Havuz

Recommend AI coding harness changes from repository context and coding signals, then distribute approved rules, skills, hooks and agents to

Make the AI coding agents on your machine (Claude Code, Codex, Reasonix, ZCode) work as one team. Zero-dependency, local, MCP + CLI.

Proof-of-done for AI coding agents. Local evidence receipts for Codex, Claude Code, Cursor, and GitHub Actions.

Benchmark of AI coding agents building web apps and deploying them to Cloudish, DigitalOcean, Render and Vercel, measuring success, time, to

Open-source ADR workflow for coding agents: 14 skills that scaffold and manage Architecture Decision Records, a plan queue and AGENTS.md con

One-line Oz MCP setup for coding agents

Wordcell keeps decisions, plans, and sources as Markdown beside your code, so coding agents can find them from the file they are about to ch

Compact coding-agent context without summarizing it away. Verbatim, offline, with a receipt and recall for every cut. CLI, MCP server, Claud

Reviewable capability layer for coding agents: portable skills, workflow patterns, verification gates, token-efficient execution, and bounde

Have a skip-level with your coding agents. Local transcripts become The 360 Review: a two-sided performance review of you and your agent.

eBPF Prometheus exporter for AI-agent activity — per-agent tools, domains, ports, files, CPU & network — with a Grafana dashboard. A yeet se

rollout grep: local search, stats, and trajectory analysis over coding-agent sessions (Claude Code, Codex, Cursor, Grok, Hermes, opencode)

Local-first desktop control room for coding agents. Run Codex, Claude Code, Cursor, Grok, Mistral, Pi, and local models together — each with

Coordination ledger for coding agents: what was decided, what's still open, where you parked — durable across sessions, repos, and weeks. Me

Brakes for the software factory: deterministic checks, a fresh-context reviewer that commits its fixes, and one-way-door triage for coding a

Coding agent harness, achieved SWE Bench Lite resolve rate of 52.4%

Retired. Excalibur (xcb) routed coding tasks across Codex and Claude Code subscriptions. Source and releases are preserved for reference.

Eval framework that ranks agentic coding frameworks (Superpowers, Compound Engineering, Agent Skills, GSD) by having each build the same spe

cmux plugin for Herdr: live sidebar status pills, tab/pane mirroring, nested agents CLI

Local credential control for AI coding agents.

The IDE for your coding agents. Use Claude Code, Codex, or any CLI agent in a real workspace; files, editor, browser, and git, all agent-awa

A local verification receipt for AI coding agents

Learn your codebases through self-quizzing and study. Track your knowledge coverage over time.

Better code search for coding agents: Claude Code, Codex, Cursor, OpenCode and Pi spend fewer tokens, tool calls and time.

A small, file-first verification harness that turns an AI agent's "I'm done" claim into an auditable admission decision. 100% offline & zero

Offline-first toolkit for agent-ready repositories: readiness scoring, instruction graphs, context packs, policy/rule packs, MCP, GitHub Act

Gobstopper is an intelligent compaction proxy for Claude Code and Codex. It compacts more often, keeps history local, and cut tokens 29% on

Run Codex and Claude Code reliably in the background on macOS—with a native dashboard, persistent tmux sessions, local checkpoints, recovery

Run agents on a cloud machine. Steer them from your desktop or phone.

FinishUP — local-first structured work evidence, deterministic checks, and honest verification receipts.

A spatial workspace for directing AI coding agents like an engineering director

See which external pull requests need context before code review. Deterministic, no login, no AI.

OMP-native workspace for orchestrating coding agents across local and remote hosts

Local code-intelligence pipeline for AI coding agents: architecture maps, hotspots, change impact, and structural regression gates before th

Persistent coding intelligence for Codex — project-aware context, adaptive reasoning, scoped changes, and risk-aware verification.

Portable skills for coding agents — self-contained Markdown procedures that run the same under Claude Code, Codex, or any host that reads th

A shared record for AI agents: decisions, completed work, and commitments, with sources. Git-native engineering memory and a self-hosted sta

Runs Claude Code and pi agents in parallel on your Mac, one Docker sandbox per issue. A host agent hands out the work, watches every sandbox

Several coding agents, one repo, at the same time: a reproducible lab to measure how they coordinate, and Médula, a kernel that decides who

Code navigator for the terminal: find your way around a project and review the code agents write. Go to definition and usages without a lang

The menu bar worth keeping for AI coding — Claude Code / Codex quota at a glance, everything else opt-in.

Keep an eye on your AI coding agents: a live browser view of your agents, and CLI-based mail for them to collaborate on Tasks.

Practical Claude Code runbooks for clean, resource-efficient open-source development - from planning and implementation to debugging, review

Talk to all your coding agents. One hands-free, full-duplex voice conversation over Claude Code, Codex and OpenCode. Runs on macOS and Windo

Runtime-adaptive steering layer and portable control contract for hard agentic work: durable goals, proportional control, bounded delegation

Native macOS client for Herdr: manage coding agent sessions with a live terminal, file explorer, editor and Git tools.

Repo-owned engineering memory for coding agents — preserve decisions, failures, domain knowledge, and deferred work across sessions, teams,

A Rust crate to connect multiple harnesses under one, simple, up-to-date interface.

A macOS browser for developers and coding agents. wkdomains lets tools like Codex and Claude Code see the page you are viewing, capture scre

Local-first repository context for coding agents: codegraph, cited project knowledge, change impact, and evidence-backed workflows.