Havuz

Pixir: supervised subagents and workflows for coding agents

Make your specs actually comprehensive. Pair your specs with tests to make your coding agent stop improvising bad code

A Flutter client for herdr: a status board and live terminal for the coding agents on your own machines. Over SSH, with no bridge binary to

ACP-friendly Node.js SDK for local coding agents: run Codex, Claude Code, Cursor, OpenCode, and Pi with streaming, abort, and session resume

Pi coding-agent harness with durable sessions, causal history, reversible components, and approval-gated host self-extension.

A state machine protocol for running controlled ML experiments with coding agents.

Agentic coding framework and meta-harness for planning, building, reviewing, and tuning software across coding agents. Portable agent squads

Reversible side effects for AI coding agents — snapshot files, hold PostgreSQL writes, and review outbound actions before they become perman

Continuously refine your project’s engineering philosophy — and keep AI coding agents honest with evidence-backed completion.

Local-first workspace for open-source maintainers and coding agents.

Bounded repository context and verified patches for Codex and Claude Code. Explicit edit grants, source fingerprints, isolated worktrees, ac

Local two-agent collaboration for Claude Code, Codex, and Grok Build. Keep your native sessions and tools; relay, review, and audit in a sha

Agentic coding scheduler, a Rust agent harness that runs background coding agents autonomously

pando, the worktree tool: one repo, every branch alive. A git worktree per branch, each with its own running dev server, database and sharea

Dynamic workflows for long-running, multi-CLI agent work — you conduct the team, agents raise a hand when they need you, and every step stay

Herdr plugin that hands an in-progress agent session to a fresh session of another installed coding agent, carrying the complete session ins

Open-source repository standard, starter template, validator, and multi-agent workflow for making vibe-coded and AI-generated software under

MCP server and Codex skill for Microsoft FastContext repository exploration

Getting Out of the Loop: 8 Months Solo-Building with AI

Local AI coding-agent history + API cost analytics (loopback-only).

See the AI keys and agents you can't. A read-only check for your Mac, Windows & Linux from GIRD.

Open-source, self-hostable server and runtime core for Run402 — backend infrastructure for AI agents. Postgres/PostgREST with RLS, storage,

Agent-safe version control with Jujutsu (jj) — jj for local change management, Git as the canonical remote/PR/CI/audit interface. Netresearc

CLI for reducing accidental secret disclosure in LLM coding sessions

The pit crew for agentic coding.

Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hooks that trace risky

Model router for AI coding agents: routes routine work to cheaper models with routing rules, 8 subagents, hooks and a CLI runner

WAKE.md for AI agents: compile project state so agents stop starting cold.

Redpen makes coding agents prove they are actually done.

Reproducible evaluation for AI coding agents. Multi-turn scenarios against Claude Code, Codex, Copilot, Cursor, Gemini CLI, Goose, OpenCode,

The factory that builds software — and itself. A runtime for self-improving agentic loops: the tracker is the control plane, git is the trut

Give your AI coding agent a voice: it speaks its decisions and questions, you answer by talking, and it can change your desktop. Local by de

Local task-state ledger for AI coding agents. Preserve decisions, source conclusions, evidence, and checkpoints across Codex, Claude Code, C

A coding workspace for AI agents, with a desktop app, terminal CLI, and shared tasks.

Git-native decision memory for Claude Code, Codex, Cursor and other coding agents. Preserve constraints and rejected alternatives; surface o

One-click sandboxes for AI agents, with egress policy, MCPs, skills and audit. Built on NVIDIA OpenShell.

Hermes-native skill for systematic coding loops, real verification, and clean agent handoffs

Private, offline AI coding agent for local Qwen models via Ollama — zero dependencies, real tools, multi-agent. Your code never leaves your

A single SKILL.md skill giving coding agents task-aware working modes (debug, fix, review, migrate, …) — works with Hermes, Claude Code, Cod

Entente — provenance engineering for coding agents: handoffs become confirmable, verifiable, retryable contracts; agents form a network with

Shared project knowledge and handoff for coding agents across long-running projects

The public marketplace for GitBot, discover, inspect, install, and publish reusable bots for Claude Code, Codex, and OpenCode.

Structural memory for coding agents — index your repo once, query symbols, callers, and call-edges over MCP.

a Lua-scriptable experimental coding harness

Make your coding agent justify architecture with real sources before it builds.

Route every coding task to the best AI agent on your machine — Claude Code, Codex, Cursor, Gemini CLI, Aider, OpenCode. Installs as a Claude

Your AI agent needs your API keys. It doesn't need to see them. tokenstash writes keys straight into .env.local for Claude Code, Codex, Curs

A practical workflow for reliable AI-assisted software development

Multi-host TUI and paired browser control plane for persistent Herdr coding-agent sessions

Occam's razor for Claude Code and Codex: a 30-line rule set. Benchmarks vs base: 51-55% lower estimated task cost on Opus/Sonnet 5.5 max wit