Havuz

Open-source AI coding agent CLI with multi-provider support, local models, MCP, and specialized AI agents.

Terminal-native AI assistant built specifically for Termux and Android development.

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?

A small, fast, open-source home for AI coding agents

Validate, repair, and retry LLM structured outputs. 13 repair strategies for common JSON malformations, JSON Schema validation, and retry-wi

An LLM-powered social simulation and roleplaying engine where NPCs have their own lives too.

Write commit messages, grep by meaning, turn English into shell — small composable CLI tools backed by an LLM. Local by default (no API key)

Your AI works the night shift — read-only reviews of your projects while you're busy, one digest every morning.

Your agent team, on your machine. Open-source harness for multi-user Claude agents.

Local-first desktop app that turns reviewed Git history into auditable weekly reports with Codex, Claude Code, or your own model.

Your AI coding agent just billed you. Here's the receipt. Cost receipts for Claude Code, Codex, Cursor, Gemini & opencode — no account, no u

Proof-driven Claude/Codex agent loop with paired execution, persistent resume, and adversarial security/performance gates.

Self-hosted PaaS for private infrastructure. Deploy 200+ services on any server in one click. GPU monitoring, AI model management, VRAM c

Open-source, agentic web testing platform.

The command center for n8n automation operators: multi-instance management, real-time error tracking, AI-assisted debugging, a Code Lab, and

Agentic AI development loop that splits Design, Code, Review, and Test into isolated roles with deterministic guardrails

Itemized cost receipts for Claude Code and Codex — by turn, verified, local.

Paste your code and get brutally roasted by AI — then refactored into something actually worth shipping.

How much code did AI actually write? Down to every line. Unifies 15+ tools, 600+ model pricing, one-command weekly reports.

Your AI finally remembers your codebase

Standalone observability dashboard and developer playground for the Laravel AI SDK. Zero build steps. Telescope for your AI agents.

One interview writes AGENTS.md and agent skills for your project, plus git and agent hooks that enforce them. Works with Claude Code, Cursor

Athena is a desktop control surface for AI coding agents with shared project context. Built with Electron, React, and FastAPI, it embeds nat

O3 Code brings the Codex desktop experience to a local browser with bridge-powered access to your Mac, workspace, tools, and running agent s

Enterprise-grade AI workspace for legal teams. Self-hostable. AGPL-3.0.

Agent Workflow Kit — Evaluation-first rules, templates, and Skill packages for AI-assisted software projects. Score risk, choose the smalles

AI coding agent workflow engine for structured task lifecycles.

Runtime economic governance for AI agents. Circuit Breaker adds risk-managed execution, cost ceilings, and kill switches to autonomous AI wo

The AI-native JupyterLab — open-source Cursor for notebooks. Cmd+K inline edit, multi-step agent with cell-level tools (read/edit/run), chat