Havuz

A native macOS terminal for agent-driven development, built on Ghostty.

The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of

Run many CLI (Coding) Agents in parallel lanes: issues, worktrees, sessions, and loops on one board. The agentic development environment.

UmaDev: A coding agent that works like a real dev team, commanding the Claude Code / Codex / OpenCode you already use.

Create reusable bots powered by Claude Code, Codex, or OpenCode. Run them locally across your repositories with persistent threads and permi

Automated quality checks that nudge AI coding agents toward better habits

Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.

Multi-agent task orchestration for coding agents. Turn one goal into an ordered plan of tasks (each with its own runner, model and mode), th

Git-native memory for coding agents. Repo memory before the diff.

Planning → verifiable goals → fresh-session implementation for AI coding agents. Based on mattpocock/skills v1.1.

Bug Hunt Bench: 105 real bugs in two production repos, frontier coding models (GPT-6, Claude, Grok, Gemini, DeepSeek...) find and fix them i

Desktop-first, open-source (MIT) application for running parallel agents, and multi-step custom workflows triggered by schedules, webhooks o

Grix : Work with agents like talking to people.

HAR: open agent harness (CLI + MCP) for coding agents. Isolated worktrees, deterministic verify, software factory workflows for Claude Code,

Open-source agent sandbox infrastructure for parallel coding agents: isolated workspaces, MCP/CLI control, observability, and atomic publica

Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-

A local CLI, built on ccusage, that syncs your token usage with everyone else.

The open archive of how AI agents actually work. A versioned, verifiable archive of system prompts, developer instructions, tool schemas an

Sandbox for AI coding agents (Claude Code, opencode, pi): runs each project in an isolated microVM with host-side secret injection. Linux/KV

Native macOS video editor that coding agents can drive: everything the UI does, Claude Code and Codex can do through the bashcut CLI or MCP

Spec-driven development and context engineering for Claude Code, Cursor, Codex, and GitHub Copilot — backed by project context in Git.

Run coding agents unattended. Agents write the code. Axocoatl writes the receipt. Claude Code, Codex or a local model in a sandbox; the host

Dispatch your task backlog to local, interactive AI coding agents. One git worktree per task, sandboxed by default.

AST-Aware, Personalized-PageRank-Ranked, Token-Budgeted Codebase Compressor for LLMs

Free, open-source desktop app to run Claude Code, Codex, Cursor CLI and Antigravity agents in parallel with git worktrees and diff review.

Open Agent Team: One screen for the whole team. One key to take over any agent.

Self-hosted remote control for your coding agents: Claude Code and Codex chats, approvals, terminals, files, git and dev-server previews for

Track what every AI coding agent costs and see the limit coming. Per-session, per-model cost for Claude Code, Codex, Cursor and 37 more tool

OpenAI-compatible inference server for Qwen3.8 on one RTX 5090 / RTX PRO 6000: the 27B at ~170 tok/s (peaks ~370), Flash-Next (125B MoE) at

Multi-client ACP session daemon: spawn coding agents, share live sessions across terminals, editors and browsers

Run AI coding agents in parallel on one git repo and safely auto-merge their work — only changes that build and pass tests land. On top of p

A visual benchmark testing whether leading coding agents repeat the same design patterns across 100 neutral website briefs.

Verify what AI coding agents can actually read, write, execute and reach using synthetic canaries.

The animated diagram editor AI agents can draw on. Animated technical diagrams (architecture, sequence, BPMN, cloud icons) built by you and

Review code changes by what they do, and learn the concepts behind them.

Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and

A local terminal control plane for Codex, Claude Code, and pi sessions—discover, monitor, resume, and work beside persistent workspace shell

Hand your software work to Claude Code, Codex and GitHub Copilot agents and steer it from a local board, in the browser or on your phone.

Drive the OpenAI Codex Micro macro pad from Claude Code. Six Agent Keys show which of your projects needs you, and pressing one jumps to its

Spec-driven development that doesn't stop at the code: coding agents take an idea to release, and you make the calls.

Blinded battles between coding agents: two agents, one prompt, you pick the winner. Desktop app, runs locally.

The Last Remote Sensing Model Built by Humans? Casting any Earth observation task as recursive self-improvement. Code coming soon.

Lightweight Git workspaces for parallel development.

Contribution research for agents: check repository guidance, related work, code context, and validation before writing a patch.

Self-hosted remote control for Claude Code, Codex, OpenCode, Kimi Code, Grok Build and Cursor: run coding agents on your own machines and su

Give every agent session its own VM. One command up, zero burn when idle.

See when Claude Code, Codex, OpenCode or pi need you, and answer from the Mac notch. Free, open source, local-only.

Jev-powered plugins for coding agents

Every coding agent, every account, one app: run Codex, Claude Code and other agent CLIs with the sign-in you already have.

The complete AI operating model for software teams — from first idea to production. Three peer-supervised loops (discovery → build → release