Havuz

Production-ready multi-agent platform delivering orchestration, session governance and audit capabilities. Stack: Go/Python/Rust microservic

Fly the web on a string — a lightweight (~7MB) Rust browser-automation MCP server for AI agents. Streamable HTTP, 21 tools, HTML→PDF, plus a

Infinite scroll terminal multiplexer and agent orchestrator for macOS

An advanced AI-powered engineering intelligence, intent-tracking, and automated code maintenance platform.

小白也能上手的 Claude Code / Codex 上游配置切换桌面应用 | A cross-platform, site-driven desktop app for switching Claude Code & Codex providers

Desktop client for the Asale token-sharing network: sell idle Claude, ChatGPT/Codex, Gemini, Kimi and Grok subscription quota for USDT, or b

The open world for autonomous AI agents on Solana Trade. Build. Fight. Earn. Explore. Connect your AI agent to a persistent shared world. Tr

Privacy-aware environmental digital twin for ambient/RF sensing in Rust — a typed, provenance-tracked graph of rooms, sensors, people & beli

A very fast, feature-packed, AI-first Markdown (CommonMark/GFM) gem for Ruby, based on pulldown-cmark (Rust).

Typed decisions from unstructured state: one forward pass, zero generated text. Local, deterministic, Jev-compatible. Not affiliated with ty

Native OpenCoven workspace for familiars, agent sessions, memory, tools, workflows, and local-first development.

X-ray for documents: lossless PDF & PPTX extraction to JSON with bounding boxes, fonts, and colors — CLI, HTTP API, and an in-browser playgr

SAP NWRFC → REST gateway designed for AI agents: search, inspect, invoke RFC/BAPI, read tables, triage ST22 dumps, and edit ABAP code over p

A code knowledge graph built for LLM agents — accurate answers, minimal tokens, maximum speed

Serverless, end-to-end-encrypted, no-account sync for your own devices — memory, tabs, and files. No cloud. MCP-native, so your AI uses the

BBARIT Terminal (빠릿터미널) — free AI vibe coding IDE, terminal & agent in one, built 100% in Rust. Ships ⚡ BBARIT Agent (built-in coding agent

See where your AI coding tokens and dollars actually go — a local-first usage dashboard for AI coding agents.

Your product idea. One command. Shipped. The Hyper-Scale Solo Infrastructure(TS 7.0, Bun1.4, oRPC v2, Nix devenv)

Local-first DOCX editing for agents and automation, with native Microsoft Word tracked changes.

Foundational ternary-model inference & training library — CUDA + CPU, BitNet/TQ ternary kernels

Fast, local-first Git desktop client, code intelligence suite, and task workspace built with Rust (Tauri 2) and Svelte 5. 100% on-device, ze

Agentic coding scheduler, a Rust agent harness that runs background coding agents autonomously

Extract domain knowledge from codebases to reduce LLM token consumption by 20x and time in agentic search by 10x — gathers and makes concept

Ask for the symbol, not the file. Token-efficient MCP server giving AI coding agents symbol-level reads of TS/JS, Rust, Python, Java, Go,

智能终端命令助手 — 用自然语言生成 Shell 命令，支持 OpenAI/Claude/Gemini/Ollama 等多后端

When Claude Code hits its rate limit, Relay hands off your full session context to Codex, Gemini, Aider, or 5 other agents — so your work ne

A live diff monitor for the terminal pane beside your coding agent. Built to stay open, not opened once per review.

A self-contained Agent Skill for Rust error handling, type invariants, ownership, async correctness, and Clippy.

🔥 Save up to 96% cost — more than Caveman (65%) or RTK (80%). AI coding agent: chat, map, edit, multi-agent. Single Rust binary.

Native desktop control center for AI coding tools — provider switching, local relay, MCP, skills, sessions, usage, and sync. Built with GPUI

AI inference library for mobile devices

CLI-first AI code review — BYOK, diff/scan/branch, pre-commit hooks. 100% open source (MIT).

Android app for cmux: watch and drive your Mac's cmux terminals and AI agents from your phone. Live multi-workspace streaming, QR pairing, T

LLM-free, layout-aware PDF chunking for RAG pipelines. Preserves document structure via regex and font heuristics. Written in pure Rust.

Portable, always-fresh docs for agents and humans. A Surface hub is a conformant OKF concept; Surface adds the freshness OKF leaves out - it

EasyOCR's accuracy in a single Rust binary: CRAFT text detection and gen2 CRNN recognition over ONNX, with no Python runtime.

High-performance Rust token compression engine for LLM inputs. Plugin-based, 50–95% token savings, AI-export diagnostics, CLI / Server / IDE

Cryptographic trust and authorization evidence for AI agents. Every action a receipt, every grant a proof.

Local LLM chat app for Apple Silicon Macs.

The most comprehensive agent skills for writing real, idiomatic Rust and porting code from other languages.

A high-performance, local, offline-first AI memory system built in Rust

A Rust crate to connect multiple harnesses under one, simple, up-to-date interface.

NPU-first local LLM runtime for Snapdragon X Elite (Windows on ARM)

A free, private, local AI for any app. One command, OpenAI-compatible, no API key.

A process manager written in Rust, and a pm2 alternative: one supervisor daemon keeps a flock of long-running processes alive on Linux, macO

A typed, replayable, budget-aware programming language for LLM agents. Compiles to Python & TypeScript.

Real-time meeting & audio transcription for Windows (system audio + mic) — live captions via Deepgram, AI summaries via OpenAI. Tauri 2 + Re

Kreuzberg v4 LTS — long-term support for the v4 line (legacy; superseded by xberg for v5+). MIT-licensed.

Use ChatGPT/Codex OAuth in Claude Code without an API key

Framework-agnostic, local-first memory lifecycle for AI agents: Rust CLI, SQLite/FTS recall, forgetting, audit, consolidation, DOX/Revolve a