Havuz

Open-source always on personal agent with its own computer. It remembers your work and keeps going while you're away. Works with any model.

Local-first work memory for Claude Code, Codex and Copilot. Plain Markdown files hold your projects, people, decisions and meetings, with a

迹录 Tracord —— 基于本地小模型多智能体的智能旅行规划助手 / AI travel planner with local SLM multi-agents — light up visited cities on a map, log expenses with one

Cross-model transfer of persistent recurrent inference state without prefix replay

💬 The community space for @openapi — APIs, open source, ideas, projects and conversations.

High-performance CUDA inference engine for Qwen models, written from scratch in C++/CUDA

Obsidian ve Claude Code kullanarak Markdown tabanlı bir kişisel bilgi havuzunu düzenleyen ve güncelleyen agent iş akışları, şablonlar ve yardımcı scriptler sunuyor.

Neden yükseliyor · 20 günlük bir repoda 694 yıldız ve son 28 günde 29 commit dikkat çekiyor; ancak commitlerin tek yazardan gelmesi, ivmenin bağımsız katkıyla doğrulanmadığını gösteriyor. Yükselişin özel nedeni mevcut verilerden kesin olarak bilinmiyor.

llama.cpp fork for significantly improved performance on Ampere generation Nvidia cards (especially RTX 3090 / 3090 Ti): example: 110+ tok/s

Dissenyador visual de workflows i graphs d’IA agentiva · Diseñador visual de workflows y graphs de IA agéntica · Visual designer for agentic

a terminal coding harness

Getting Out of the Loop: 8 Months Solo-Building with AI

Local desktop coding assistant you can run with any local model. No API key required. It can read your project, edit files, run commands, ve

Per-conversation x-opencode-session injection for OpenCode Go in DeepSeek Harness - fixes 400 MissingSessionID without breaking other provid

FreeDeepseekAPI-EN, DeepSeek Web oturumunu yerel ve OpenAI uyumlu API uçları üzerinden istemcilere bağlayan deneysel bir proxy sunar.

Neden yükseliyor · DeepSeek Web’i yaygın API uyumlu araçlara bağlama ve resmi API dışında kullanım olanağı sunma vaadi dikkat çekebilir. Ancak 22 günlük yaş, 37 yıldız ve son 28 günde tek commit ile tek yazar, ilginin sürdürülebilir benimsemeye dönüştüğünü göstermek için henüz zayıf kanıt.

👁️ Review AI generated code and plan changes

Open-source AI job search agents for Claude Code. Polls Greenhouse, Ashby and Lever job boards directly, scores roles against your profile,

Text-to-SQL access control: schema selection that gives the LLM only the tables the caller is allowed to read. Row-level-security-aware tabl

Anyone can predict the future. Almost nobody keeps the receipt. A hash-chained prediction ledger for LLMs — sealed before the answer exists,

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

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。

由 LLM 驱动的可交互智能体：有记忆、有性格、有自己的日程与作息

Ollama-compatible LLM server on a tuned llama.cpp fork. Beats vllm by 40% on single stream decode, and by 20% on multi stream decode, and be

35 native skills for one developer's real workflow — API design to deployment, code review to docs. Self-contained, no external harness requ

DeepSeek Harness (dsh) 插件：注入系统提示词，强制 Agent 的思维链 / 规划 / 工具推理全程使用简体中文，防止中文思考漂移为英文。零外部依赖，任意本地目录 link 即装。

Turn any topic into a 20-30 min cinematic AI documentary: script, visuals, voiceover, music, captions, thumbnails, and YouTube metadata, ful

Generates a test suite from acceptance criteria, then converges code against it with an agent that never sees those criteria.

Version control for AI agent memory. Commit, branch, merge, blame and time-travel what your agents know.

🛠️ toolhub - Turn ANY console script into an LLM tool in 2 seconds. Lightweight, self-hosted, tree-structured alternative to MCP & LangChain

Paste the text you would put in an AI bot's profile. Get back what is already there and the lines that are missing.

ИИ под названием Vortex для любых задач. Сейчас уже доступна рабочая версия проекта, которая ежедневно улучшается

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.

Open-source AI citation monitoring platform.

ENGRAFT: write facts into an LLM's n-gram (Engram) memory table as a removable overlay: 100 facts in a 9 MB file, no weights touched, verifi

Agent 工坊（Agent Workshop）：给它一个 PRD、一个需求点子、或一个可落地的 Agent 方向，它推导出架构方案、组件选型与代码骨架，直到一个能在真实环境运行的产品。

Local, identity-aware speech transcription and diarization engine — turns multi-speaker audio into structured, named intelligence, 100% offl

Autonomous framework for long-running agents: a charter guides Claude Code, Codex or Pi through an actor, critic and scribe loop for hours.

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

RigMark benchmarks local AI the way coding agents actually use it.

学练agent-应试学习,学习ai,题库搜索,练习反馈。StudentBuddy：面向编程入门与自学的开源 AI 学习 Agent，串联资料共读、出题作答、逐题解析与知识复习；支持 Windows 本地版和自托管。

Local multi-provider proxy for Claude Code — automatic failover, priority routing, auto-recovery, usage analytics, and a provider catalog

Hands-on LangChain learning repository covering Chat Models, Prompt Templates, Chains, RAG, Agents, and Tools with practical Python examples

Daedalus CRM — 跑在你自己电脑上的 AI CRM。Mac / Windows 桌面端：个人版免费，团队版按席位收费、客户数据加密同步。AI-native CRM desktop app for macOS & Windows — free for individua

Measurement for coding agents building UI: extract a contract from the reference page, check the implementation, get numbers back

给 AI 角色用的吧台状态引擎。递一杯酒，状态自己会到，几小时后慢慢退掉——引擎只给推力，怎么反应由角色自己决定。

NeoHorse, agent iş akışlarında tool use, coding ve yapılandırılmış kararlar için açık ağırlıklı 4B ve 9B modeller sunuyor.

Neden yükseliyor · 23 günde 1.094 yıldıza ulaşmış; son 28 günde 13 commit ve 6 farklı yazar katkısı da projede yakın dönem geliştirme hareketi olduğunu gösteriyor. README'de model yayını ve arXiv teknik raporu duyurulmuş; ancak ilgi ve ekip aktivitesi, modellerin gerçek kullanımını veya bağımsız başarı teyidini tek başına kanıtlamıyor.

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

Mutual-credit coordination for contributing spare LLM subscription capacity through GitHub issues and pull requests.

Turn CNB cloud-workspace in-network AI into production OpenAI & Anthropic (Claude Code) APIs. Zero deps, v5.2 self-healing HA, quota CLI.

Evidence-grounded financial risk analysis from corporate filings, combining constrained LLM interpretation, deterministic analytics, version

GreatSage · 大贤者 — a Windows desktop voice secretary that listens, remembers across sessions, turns meetings and Markdown notes into cited mi