Havuz

Harness/code for DrivingBench v1, which allows frontier LLMs to control cars via Comma/openpilot + MCP tools.

The AI-native wire format for structured data. 100% comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ lossless roun

CCB · AI 编程助手一键配置 —— 把 Trae / Qoder / CodeBuddy / WorkBuddy / Cursor / ZCode 等客户端一键接入 CCB：全部模型自动写入、自动设为默认、自动启动（仅桌面客户端开源）

Evidence-backed knowledge graph construction with typed Jev relation decisions

Carves your agent's tool outputs down to what matters. Never cuts what doesn't come back.

Testing skills for AI coding agents: evidence-backed strategy, executable cases, Playwright/API testing, regression and QA memory. 面向 AI Age

An iPad IDE with local LLM inference on an AMD GPU over Thunderbolt: the upstream Linux amdgpu driver embedded as DriverKit, LemonSeed Engin

24/7 AI-DJ radio in Go. Persistent ffmpeg→Icecast with live ducking, LLM banter, BYOK, editable skills. ~50MB RAM.

⚔️ Compare AI models side by side — same prompt, streamed answers, live code previews, speed, tokens and cost. Keys never leave your browser

Local-first research tool with explicit fetch decisions, source evidence, and cited reports. CLI and MCP interfaces. Python, MIT.

One command to install, heal & prove ruflo (claude-flow) + agentic-qe + RuvNet Brain — plus ambidextrous Claude/Codex/OpenCode host routing,

Open-source, self-hostable, always-on personal agent with its own computer. Runs on Cloudflare Workers or Node.

Optimize LLM agent harnesses through tunable Formulas to dynamically enhance the agent, and improve those Formulas with optimizers based on

Open Source Brain Platform | AI training and inference in Rust

Big models. Small Macs. Zero excuses.

Turn any document into clean, AI-ready Markdown — locally on your machine. Desktop app for Windows, macOS & Linux powered by MarkItDown, Doc

Open-source email infrastructure for AI agents.

ast-outline lets AI coding agents pull exactly the code context they need — a repo skeleton, a file outline, or one symbol — instead of read

Turn noisy command output into a short, actionable first pass for coding agents.

Self-hosted PII redaction proxy for LLM APIs and agent CLIs. Scrubs names, emails and secrets from Claude Code, Codex and any OpenAI-compati

Open-source platform for creating, distributing and running sovereign EU-compliant LLMs. Verticalize any model for your domain, language and

Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at

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

MIT-licensed, backend-agnostic AI agent orchestration loop in Python: orchestrator→worker→reviewer as a deterministic harness. Drive coding-

Metarhia skills 🪄

Hybrid GPU + CPU inference for mixture-of-experts models, written in Rust down to the CUDA kernels. A drop-in llama-server.

An fzf-inspired issue tracker with vim mode and LLM-assisted backlog refinement. Jira today, more providers coming.

The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.

AI-powered QA testing framework that uses LLMs (Claude or GPT) to test web apps, CLI tools, and TUI programs from markdown story cards, retu

llama.cpp performance patches developed and measured on Tesla P100 (GP100, sm_60). Most are not Pascal-specific.

輸入文字或圖片，LLM會找出適合的梗圖來回覆你

Turn scattered knowledge, operational data, and history into source-linked context that your agents can inspect, explain, and reuse.

A local review board for work an agent wants a human to look at — agent publishes, you annotate in the browser, feedback flows back as JSON.

Production-ready, bleeding-edge, upstream-first vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a), verified against real models on

面向 AI 时代的数据可视化规范与工作流库 — specification & workflow library for AI-era data visualization

Open-source agent execution-recovery controller for coding and tool-using AI agents.

A terminal AI agent you can fully undo - every file and shell action is snapshotted and reversible. Model-agnostic (any LLM), and connects t

Keep your Claude Code / Codex 5h rate-limit windows back-to-back — auto-pings each provider the moment its window resets. | 在 5 小时限额窗口重置的瞬间

让任何 AI 真正"看"视频：纯本地的视频阅读 skill——faster-whisper GPU 转写 + ffmpeg 场景感知抽帧，双通道带时间戳（t=MM:SS），数据不出机。1 小时视频 3~5 分钟读完。Give any AI agent eyes for video

Local-first AI PKM for coding conversations: import Claude Code/Cursor/Codex, distill notes, semantic search, tag graph, MCP memory.

An open-source, coding agent harness designed specifically for local LLMs. Designed as everything a user needs to jumpstart their own harnes

Privacy-focused AI conversation platform for chat, coding, research, and documents.

Is your CLI ready for AI agents? Automated checks to ensure optimum agentic CLI use: don't block agents, don't waste tokens, ensure safe use

Cloud native chaos engineering toolkit for Go. Inject faults across HTTP, gRPC, Kafka, Redis, SQL, and MongoDB. YAML defined policies, multi

Benchmark your local LLMs: speed, memory, and quality, in one command. TUI leaderboard for Ollama, LM Studio, llama.cpp, and vLLM.

Keep private data, internal infrastructure and secrets out of cloud coding agents without breaking your workflow.

MIT-licensed TypeScript runtime for AI-native game characters and worlds, with durable state, reliable actions, memory, tools, and Unity, Go

Blazing fast Go port of gemini-web2api. Convert Google Gemini web into OpenAI-compatible API. Zero cost, single static binary.

Native Code Graph · Extreme KV-Cache · Cross-Platform All-in-One Agent (TUI, WebUI, Desktop, OpenWRT) | 原生代码图谱 · 极致缓存 · 跨平台全能型 Agent（TUI / W