Havuz

Runtime for coding-agent harnesses. Run Claude Code, Codex, OpenCode, Pi, and Grok in one terminal; hop live between them; search or resume

Cross-platform .NET performance engineering skill for coding agents, covering CPU, memory, GC, benchmarking, concurrency, startup, native pr

Agent skills for coding CLIs, multi-agent runtimes, context engines, MCP extensions, and terminal tooling. Instead of using claude code's so

Your coding agent says "done". Orvant asks for proof. A skill for Claude Code, Codex and other file-capable agents, plus a Python engine tha

Wakes your Mac for scheduled jobs, holds it awake while long work finishes, and lets it sleep otherwise. Finds the cron jobs that have been

The networked cross-session for coding agents — @mention another team's AI so yours and theirs integrate directly across sessions, machines,

Frontier model solution tracing, then made the prompting skills

When an agent needs you, answer from your phone — self-hosted, end-to-end encrypted control of your coding agents.

AGENTS.md contract for AI coding agents + zero-dependency linter + SessionStart hook. Works with Claude Code, Codex, Cursor, Copilot.

Coding Agent insights for teams

AI agents now operate with authority. Authority without discipline is how complex systems fail. Nuclear’s control loop, ported to AI-assiste

Your coding agent says done. Show the receipt. Evidence-first workflows, practical skills, and plugins for Claude Code and Codex.

A native macOS code editor for CLI-agent workflows. Split editor and terminal panes, a cross-project Agent Inbox, private notifications, LSP

Curion is a project-local memory layer for AI coding agents, published as an MCP server for Claude Code, Codex, OpenCode, and other MCP clie

Retrieval + inference offload for AI coding agents.

Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies i

Local-first AI coding agent for desktop, terminal, VS Code, Visual Studio, and CI code reviews.

Structure-first operating process for AI coding agents: Blast / Mid / Inner build altitudes with clear ownership, then T1 structural, T2 bug

Open visible sibling AI sessions in Herdr or tmux. Reopen, message or retire supported siblings by garden id—retirement only on explicit req

Styx is where everything converges: every repo you work in, the AI coding agents building in them, and every login they need to ship. Switch

A work journal your coding agents write to. Evidence required.

Pi coding agent extension for focused code retrieval, grounded edits, safety checks, and language-server support.

Human-in-the-loop multi-agent task orchestration platform for Git-based software workflows.

Desktop provider manager and local failover router for Codex, Claude Code, and Grok.

Diff filter that expands every hunk to include the enclosing function or block via tree-sitter. Pager for git, gh, or lazygit; viewer for co

Secure MCP access to local repositories — without shell, Git, or arbitrary writes.

A tool that replaces everything that can be deterministic in repository work: search, symbols, callers, task scope, history, review and Git

A native macOS multi-agent terminal orchestrator: manager-driven agent trees for Claude Code, Codex, and OpenCode

Forkable shell substrate for a single code repository — DB-backed identity, memory, roadmap, content; harness-agnostic boot. We build the da

Generative UI for working with coding agents. Review, annotate, brainstorm, and give feedback through task-specific desktop workbenches.

Local-first mindmap for organizing persistent tmux terminals and coding-agent work.

A native macOS kanban board for mattpocock/skills tickets. Live agent sessions with their steps and changed files, read-only, free and open

Governed local runtime for AI coding agents: task lifecycle, mandatory gates, reviews, doc-impact checks, and auditable completion.

CLI debugger that lets coding agents inspect live Python runtime state, with optional MCP integration.

A platform evolution of OpenAI Symphony (openai/symphony) for running Codex, Claude Code, CodeBuddy Code, and OpenCode from real project tas

Relational codebase compiler and spec-driven containment engine for AI coding agents. Compiles polyglot repos (Rust, Python, TS, Go, C/C++,

SWE-bench for your codebase — mine your merged PRs into local, contamination-free coding-agent benchmarks. Adapters: claude-code, aider (Opu

TuckBit: right tools, scoped context and adaptive workflows on cue. Portable efficiency skills/plugins for Codex, Claude, Gemini and more.

An analytics tool to explore Claude code usage patterns, errors, and token costs

Skill pack that turns any coding agent (Claude Code, Codex, AGENTS.md-compatible) into a senior production engineer — FastAPI, PostgreSQL, D

Agent-first runbook and scripts for running the public Farcaster client in an iOS Simulator.

Bounded loops for coding agents: test gates, held-out acceptance checks, hard stops, git-backed resume

Extensions, tools, and integrations for the pi coding agent.

Your AI coding agents keep working while you sleep. Drive Claude Code, Codex, Gemini, opencode & more from your phone: resume past usage lim

The agent-native design canvas - a design/ folder, one command, live frames from your repo's real components. Comment @marver and your own c

Durable, repo-native project memory for coding agents, without context bloat.

Every agent turn becomes a traceable commit carrying the full interaction trace, model, and token cost, plus a live dashboard and a coach th

Six skills tell coding agents how to work. Two guards enforce the parts that should not depend on judgment.

Local, deterministic review of Git changes: weakened tests and CI gates, security boundaries, blast radius. CLI, GitHub Action, MCP server,