The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.

One memory shared by Claude Code, Codex, Cursor, Copilot CLI, OpenClaw and 20 more coding agents, built from the session history already on disk. A fix found in one agent comes back in any of them, including months of sessions from before you installed it. No LLM, no embeddings, one local Go binary.

A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions, run secure background agents, and more.

Collaborative multi-agent AI coding workspace: aggregate sessions from Claude Code, Codex, OpenCode, Pi, Grok Build, etc. Desktop app, self-hosted server, or Docker.

Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.

AI coding workstation: Claude Code + web UI + 8 AI CLIs + headless browser + 50+ tools

Lightweight coding agent written in Rust, optimized for memory footprint and performance

A framework-agnostic, git-native standard for defining AI agents

The missing open-source Kubernetes UI with a built-in MCP server for AI agents. See what's broken, why, and what changed. Issues, Topology, event timeline, Helm, GitOps, live service traffic, and cluster audits - all in one Go binary.

Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

Visual testing tool for MCP servers

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

Crabbox: warm a box, sync the diff, run the suite.

Agent Orchestration Command Center

Security testing that runs inside the coding agent you already use. Source-available, not open source.

Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.

Run Linux-style commands on Windows via deterministic bash→PowerShell translation. No VM, no WSL. MCP server + CLI built for AI agents (Claude Code, Codex, OpenCode...). GNU-style output, bash-style errors, UTF-8/GBK handled.

Open-source local workbench for multi-agent software development.

An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration

An evaluation and evolution tool for Agent Skills.

Type `ralph "prompt"` to start open code in a ralph loop. Also supports a prompt file & status check. Open Code, Claude Code, Codex, Copilot

🏄🏼‍♂️ The blackboard for coding agents - agentic development environment for claude code, codex, cursor, opencode, grok and more.

lnwjud — local AI-agent runtime & MCP gateway