Havuz

An open-source workspace for coding agents, running on your own machine. More work. Less AI waste. Same subscriptions.

A finite ontology of 115 recurring software elements and a composition framework for LLM-based coding agents

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

All of your agents, shells, and TUIs in one durable terminal workspace

Local-first CLI for coding-agent context handoff. Transfer and resume sessions across Claude Code, Codex, Cursor, Cline, Kimi, Antigravity,

Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph, blast radius, diff-aware revi

Engineering workflows for AI coding agents or flesh engineers. It helps absorb silent base-model quality drift.

DAG runtime for coding-agent workflows with verification, resume, replay, and effect checks.

Accountable long-running coding shifts for Cursor, Codex, and Claude Code. Safe autonomy, recovery, persistent state, and reviewable results

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

Local-first analysis of Claude Code and Codex sessions: token spend, context windows, files touched, and cost.

A Complete faster runtime for coding agents. Optimize the journey, not the hop. Make coding agents 25% faster and 30% cheaper on average whi

Code-quality skills by Max Kanat-Alexander.

Stop Claude Code/Cursor from guessing UI. Extract any website's design system into a spec-valid DESIGN.md that passes the official @google/d

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

Zed extension for Headroom — context compression for AI agents

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

An SDK for verifiable intent, inline with code: one-line claims above your functions, verified at the rigor you choose and flagged when they

ZeroSpec is a zero-dependency Markdown framework that helps AI agents understand your repository structure, rules, and source of truth befor

Resume and hand off Claude Code, Codex & Gemini CLI sessions between agents: one terminal picker for all your local coding-agent history (al

A pure-Python reachability and skeletonization layer that decides what a coding agent actually sees before a request reaches the API.

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

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

Repo-local continuity runtime for AI coding agents. Helps them continue from the same inspectable work state instead of starting cold. Stop

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

Cognitive memory for LLM agents — local-first, and shareable across a team through the cloud.

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

A Codex custom subagent library with 36 project-scoped TOML agents for development, review, testing, DevOps, design, debugging, planning, an

A desktop workspace (inspired by Grok Bot & Muse) for AI agents that collaborate, write code, and use tools. Run locally or on your own serv

Open-source alternative to Claude Artifacts for every coding agent. Any agent ships a self-contained page or app to a live URL — Claude Code

The design layer for agentic AI — design context, interface checks, and verification for coding agents.

Iterative agent harness improvement: run a coding agent on a hard task, generate the reusable tooling it was missing, qualify it, and replay

HEDGEHOG codes Cleaner, Faster and with Fewer Tokens. Hedgehog's AI-driven development builds a task dependency graph from your spec-driven,

Run reviewable, resumable coding-agent workflows across Claude Code, Codex, Gemini, GitHub Copilot CLI, or any CLI. You define the stages in

Build production-ready AI agents in Claude Code from natural language. Analyzes your problem, researches best practices, and generates subag

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

Extract domain knowledge from codebases to reduce LLM token consumption by 20x and time in agentic search by 10x — gathers and makes concept

Agent-managed GitHub merge queue for Codex, Claude Code, Cursor, and MCP clients

Sandboxed Python environments with the uv workflow. Registry-only installs, read-only dependencies, and deny-by-default networking. Local-fi

Multi-session IDALib MCP router for coding agents. Analyze multiple binaries in parallel with IDA-compatible reverse engineering tools.

Superpowers workflow skill pack adapted for Hermes Agent and ChatGPT

Local-first static analysis that turns source code into deterministic, source-grounded workflow maps for coding agents via MCP.

The visual layer of your agent harness. Renders React components and Three.js scenes from source, with structure and evidence behind every f

AI terminal for coding agents: run Claude Code, Codex, and shells side by side on your computer or remote servers. Agents ask each other for

Skill repository to enforce Engineering disclipline in coding assistants

Open-source Codex plugin for Sol-governed multi-agent coding, bounded AI code review, model routing, and LLM cost optimization

Click does not replace Nx, Bazel, pytest, or Jest. It sits above existing verification tools and manages which verification evidence remains

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

A repo investigator for Claude Code and Codex. Offload codebase investigation and get up to 2.7× as much work from the same limits.