Havuz

AI side-panel assistant for Chrome. Reads the active page and acts on it with your approval — click, type, switch tabs, fill forms. Multi-LL

Low-memory C++20 LLM inference runtime for quantized GGUF models on CPU — mmap-backed weights, paged KV cache, Q4/Q8 kernels, and reproducib

Behavioral testing for AI agents.

Terminal coding agent with browser UI, MCP, Obsidian memory, and live office floor. Any model via OpenRouter. MIT.

:sparkles:只收录免费额度的 LLM 中转站 / 聚合网关。注册赠送、每日签到、部分模型免费、无限免费等

Self-hosted, read-only MCP server that serves IMAP mail from a local notmuch index over authenticated HTTP

Tailor your resume and cover letter to a job posting, inside Chrome. No account, no server - bring your own AI provider key.

Agent-native multi-provider web search for AI agents (Claude Code, Hermes, DeepSeek Harness, OpenCode, Codex). Model grounding (Responses, A

Multi-agent workflow orchestrator with MCP tool servers: planner/executor agents, tool-use loop, MCP client/server, tracing and durable runs

The best AI harness you can run yourself. One file: web UI, tools, memory and orchestration built in. Run a team of agents across providers

Local-first control plane for AI-agent development — watch every Claude Code session live, ledger tasks/worktrees/resources, track token spe

Model-agnostic AI poster grid inspector: detect a poster's layout grid system with a vision model, view it overlaid, and export SVG guides /

A tiny neural-network framework in pure Go with AVX2 SIMD kernels (GOEXPERIMENT=simd)

A local coding harness for Mac. Chat with coding agents across cloud and local models, watch every tool call in a live activity feed, and dr

Agents can work. They cannot declare success. A governed coordination protocol for multi-agent AI work: eight contracts (task, resource, own

A coding agent harness built specifically for Motif-3

Reasoning-effort editing for third-party models in DeepSeek Harness: per-model thinking levels with a knowledge base + protocol inference, e

ChungusHub is a local-first, privacy-focused LLM frontend for roleplay.

Ground Truth: A working developer's path into AI and machine learning, with interactive explanations, reproducible Python labs, and practica

Durable, traceable project memory for AI coding agents. An evolution of Karpathy's LLM Wiki pattern built for codebases.

🐮 牛来动画生成器 —— 输入一段小故事，一条命令产出还原电影《牛来》风格的抽象动画：无厘头台词、严格同步的字幕与配音、粗糙低模的直立牛。Three.js 程序化 3D 渲染 + DeepSeek 剧本生成 + TTS 配音 + FFmpeg 合成，不依赖视频大模型。AI vid

Open Source Alternative to Grok Bot, muse by meta and dots by openai

DSH web plugin: per-day token usage statistics with a GitHub-style activity heatmap, cache hit-rate curve and per-model breakdown

Math Modeling AI Agent Flow | 数学建模全流程 AI 助手（国赛 CUMCM / 美赛 MCM-ICM）。四阶段流水线 Solver→Paper→Finalizer→Growth：解题认证、论文写作、提交终检、赛后复盘。防 AI 幻觉、防版本冲突，可安

a truly open experimental coding harness

Local-first multi-agent coding workbench built on Electron, React and the Mastra framework. 本地优先的开源桌面 AI 工作台，基于 Mastra + Electron，把一次 Agent

Cyberpunk multi-agent command center for DeepSeek Harness — Chinese-first conversation, code execution, VS debate and trajectory workbenches

A self-hosted Cloud API aggregator and control plane for managing LLM inference infrastructure across multiple machines.

OpenAI-compatible API gateway backed by the ChatGPT.com web UI (patchright + real Chrome): chat completions, thinking modes, image generatio

Open-source, self-hosted room for AI agent teams. Any model, Claude Code & Codex over ACP, its own computer in a container. Desktop + phone.

Production-grade, security-first AI platform on a single local K8s cluster — GitOps (ArgoCD), Vault, Kyverno, Falco, self-hosted GPU LLM ser

only-cli, web sayfalarını AI agent’ların daha az token harcayarak inceleyip etkileşebileceği kompakt bir CLI arayüzüne dönüştürür.

Neden yükseliyor · Agent’ların web erişimi ve token maliyetini azaltma ihtiyacına doğrudan hitap ediyor; 40 günde 517 yıldız ve son 28 günde 103 commit dikkat çekiyor. Bu veriler ilgi ve geliştirme temposunu gösterse de benimsenme veya ürün kalitesini tek başına kanıtlamaz.

agy-staff, Claude Code, OpenAI Codex ve Pi kullanıcılarının Google Antigravity CLI üzerinden Gemini tabanlı bir agent’ı farklı görevler için çağırmasını sağlayan bir plugin’dir.

Neden yükseliyor · Farklı coding-agent harness’leri üzerinden agy’ye görev devretme fikri dikkat çekici; 40 günlük yaşına karşılık 652 yıldız ve son 28 günde 14 commit ile 3 farklı yazar görünür bir ilgi ve geliştirme faaliyetine işaret ediyor. Bu veriler kullanım veya kalite kanıtı değildir.

ResumeForge: a professional resume editor with a local AI workbench — fine-grained layout and typography control, a fact ledger that blocks

CrowdGPT is an opensource framework that aims to train AI without any datacenters

OpenFlow — a visual builder for multi-agent AI workflows, built on the opencode engine

基于 Deepseek-Harness 核心底座打造的桌面版 Agent.继承底坐全部能力。并补全 IDE 相关功能。

Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.

数模Agent（数模 Agent）/ 数学建模 AI 助手：多智能体协作完成题意分析、文献检索、建模、代码执行与论文写作，支持人工审核和断点恢复。Local-first multi-agent workbench for mathematical modeling.

AI travel planning engine with deterministic route scheduling, verified POIs, and fact-grounded LLM generation.

Agentic development environment: run Claude Code, Codex, OpenCode and Gemini CLI side by side, and follow every PR from agent to release wit

DeepSeek Harness 插件 · 发送栏一键「优化」提示词草稿：五维诊断 + 改写稿 SSE 流式上屏，可替换 / 复制 / 撤回，模型路由默认跟随当前会话。

Grux AI: open source AI agent for macOS (MIT). One Command Panel for your mail, calendar, meetings, files and a shell it can undo. Runs on a

A TUI agent orchestrator for power users.

The AI frontend you can reshape just by asking.

The open-source Agentic Development Environment (ADE) for FPGA/ASIC work

Локальное обезличивание документов перед отправкой в LLM и обратная подстановка после ответа. Скилл, MCP-сервер и CLI.

Maintain the same context between AI chats, models, and coding agents. Stop re-explaining your project every time you switch AI tools.

Local OCR, metadata automation and RAG document chat for Paperless-ngx using PaddleOCR and Ollama, designed for CPU-only self-hosted servers

Open-Source and Self hosted gateway for MCP. Connect MCP clients to MCP servers through one place for authentication, credentials, policy, a