AI tools for “refactor”

GitGlow is a local-first visual Git workbench for precise staging, commit history, conflict resolution, coding-agent review, and release preparation.

Draw or trace a floor plan free in your browser, furnish it from 10,000 models (2,000+ free), walk through it in 3D and export PDF, PNG or DXF. No sign-up.

Budget-driven routing, token compression, and team observability for Claude Code, Codex, Cursor, and Copilot. Route to open weight models mid-task, no quality loss, no code changes.

An AI coding agent for the CLI and your IDE, with one memory that follows your account across chat, the terminal, and your own code. It learns from a correction and applies it everywhere.

AI got your app working. We take it from there: we put it online, open to everyone or behind a sign-in, and give it everything it needs to run, from its database to its backups.

Your AI agents write the code. Your people make the calls. Spec Kitty makes sure coding agents build with what your experts know and what your team decided. Free, MIT CLI for Claude Code, Codex, Cursor, Copilot and 20+…

Local-first workflow orchestration in declarative YAML. One open-source binary with schedules, retries, human tasks, logs, and a Web UI. No database, no framework. Airflow alternative.

Caura (formerly MemClaw): governed memory for AI agent fleets. One persistent memory agents learn from; scopes, policy, audit and isolation built in.

A Node.js CLI tool that automatically generates configuration files for various AI development tools from unified AI rule files.

AgentOS documentation — guides, tutorials, and TypeDoc API reference for building production AI agents with TypeScript. Graph orchestration, cognitive memory, RAG, guardrails, voice pipelines, and 13 LLM providers.

Keep the decisions, discoveries, and fixes from your work ready for the next session. Open-source claude-mem captures memory; CMEM Pro adds hosted observation, cloud sync, and MCP recall.

Turbo Flow is the open-source rules layer for AI-written code: rig-lite, a portable governance kit — fail-closed cross-model review gate, constitution, git-versioned memory. Works with any harness. Agents build, humans…

QuotioDocsChangelogSearch⌘KQuotio1.0 betaYour command center for AI coding quotas, accounts, and local agents.Download for MacmacOS 14+Quotio shows how much quota you have left across Claude, Codex, Gemini, Copilot and…

Open-source coding agent that runs in your terminal and talks to any model: OpenAI, Gemini, Ollama, GitHub Models, and 200+ more. One install, every provider.

Free, open-source desktop app to browse, install, edit, and organize AI agent skills across Claude Code, Cursor, Codex, and 21 more tools. macOS, Windows, Linux.

Local evidence debugger and trajectory-test toolkit for TypeScript AI agents — framework-faithful execution trees, TraceFacts, TraceContract, Evidence v2, and read-only MCP without a collector or default upload.

Bex is an open-source PaaS for developers and AI agents, with Git deployments, a dashboard, and REST, GraphQL and MCP interfaces. Public alpha; not ready for production workloads.

Coordinate coding agents with Intent. Plan tasks in a shared living spec, review code and diffs, and manage workspaces across your computers and mobile devices.

CCC puts every coding-agent session, every engine, however you launched it, on one local board and tells you which one needs you. Local, source-available, and free to use and modify, including at work.

Token Telemetry is local, read-only observability for 20 coding agents (Claude Code, Codex, Gemini CLI, Cursor, Copilot, Qwen, OpenCode, Vibe, Antigravity, Grok Build, Cline, SmallCode, Pi, Oh My Pi, Muse Code, Prime…