Havuz

Semantic cache strategy bench: replay recorded request traces through candidate caching policies and measure which one actually pays off.

23 practical agent skills: TeamWorkflow, multi-model review, media ingestion, and writing. Original Claude Code packages plus a Codex deskto

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

AI commit messages from your local LLM - Ollama / llama-cpp backed, offline, Conventional Commits, with review + changelog modes.

obra/superpowers extended — 14→24 skills, 6 GadaaLabs engineering improvements, override infrastructure, one-command install

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

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.

Interactive terminal coding agent in Rust — runs the DeepSeek V4 Flash model locally on macOS (Metal), with a Ratatui TUI, a full tool suite

Benchmark for the quality of LLM-generated test suites — anti-fragility, rigor, mocking discipline, reuse — scored against human baselines,

Open-source dynamic multi-agent workflows for AI coding agents - the script-as-orchestrator engine behind Claude Code dynamic workflows & ul

本地化个人理财助手 — A股/基金/理财/现金/数字资产/机器人全资产看板 + 市场AI问答 + 个股K线盘口详情 + 板块对比 + 早盘信息简报 + 资讯AI解读。只给客观信息，不荐买卖。

One local, searchable index of your AI coding-agent history Claude Code, Codex, Cursor, Gemini & more. Keyword + semantic search, MCP server

自托管的长篇写作台：Python 后端 + 网页版 + 安卓壳。多 Agent 分工写作、世界状态引擎、568 条 AI 味规则、一键听书。clone 下来就能用，稿子只存在你自己机器上。

Karpathy-inspired coding-agent guidelines packaged for Claude Code, Codex, Cursor, Gemini, OpenCode, Aider, Copilot, OpenClaw, and any AGENT

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured

The open standard for omnipresent AI. Claude Code, OpenCode, Gemini CLI, Shell, Chrome, DeepSeek Harness. Model-agnostic

Open coding agent that matches the best at lower cost: any model, sandboxed, scriptable, embeddable. Engine of Murage.

Command-line tool for Apple's Foundation Models framework.

A coding workspace for AI agents, with a desktop app, terminal CLI, and shared tasks.

Tricorder provides simple, fast, focused feedback when hacking on Haskell (with or without LLM agents).

Multi-agent orchestration & workflow engine. Declarative YAML workflows, LLM coordinator with hub-and-spoke mailboxes, race-safe delivery. O

Ollama Model Test - Figure out the best model for the task

Cost-optimised agent router for Claude Code: sends every sub-task to the cheapest model that can do it, and escalates only on verified failu

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

跨平台桌面工具箱·36+ 工具·AI Chat/翻译/Provider 切换/Claude·Codex 用量洞察·剪贴板/HTTP 调试/取证/编解码/加密。Wails + Go + React + TS

Official code for "CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges"

Open, self-hosted runtime for real-time voice agents — a Rust recreation of ChatGPT's Advanced Voice Mode (GPT-Live), model-neutral

The Fastest enterprise AI gateway — route LLM traffic across OpenAI, Anthropic, Gemini, Groq & 30+ providers via a single API. Self-hosted,

Benchmark for comparing agent harnesses on everyday online tasks — fixes the base model, varies the harness. Sister project of ClawBench, sa

An intelligence layer grounding autonomous agents in verified, real-time knowledge at scale.

Point at any part of your running app, describe the change, and Lasso edits the real source file — not the DOM. Works with Vite and Next.js.

An AI coding harness that shaped itself - repo awareness, surgical edits, validation, recovery, and safe diff approvals.

日本語の文章から「AI 臭さ」を機械的に拾う Rust 製の Linter

Token-budget-aware graph navigation for AI coding agents. Serve exactly the noodles your LLM needs. 🍜

先说清你想解决的事，再开始学习。问流 WenFlow：从真实问题出发的开源 AI 学习路径原型——对话澄清目标、生成可执行路径、回合式教学、遗忘曲线复习、学习负荷追踪（LSS/KTL/LF/LSB）；自带 18 页管理后台与虚拟学习者仿真。Vue3 + Node.js + SQL

Run Claude Code on any LLM provider without losing your setup, local-first proxy with verified profiles, OAuth device-flow login, failover,

🥷 Give your codebase a black belt. Local code intelligence, security analysis, and compiler-backed facts for humans and AI.

Humanlike — deterministic persona, context, memory and privacy controls for conversational AI agents · Детерминированное поведение ИИ-агенто

Tool-to-Agent Protocol: tools can be smart without embedded LLM calls.

Edit a DeepSeek Harness (dsh) custom mode: system prompt, base mode, and plugin switches.

Open-source factory for generating, validating, and publishing reusable Agent Skills

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

Coding-agent tools on TypeSafe's Jev, measured in public. review-router: caught 13 of 13 CVE fixes a filename rule sent to a quick review. j

Apple Icon Composer CLI & MCP server: create and manipulate .icon bundles and images with Liquid Glass rendering

Claude Code skill that delegates implementation to GPT-6.1 (whatever is the latest) Sol via Codex CLI, Claude plans and reviews the diff, So

Hive mind mechanics for agents. A step closer towards AGI

Open-source agentic software development platform for building, orchestrating and monitoring autonomous AI coding agents.

📊 Automated hourly benchmarks for 20+ NVIDIA NIM models — interactive dashboard, zero infra, self-hostable. Open-source & community-driven.

开源桌面 AI Agent 与 CLI：长期记忆、多 Agent、实时语音；Qwen3.8-27B Coder390 EfficientThink 本地 GGUF（llama.cpp Q2/Q3，内置 Q4 MTP）· Open-source desktop AI agent &

One free AI endpoint, every free tier behind it. Local OpenAI-compatible gateway routing across OpenRouter, Groq, NVIDIA NIM, Cloudflare Wor