Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)
Automatically create new skills based on past agent traces
AI-powered multi-agent code review. Simulates a customizable team of Engineers performing code review with built-in discourse.
Curated agent skills by humans. Search, run, install, and keep them current from one CLI.
Persistent memory for AI coding agents: automatic capture, explainable recall, knowledge consolidation, privacy controls, and portable offline storage. One Python file, zero dependencies.
One dashboard for all your local AI coding agents. Switch providers, manage sessions, and orchestrate tasks across Codex, Claude Code, Gemini CLI, CodeBuddy Code, Pi, OpenCode, KiloCode, and OpenClaw. Zero cloud, local-first control plane.
Deploy any Agent Skill as an API via POST /run. The open-source multi-model alternative to Claude Managed Agents, Microsoft Foundry & Mistral/Koyeb — works with any LLM.
Tools for AI agents to test, fix and optimise your codebase
AI agents can now write 99% of the code. This changes what it means to be a developer. Our role shifts to knowing "what good looks like". To do that, we need completely new developer tools. Tendril is what replaces your IDE in an agentic era.
A configurable Bash/PowerShell loop that runs an AI coding CLI with a fresh session each iteration
Command-line interface for Todoist.
IAM Policy Autopilot is an open source static code analysis tool that helps you quickly create baseline AWS IAM policies that you can refine as your application evolves. This tool is available as a command-line utility and MCP server for use within AI coding assistants for quickly building IAM policies.
Hook-based token compressor for 5 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI). Up to 95% bash compression, signature-mode for code reads, cross-call dedup, MCP server, self-teaching protocol. Zero runtime deps.
Persistent, local memory for developers and their coding agents. Records commands, output, errors, and the fixes that worked into SQLite and serves them over MCP.
Manage and orchestrate your Claude Code, Codex, Cursor, Antigravity, Kimi, Grok, Devin, Droid sessions on your Machine. Spawn in parallel, ship in parallel. Open source.
Delegate tasks to DeepSeek right inside your Claude Code / Codex sessions.
Native Liquid Glass AI token tracker for macOS. Breakdown into sessions/models/tools.
Basecamp CLI and Agent Skills
Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI, opencode).
Multi-CLI agent swarm orchestrated by Claude Code: external AI CLIs code in isolated worktrees, Claude verifies and merges
📊 Browse your AI coding spend in the terminal — OpenCode, Claude Code, Codex & friends
Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Cursor CLI, OpenCode, Kilo, Pi, Kimi
Run AI agents isolated in a macOS user account and sandbox-exec. Configured to run Claude Code, OpenAI Codex, Cursor Agent, Google Gemini.
Bring Claude Code, Codex, and your favorite CLI agents into one visual workspace. Run agents in parallel and build executable workflows in isolated Git worktrees. Build your own AI coding team, and turn builds, tests, and dev servers into reusable canvas workflows.