We check every product on this page once a day and record whether it still answers.
An open-source, self-hosted tool that lets two developers pair-program together on the same live Claude Code session, with the collaboration backend running in their own Cloudflare account.
Open sourceSelf-hosted
What to know▼
How it works
A fork of Mosaic/cmux adding self-hosted real-time pair programming; two developers share one live Claude Code session, with the backend deployed to their own Cloudflare account.
Best for
Development teams who want real-time pair programming with Claude Code without relying on a third-party hosted backend.
We check every product on this page once a day and record whether it still answers.
A 3D animated Mac desktop pet that sits on top of CLI coding agents like Claude Code or Codex, showing their status and confirming risky commands.
No tracking
What to know▼
How it works
A floating 3D pet on your Mac desktop that sits on top of CLI coding agents (Claude Code, Gemini, Codex, or others) — before a risky command runs, it shows the exact command in a speech cloud for you to allow or deny by voice or click.
What's different
Its 8 moods mirror the underlying agent's status live, and secrets are stored in Keychain with no telemetry.
Best for
Developers running CLI coding agents who want a visible, glanceable approval layer for risky commands.
We check every product on this page once a day and record whether it still answers.
Deploys a frontend or full-stack app to a live shareable link about 15 seconds after you type "deploy" inside Claude Code. Built for developers already coding with Claude Code, free for frontend apps with no sign-up.
FreeNo sign-up
What to know▼
How it works
Type "deploy" inside Claude Code and the app — frontend and backend — goes live at a shareable link about 15 seconds later; the agent can also trigger the deploy on its own.
What's different
Deploys from directly inside Claude Code without leaving the editor or setting up a separate hosting pipeline.
Pricing
Free for frontend apps, no sign-up required; teams get their own domain, link permissions, and company data connections.
Best for
Developers already coding with Claude Code who want a fast path to a live link.
We check every product on this page once a day and record whether it still answers.
An open-source, local-first CLI that records which lines of code were written by AI, by which model and tool, building a deterministic attribution ledger.
Works offlineOpen source
What to know▼
How it works
Records which lines of code were AI-written, which model and tool via which prompt, giving one ledger across Cursor, Claude Code, and other coding agents.
What's different
Deterministic and local-first; agents can query the CLI to surface context hidden behind existing code.
We check every product on this page once a day and record whether it still answers.
A hardware-isolated VM for running Claude Code, Codex, or Grok Build so your API keys and AWS credentials stay protected from malware, exfiltration, and prompt injection.
FreeOpen source
What to know▼
How it works
Runs agentic coding tools in an isolated VM on Apple Silicon or via OpenAI/Anthropic, reachable by app, CLI, or SSH.
Pricing
Free and open source.
Best for
Developers running AI coding agents who want their credentials isolated from supply-chain and prompt-injection attacks.
We check every product on this page once a day and record whether it still answers.
A JetBrains IDE plugin that lets you review and approve an AI coding agent's spec and plan step-by-step before it executes changes, working on top of Claude Code or Codex.
Free
What to know▼
How it works
Turns chat-coding into a plan-first workflow: spec, plan, then step-by-step execution you can accept, reject, or roll back.
We check every product on this page once a day and record whether it still answers.
Honey is a free, open-source (MIT) skill that reduces token usage for AI coding agents like Claude Code by enforcing concise code and prose conventions and cheaper bulk reads.
Free
What to know▼
How it works
enforces YAGNI/stdlib-first code, answer-first prose, compact JSON/ESON handoffs between agents, and renders bulk reads as images to cut token cost
Pricing
free, MIT license
Best for
developers running AI coding agents (Claude Code, GPT, etc.) who want lower token usage
We check every product on this page once a day and record whether it still answers.
An open-source dashboard and automation layer for Claude Code that tracks repos and sessions, enforces standing checks, and blocks repeat mistakes — built for developers already using Claude Code.
Open source
What to know▼
How it works
An open-source dashboard for Claude Code that tracks every repo, session, and routine, holds standing checks (like "tests always green") true by fixing drift automatically, runs a manager per repo, blocks repeat mistakes machine-wide, and can rescue crashed sessions. Installed with one command, npx claude-basecamp.
What's different
Fully local with zero dependencies and released to the public domain, and only escalates real decisions rather than every drift.
Pricing
Open-source and public domain.
Best for
Developers running multiple Claude Code sessions and repos who want automated drift-fixing and cross-repo oversight.
We check every product on this page once a day and record whether it still answers.
A terminal tool to browse, search, resume and convert AI coding sessions across Claude Code, Codex, Gemini CLI and OpenCode -- local-first, open source, with no telemetry.
Works offlineOpen sourceNo tracking
What to know▼
How it works
A terminal picker to browse, search, resume and branch AI coding sessions across Claude Code, Codex, Gemini CLI and OpenCode, including converting a conversation from one agent's session format to another's.
What's different
Runs 100% locally as a single static Go binary with no telemetry.
Pricing
Free and open source (MIT license).
Best for
Developers juggling multiple AI coding tools who want one place to manage sessions.
We check every product on this page once a day and record whether it still answers.
A keyboard-first issue tracker built for dev teams working alongside AI coding agents, linking to GitHub/GitLab/Gitea and exposing 40+ MCP tools so agents can file and resolve issues.
Free
What to know▼
How it works
A keyboard-first issue tracker with board, list, calendar, and roadmap views that links directly to GitHub, GitLab, and Gitea, catches duplicate reports automatically, and exposes 40+ MCP tools so agents in Cursor or Claude Code can search, file, and resolve issues.
Pricing
Free forever for solo devs; simple seat pricing for teams.
Best for
Dev teams that work alongside AI coding agents and want issue tracking reachable from their agent tools.
We check every product on this page once a day and record whether it still answers.
A tool that lets you snip a screenshot and add one note, saving both as a file bundle an AI assistant can read directly, instead of retyping context for the AI each time.
FreeNo sign-upWorks offline
What to know▼
How it works
Snips a screen region, saves a note baked into the PNG metadata plus a Markdown sidecar and a rolling index file, and works fully offline with no account or telemetry.
Pricing
Free core; one-time $9.99 for Pro, no subscription.
We check every product on this page once a day and record whether it still answers.
A minimal project board where you assign tasks and bugs to AI coding agents like Claude Code and Codex, which then work them automatically instead of a human developer.
What to know▼
How it works
lets you assign board tasks/bugs to AI coding agents, which pick them up and complete the work
We check every product on this page once a day and record whether it still answers.
An SEO system of record that finds technical SEO issues and generates content briefs for teams whose AI coding agents ship fast but no one is tracking whether the site turns into AI slop.
What to know▼
How it works
Connects to site and search data, monitors technical issues, syncs approved changes between cloud dashboard and local coding agent workflow
We check every product on this page once a day and record whether it still answers.
A statusline add-on for Claude Code that shows a sponsored ad while you wait and splits the revenue with you via Stripe; ad targeting runs locally on your device.
Watch out · Targeting claims to run locally, but the product still shares a category tag externally for ad matching.
What to know▼
How it works
Adds a single sponsored line to the Claude Code statusline during idle wait time; ad targeting is computed locally on-device and only a broad category tag is shared externally.
What's different
Splits ad revenue with the user — 50% payout via Stripe, starting at $10 — instead of just showing ads.
Pricing
Users earn 50% of ad revenue, with Stripe payouts starting at $10.
Best for
Claude Code users who don't mind a sponsored line in their statusline in exchange for a revenue share.
Watch out
Targeting claims to run locally, but the product still shares a category tag externally for ad matching.
We check every product on this page once a day and record whether it still answers.
Lets you approve requests and inspect context for Mac-based AI coding agents (Codex, Claude Code, Cursor, Gemini CLI) remotely from your iPhone, over your own network or tunnel.
What to know▼
How it works
Connects to supported agent sessions over LAN, Tailscale, VPN, or a self-managed tunnel, with no hosted relay run by the product itself.
Best for
Developers who want to monitor and approve agent actions away from their Mac.
We check every product on this page once a day and record whether it still answers.
The control plane for autonomous software labor
What to know▼
How it works
Lets humans define high-level objectives while autonomous coding agents like Claude Code, Cursor, and Codex decompose, execute, and check in the work; every decision is signed and every change is audited.
What's different
Described as 'post-kanban' planning built for agent-driven work rather than human task boards.
Best for
Teams directing multiple autonomous coding agents who need an audit trail of what agents decided and changed.
We check every product on this page once a day and record whether it still answers.
A context-management runtime for AI coding agents that speeds up and cuts token costs for tools like Claude Code, Codex, and Cursor.
What to know▼
How it works
A context runtime and cost-optimization layer for AI coding agents that manages the full context window end-to-end, instead of passive indexing or simple output compression.
What's different
25% faster and 30-67% cheaper on some workloads, with 0.727 MRR code search vs the best rival's 0.557, audited on SWE-bench.
Best for
Users of Claude Code, Codex, Cursor, and other MCP-compatible agents.
We check every product on this page once a day and record whether it still answers.
An MCP server for developers that lets coding agents deploy an HTML preview to a shareable URL and pull reviewer comments back as markdown.
What to know▼
How it works
coding agents like Claude Code, Cursor, or Codex deploy HTML to a secure share URL, collect human comments, and pull them back as LLM-ready markdown for a redeploy loop
Best for
developers using coding agents who need human feedback on generated HTML without leaving the agent
We check every product on this page once a day and record whether it still answers.
A macOS menu-bar app that alerts you when AI coding agents like Claude Code, Gemini CLI, or Codex need your input, and jumps you back to the right terminal tab.
What to know▼
How it works
Watches for when AI coding agents need input and jumps you back to the relevant terminal tab.
We check every product on this page once a day and record whether it still answers.
A local CLI that analyzes your Claude Code or OpenCode session logs to find where a coding agent's output starts degrading, with no network calls.
What to know▼
How it works
A local CLI that analyzes Claude Code and OpenCode session logs to find where a coding agent's output starts degrading, compare models, and estimate the cost of degraded steps.
What's different
Runs with zero network access, and v0.4.0 adds reversal-count analysis to test whether degradation depends on what's in context rather than just how full it is.
Pricing
Run via `uvx contextrot`.
Best for
Developers using Claude Code or OpenCode who want to know when to reset context instead of pushing through.
Tools that plug into Claude Code — the short answers
Every number here comes from our own daily check — not from a vendor list.
Tools that plug into Claude Code — how many are there?
Tablif is tracking 22 of them. 22 answered our check today.
Which ones are still maintained?
Tablif knocks on every door once a day and records the answer. 22 of these 22 responded on the latest run, so that number is what "still here" means on this page — not a review score.
Are any of them free?
7 of the live ones say so in their own words, and 2 let you start without making an account. Tablif records the claim the product makes; we don't verify pricing.
Any open-source options?
6 of the live ones on Tablif mention being open source.
What's the newest one?
SEOagent — Tablif first saw it 8 days ago.
Did a person actually look at these?
22 of them Tablif opened and read, then wrote a one-line summary in our own words instead of reusing the founder's tagline. The rest carry keyword labels we haven't confirmed by reading yet — and we say so rather than hiding it.
