Havuz

A coding agent that lives in your terminal. Local Ollama first, or hosted models through the Aether AI fleet.

Forge your own agent harness — a config-to-code generator that renders a thin, standalone Python agent harness you fully own. No LangChain/L

Convert JSON Schema into Pydantic models with runtime validation.

Generate a production-ready, best-practice Claude Code harness tailored to your use case in minutes -- at any skill level. Or validate, upda

CoDA-Bench is a benchmark for code agents on data-intensive tasks. 🎈代码智能体能搞定数据密集型任务吗?

Generate schema-valid Paperclip agent-company bundles from a Markdown brief.

AI-native methodology for Go backend microservices: rebuild the whole codebase from docs/ + .claude/skills, driven by a 12-lens high-perform

让 AI 编程助手（Cursor / Claude Code 等）能更好地编写 Minecraft 模组的完整工具包。

A senior-engineer protocol for polyglot code generation, architecture, testing, security, performance, and agent validation.

Bridges Superpowers + OpenSpec workflows into OpenCode with enforced worktree isolation.

针对中文AI编程的Top 20 提示词，做skill用于辅助codex/claude生成代码

Autonomous AI agent loop that keeps working through your project while you keep planning what comes next.

Train your AI coders the way you'd train a vine — discover your codebase's actual patterns, then encode them as Claude Code rules, skills, a

Beagle is an independent statically typed Lisp derived from Clojure.

Structured file edits for AI agents (JSON/YAML/TOML, markdown, AST, dry-run, MCP). Not a generic filesystem MCP.

Fast, idiomatic Go client for Telegram MTProto: bots, userbots, generated TL types, middleware, plugins, storage, MTProxy, WebSocket, and au

An AI coding agent that reads your code, edits files, runs commands, and reasons through bugs — across a terminal REPL, a full-screen TUI, a

Multi-agent inference framework for RTL generation. A Verilog agent and a Python reference-model agent independently propose implementations

Command-line client for the Harmont CI platform

Open-source, multi-model agent for coding, research, and everyday workflows. Independently built engine with our own Alysis Sandbox, strict

From any API surface to verified AI agent tools: Go CLI + MCP + skills + SQLite + policy + proofs.

Research-first architecture engine for Python, TS, Go and Rust. Mines GitHub Issues for real production failures before scaffolding, then au

Free, open-source AI coding agent for terminal and browser. A Claude Code / Cursor alternative that runs offline with Ollama or with your ow

An open-source, local-first AI teammate and agent operating environment for turning intent into completed work—with tools, memory, permissio

Open-source OpenAPI mock server with cloud hosting and local modes for development, testing, and CI. Generates realistic API responses from

Spec-Driven Development framework that enables humans and AI agents to build better software by giving them small, local instructions right

Cost saving Cognitive Architecture for AI Agents. Infinite Context. Perfect Recall. Zero Hallucinations.

Automatically completes the full workflow from requirement research → research review → planning → plan review → development → development

A native Python agent CLI built on DeepAgents CLI, featuring an independent memory Agent that captures learnings after each task and deliver

A harness optimized to smaller LLMs

Domain-agnostic multi-agent software design and evolution harness

Netbeans Plugin to integrate with Coding Harnesses like Claude, Cursor, OpenCode, Pi, Hermes and Goose using ACP

Zero Code Studio 是一个工程化 AI 代码生成平台，基于 Spring Boot、LangChain4j、LangGraph4j，支持工具调用、Workflow 编排、任务计划规划、三层上下文压缩、SSE 过程可视化、定点修改与一键本地部署。

Zero-reflection .NET source generators: [Log] structured logging, [Trace] OpenTelemetry spans, [Aop] aspects (Retry/Cache/Metrics), Dto/Crud

SQL as a first-class language: formatting, linting, security auditing and pre-commit hooks for your .sql files, plus type-safe code generati

Claude Code skill for using Codex CLI as an execution specialist for implementation-heavy coding work, multi-file refactors, and wrapper-bas

Generate OpenAPI 3.1 specs from Go source code via static analysis — zero annotations, automatic framework detection

Describe a Solana program in plain English - Sigil's AI agent writes the Anchor code.

🦀 Open-source alternative to Claude Code, built from scratch in Rust. Agentic coding CLI — thinks, plans, and executes with any LLM. Compati

The polyglot binding generator behind the xberg.io ecosystem: language-native bindings, packages, docs and e2e tests from one alef.toml.

Learning Hierarchical and Geometry-Aware Graph Representations for Text-to-CAD

Agent 驱动的专业级平面设计工作台 / Agent-powered graphic design workbench that uses HTML/CSS/SVG as the design medium, supporting vector-quality output,

Open-source AI coding agent. Desktop app, bring your own model. Writes code, browses the web, verifies its work. Apache 2.0.

Turn a one-line idea into a branch with tested, reviewed, committed code. The brainstorm-to-commit pipeline for Claude Code.

AI-powered QA agent for VS Code. Analyzes code changes, generates test plans, runs real browser tests, and delivers evidence-backed merge ve

One command. Full stack. Zero compromise. — All-in-one Claude Code skill with 33 modes, 6-layer security, 23 hooks, and 75% token savings

Autonomous AI dev team — 9 Claude agents run as an agile team: plan sprints, write code, review, test, deploy. Runs 24/7 via cron.

Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi

One command to turn any codebase into an MCP server

Curated Claude and Codex skill collection for local AI workflows, automation, research, and product-building.