coding-agents

ctx is a local-first desktop workbench for coding agents, now open source under GPL-3.0. The page explains that it runs agents in a desktop environment with worktrees, transcripts, artifacts, diff review, container boundaries, and a local merge queue.

Darc is a CLI tool for coding agents that indexes prior agent sessions for grep-like memory search and lets teams share encrypted session indexes through Git-backed branches.

A local-first shared development environment for humans and CLI coding agents, with persistent workspaces, worktree-isolated tasks, agent coordination, and built-in review and browser tools.

Open-source visual workspace for building with coding agents like Codex and Claude Code, with session management, task tracking, diffs, and custom editors.

Self-hostable MCP server that collects memories from coding agents and regenerates shared AGENTS.md-style context for the next session.

Maxxwell is a workspace for managing multiple coding agents at once. It tracks agent progress, highlights stuck work, and surfaces where time is being spent so you can intervene only when needed.

A production-ready Rails SaaS starter designed to give coding agents strong architectural context, with authentication, billing, authorization, Hotwire, Tailwind, Kamal, and repo-based guidance for extending the app consistently.

Blume Sidecar is a desktop companion for managing coding agents across tools like Cursor, Claude Code, and Codex. It tracks agent activity, monitors rules and hidden files, shows usage limits, and suggests fixes when instructions drift from chat context.

ModelPeer is an open-source tool for cross-model peer review in coding workflows. It lets Claude Code, Codex CLI, and Gemini CLI review one another as read-only engineering peers, with commands for consultation, diff review, setup, updates, and safety controls.

Self-hosted voice assistant that can answer aloud, dictate text, run shell commands, control mouse and keyboard, and connect to MCP-enabled services. It can hand off heavier tasks to coding agents and run on local hardware or with hosted providers.

ZeroShot is a developer tool for monitoring coding-agent sessions, turning sessions and PR reviews into reusable skills, and enforcing team conventions on every PR.

Stele is a hosted shared memory layer for AI coding agents. It keeps decisions, tasks, lessons, and risks in a project graph that Claude Code, Cursor, Codex, and other MCP-compatible tools can read and write.

Rinkata is a shared project context layer for teams using coding agents, with knowledge capture, goal tracking, decision handling, and evidence packs for completed work.

A repo for keeping coding agents from overengineering by injecting a ruleset during coding and running a slop-check after edits. It supports multiple agent setups, including Claude Code, Codex, OpenCode, Cursor, Copilot, and generic AGENTS.md-based workflows.

Open-source coordination protocol for coding agents that helps detect intent conflicts before code conflicts, built above Git and integrated with tools like Claude Code, Codex, and Cursor.

Local memory and skill layer for coding agents that records procedures, reinforces useful patterns over time, and keeps provenance and trust tied to each memory.

Open standard for product intent and evidence in AI agent-led software work. The repo includes a spec, parser/CLI tools, MCP server support, and loadable agent skills for writing, validating, and reconciling Product Specs.

Wolfpack is a self-hosted control room for persistent coding-agent sessions across your machines, with Tailscale-based private access and support for tools like Claude Code, Codex CLI, Gemini CLI, and shell sessions.

Open-source MCP server for live messaging and coordination between coding agents like Claude Code, Codex, Cursor, Gemini CLI, and Grok Build.

A GitHub project that adds a popup UI for surfacing and editing a coding agent’s implicit assumptions while it works. The README describes how a watcher sub-agent scans session history, generates steering controls, and updates decisions without polluting the main thread.

SHIP is an agentic engineering platform that assigns issues to specialist AI agents to plan, build, review, deploy, and test software on your own infrastructure. The page shows issue-to-PR workflow, mission timelines, cost tracking, model selection, and support for GitHub and Linear.

Heddle is a GitHub repository for a git-native coordination layer for coding agents, using intent leases, isolated worktrees, and gated landings to avoid agents overwriting each other.

Tmux plugin that shows live status markers in window tabs for coding agents like Claude Code, Grok Build, and Pi, with a shortcut to jump to tabs needing attention and optional quota usage display.

A plugin for coding agents that lets them message and coordinate with other agents across sessions, including Claude Code, Codex, and Antigravity.