Havuz

Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable

🤖 Bots you run yourself: a daemon on your machine runs each bot through Pi, with web, iOS and macOS apps.

Adaptive Chunking: automatically select the best chunking method per document for RAG. Accepted at LREC 2026.

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

Benzi is code intelligence infrastructure for AI models. It compiles your codebase into a resolved, queryable map of calls, data flow, contr

Which AI coding model, at which effort, on which plan? Recommended efforts, a leaderboard at those efforts and plan advice from modelplan.ai

Long-term memory for any AI agent. One Rust binary, offline, 98.2% recall@5 on LongMemEval-S. Self-host free or use Uteke Cloud.

dsh-model-master（模型选择大师）— model selector for DeepSeek Harness: search across providers, probe any model with a real streaming request to mea

本地优先的视频→结构化笔记服务：B站/抖音/本地视频，平台字幕+本地离线转写，LLM 生成带时间轴笔记；桌面应用 / MCP / Agent Skill 三种接入。

AI-powered Vibe Investing for NASDAQ, S&P500 & crypto: LLM quant trading tools, multi-agent backtesting, and data-driven market columns (mNA

Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite fi

Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compatible.

Run Claude Code against any AI provider. DeepSeek, Groq, Ollama, OpenRouter — your call.

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history,

Community Docker and Kubernetes packaging for DeepSeek Harness (@deepseek-ai/dsh), with a hardened image, Compose stack, Helm chart, Web UI,

Open-source EPUB reader and remote library client for Android, with a Kindle-inspired reading experience

📚 Read a top-tier AI paper in 5 minutes.

Ask your house a question, get a number back. Home Assistant integration for TypeSafe Jev: typed answers as sensors, four actions for automa

Open-source AI office assistant for your desktop: describe the result or file you want in one sentence, and Abu plans and does the rest. Loc

Meet JevEmbed — turn embeddings into decisions. Choose, score, and judge with your choice of embedding model.

Real-time multimodal AI pipelines on Apple Silicon

Open-source desktop coding agent where a lead model plans and cheaper models handle search, edits and review.

Cited Q&A over IIIT Delhi academic rules — answers only from official PDFs, with page links. RAG + FastAPI + Gemini.

An autonomous, always-on agent on your Android phone. It has its own browser, keeps a wiki memory of you, and hands the heavy jobs to your o

Comprehensive scholarly work with your Zotero library: database search, screening, cited answers and checked literature reviews (formerly Zo

SkillAdam: Better Skills for Your AI Agent🚀 Claude Code/Codex/Cursor 插件，一键进化你的skill

The open archive of how AI agents actually work. A versioned, verifiable archive of system prompts, developer instructions, tool schemas an

Use DeepSeek, GLM, Kimi, OpenRouter and more in Codex CLI and Claude Code: one local endpoint, API translation, failover. Single Rust binary

A curated list of code samples and tutorials for building agents on Gemini Enterprise Agent Platform (previously Vertex AI).

Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness: a ctx.memory capability seam with a zero-dependency S

Engineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution, retries, DAGs, agent runtimes, m

🔎 深度研搜对话式多智能体 AI Agents，最适合系统学习 DeepAgents 的实战项目｜AI Deep Research Agent 实战 · LangGraph + RAGFlow + Tavily + FastAPI + WebSocket 从0到工程化落地。前后端

DeepSeek-V4-Flash-0731 284B inference in ~25 GB of RAM / Qwen3.8-Next-Flash inference in ~15 GB of RAM on any M-series MacBook

Word-sized charts for React, made for LLMs and humans — 106 chart types, zero runtime dependencies, accessible by default, RSC-safe.

Look inside any local LLM (GGUF from Ollama, LM Studio, Hugging Face, Jan, llama.cpp): layers, heads, vocabulary, chat template, weights. Ex

A Simple and Universal Product Rehearsal Engine, Speccing Anything. 简洁通用的产品推演引擎，推演万物。

先进且稳定的企业级智能分析平台；面向企业问数、洞察分析的Data Agent，基于数据分析方法论打造可审计、可治理、可复现workflow

Your own team of AI bots in one self-hosted binary: spaces, every account you have, handoffs, approvals and routines. Open-source, self-host

Agent skills for developing Home Assistant integrations and Lovelace cards

Local-first MCP gateway. Set up MCP servers once and use them in every AI client, with secrets in the OS keychain, tool integrity checks and

A living AI-agent office on your desktop wallpaper — Claude Code agents that walk, work, delegate, learn & hold meetings. Per-agent swappabl

📚 An educational, step-by-step implementation of LLM KV cache reuse — learn prefix caching, chunk keys, storage & eviction, from pure Python

Jailbreak system prompt. One file, one speaker, no second-guessing. Paste it as the system prompt on any provider.

Zero-overhead, terminal-native local-LLM orchestrator. Run any engine, any model via the same proxy.

Windows 微信群聊机器人：按设定人设回复群消息，本地运行、接入你自己的模型 API。控制台为原生桌面窗口（27 个面板），发消息/切会话/发图/发表情走后台投递——不动鼠标、不要求微信窗口可见。非官方产品，与腾讯无关。

Open-source AI-assisted writing studio for long-form fiction. 故事设定、正文版本、AI 协作、审稿与交付一体化的长篇小说写作工具。

The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with

The self-hosted platform for your company's AI agents. Your team builds them on Claude Code, Codex or local models, and they work in chats,

shared-memory-vault, birden fazla agent’in bulutla senkronize edilen Markdown dosyaları üzerinden ortak hafıza kullanması için kurallar ve otomasyon script’leri sunuyor.

Neden yükseliyor · 23 günlük bir repoda 96 yıldız dikkat çekiyor; agent hafızası ve ortak bilgi tabanı ihtiyacına doğrudan hitap etmesi ilgi görmüş olabilir. Ancak son 28 günde 1 commit ve 1 farklı yazar var; mevcut veriler geliştirme ivmesini veya topluluk katkısını doğrulamıyor.

Agentic enterprise data analytics: governed facts (DataBridge), reusable methodology (Skill-Hub), and controllable execution (Host)