local-first AI agent with real desktop execution and dual-device real-time sync.

Keep private data, internal infrastructure and secrets out of cloud coding agents without breaking your workflow.

A collection of public writeups on attacks against AI agents: prompt injection, tool abuse, memory poisoning, and data exfiltration.

Antigravity 跨平台桌面客户端：多账号管理与一键切号，让 IDE/App/CLI 接入 Claude、DeepSeek、GPT、Ollama 等模型 (BYOK) 并优化上下文压缩。 | Multi-account management & switching desk

Official Consensus MCP server. Semantic search over 400M+ research papers, including all of PubMed, for Claude, ChatGPT, Cursor and any MCP

DSH 消息编辑插件：编辑已发送的消息并从该处分叉对话，气泡下方带版本计数与树状视图。Edit a sent message and branch from that point — version counter, tree view, placement presets.

Compact coding-agent harness built for people who prefer to stay in the terminal

CubicLM is a unified cross-platform AI workspace with local GPU acceleration (GGUF, LiteRT-LM). Supports on-device image generation, 23+ clo

WicaraLLM is our Indonesian Small Language Model (56M parameters), built from scratch and trained on a 1.3B-token Indonesian corpus. Enginee

Consensus REST API. Semantic search over 400M+ peer-reviewed research papers, including all of PubMed, for RAG, AI agents and research tools