Havuz

Application hosting made easy. Push a repo, pick a server, get a deployment - on any hosting, with any price.

Honest local LLM deployment planning and benchmarking for high unified-memory Macs and future Linux/NVIDIA rigs.

Run a 110B on a 2016 PC with 16 GB RAM. Know your tok/s before you download. Placement beats budget: predicts speed + memory fit for any GGU

A faster drop-in replacement for the Firebase Local Emulator Suite: keep your firebase.json, SDKs and ports, and get 40× faster writes, 10×

Paste a GitHub repo URL and see where your stargazers live on an interactive world map. Free, no login.

The Open Source Voice Agent Platform - Build voice agents by connecting nodes in a canvas, deploy them to handle inbound and outbound phone

The stupid coordination tool - tasks and architecture decisions in your repo, behind one CLI any coding agent can call

AI-Agent-ready CLI framework for editing, testing, running, tracing, and diffing Excel VBA projects.

A minimalistic, Git-backed markdown note-taking app for desktop and mobile

Open bridge layer connecting local AI Agent CLIs to web, H5, mini programs, apps, IM, and custom clients.

Linux kernel diagnostics in your terminal. Investigate scheduling, memory pressure and block I/O. Built with Rust.

Non-destructive photo editor for your Immich library and your phone’s gallery. Android and Windows, open source under the AGPL.

MCP management console for the official DeepSeek Harness MCP client: /mcp command with health diagnostics and pipeline trial calls, a Settin

The Biomimetic Context Engine & Neural Runtime for AI Coding Assistants

Save 40%+ on agent token costs with code graphs: call graphs, dependency graphs, dead code detection, and blast radius analysis.

Decentralized git node — self-hostable, Ed25519 identity, HTTP signatures, libp2p gossip. MIT/Apache-2.0.

Cross-platform office automation CLI -- WPS COM on Windows, LibreOffice headless on macOS/Linux. Same commands, any platform.

A local-network remote control for coding agents running on your own computer.

[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.

Desktop app for DeepSeek Harness with a live energy/carbon console: measure local GPU inference, estimate cloud APIs via published coefficie

AI-powered open source contribution finder and repo radar

Lightweight system monitor for Linux VPS

An Orchestrate multiple coding agent desktop app

✅ Acceptance is open-source e2e testing for Agents. Your coding agent turns a prompt into observable checks, runs the real product, and publ

A local-first repository health scanner with actionable scoring for open-source maintainers.

Open-source, Bloomberg-style stock dashboard for the terminal: live quotes and candlestick charts next to AI-scored news, SEC Form 4 insider

💠جمع‌آوری خودکار و رایگان کانفیگ‌های V2Ray از گیتهاب و تلگرام (بدون API). آپدیت هر ۱۵ دقیقه با GitHub Actions. خروجی تفکیک‌شده بر اساس پروتک

The directory page for the people you host services for: no account, multilingual, live status, one tiny container.

NEXBENCH measures what an autonomous agent can actually do on-chain — execute transactions, route swaps, bridge funds, manage DeFi positions

Tiny self-hosted SSH/TUI workspace chat for small teams and operators who want real-time collaboration over SSH.

Download years of statements, receipts, pay stubs and tax forms from 60+ banks, cards, employers, stores and utilities as PDFs, then turn th

Native Mac, iPhone & Apple Watch companion for Claude Code, Codex, Grok and Cursor. Task inbox, wrist notifications, agent handoffs, quota w

"AI 桌面管家 · 多 Agent 协作编排 · 一句话调动团队完成复杂任务

[Public preview] The first public quant trading benchmark scored against what professional traders actually made on the same asset

Security testing that runs inside the coding agent you already use. Source-available, not open source.

A macOS notch companion for Claude Code — your buddy lives here now.

An advanced, responsive, and high-information statusline plugin for Antigravity CLI

Open-source, self-hostable markdown team wiki with a built-in MCP server — so AI agents read, write, and search your docs as first-class tea

One command to explain your Python environment, trace imports, and detect shadows.

Local-first task and context manager for multi-agent AI development workflows.

Self-correcting learning engine for Claude Code — persistent identity, behavioral pattern tracking, and cross-session memory

A Kanban that lives inside your repo. Ordna is a local-first, git-based task board you run from your terminal or your browser.

Turn any Android phone into a full self-hosted Private Cloud & Media Server using Termux, FileBrowser, Jellyfin, and Syncthing.

A linked-list discipline for knowledge, memory and pointer hygiene in large projects: five laws plus portable Python engines (declarative ru

An open-source workspace for coding agents, running on your own machine. More work. Less AI waste. Same subscriptions.

A self-hosted digital picture frame for the Raspberry Pi: a single Go binary that serves an HD slideshow and a browser admin UI, running ent

Git-native truth docs for AI-assisted codebases, keeping branch-scoped documentation aligned with code so changes stay visible, reviewable,

CleeCode: a terminal IDE written in Rust — micro-style editor, file tree, integrated terminals, syntax highlighting, classic drop-down menu

Composable Agent Skills (Claude + OpenAI Codex) for taking an idea from fuzzy → validated → sequenced build → shipped — a manual tier (ideat

OpenScreenShot is a privacy-first, free, open-source screenshot extension -- zero data leaves your device, no account needed, no telemetry,