Your digital partner.

Desktop workspace that runs Claude Code, Codex, Kimi and GLM side by side on the plans you already pay for, with up to 32 live panes, a local code index and context compression to cut token spend. The app is open source (Apache 2.0) on macOS, Windows and Linux; optional Halv Cloud routing is $10/month.

Claude Code mod that reads your plan's 5-hour and weekly usage and holds subagent fan-out, heavy-context prompts and retry loops before they spend your window, asking in Claude Code's own dialog. Local only, no network; MIT licensed.

Open-source, self-hostable alternative to Railway, Render and Heroku on Kubernetes: deploy from GitHub or an image, wire services on a visual canvas, managed Postgres with backups and PITR, per-branch preview environments and whole-stack rollbacks. Drive it from a coding agent skill, the canvas or a CLI; MIT licensed.

Open-source macOS app (Apple Silicon) that reads your local Claude Code, Codex and Cursor history to show agent activity, estimated human time, API-equivalent spend and how fast you are using your Claude and Codex limits. Apache-2.0.

One permanent webhook URL that routes Stripe, Paddle and other provider events to whichever branch deployment is active, switched from a dashboard, CLI or GitHub Action. Runs on Cloudflare's edge; free tier covers 1,000 webhooks a month.

Native macOS terminal built on libghostty that your coding agents can control and extend: ask an agent to build custom panels, commands and layouts in HTML, CSS and JavaScript, and see which agent is working in each pane. Requires macOS 27 on Apple silicon.

Open-source managed agent platform, pitched as a self-hostable alternative to Claude Managed Agents and OpenAI's Agents API: run AI agents on any model and any machine through an API and CLI, with tools, secrets, permissions and streaming built in. Self-host free under Apache-2.0 or use Omnara Cloud.

Runs Claude Code or OpenAI Codex CLI unattended on a brief, fenced to the folders you give it and under a per-run dollar budget enforced by a loopback API proxy, leaving one ledger line per run. Single Python file, standard library only, macOS only, Apache-2.0.

Cursor

AI Editors & Agents

AI coding agent and VS Code-based editor with codebase-aware chat, autocomplete and agent mode.

Devin Desktop (formerly Windsurf)

AI Editors & Agents

AI-native IDE from Cognition, renamed from Windsurf (originally Codeium), with the Cascade agent for multi-file edits.

GitHub Copilot

AI Editors & Agents

GitHub's AI pair programmer with completions, chat and coding agent across popular editors.

Claude Code

AI Editors & Agents

Anthropic's agentic coding tool that runs in the terminal and works across your codebase.

v0

AI Editors & Agents

Vercel's generative UI and app builder producing React/Next.js code from prompts.

Bolt.new

AI Editors & Agents

StackBlitz's in-browser AI full-stack app builder powered by WebContainers.

Lovable

AI Editors & Agents

AI app builder that generates full-stack web apps from natural language.

Replit

AI Editors & Agents

Browser-based IDE and hosting with Replit Agent for building apps from prompts.

Vercel

Hosting & Deployment

Frontend cloud for deploying Next.js and other frameworks with preview deployments and edge network.

Netlify

Hosting & Deployment

Platform for deploying web projects with Git-based builds, functions and forms.

Cloudflare Pages

Hosting & Deployment

Deploy static and full-stack sites on Cloudflare's global network, integrated with Workers.

Render

Hosting & Deployment

Cloud platform for web services, static sites, cron jobs, workers and managed Postgres.

Railway

Hosting & Deployment

Infrastructure platform to deploy apps and databases from a repo with minimal config.

Fly.io

Hosting & Deployment

Run full-stack apps and databases close to users on Fly Machines (lightweight VMs).

Supabase

Databases & Backend

Open-source Postgres development platform with auth, storage, realtime and edge functions.

Firebase

Databases & Backend

Google's app development platform with Firestore, auth, hosting and cloud functions.

Neon

Databases & Backend

Serverless Postgres with branching and autoscaling.

PlanetScale

Databases & Backend

Managed MySQL (Vitess) and Postgres database platform built for scale.

Convex

Databases & Backend

Reactive backend with a TypeScript-native database, functions and realtime sync.

Clerk

Authentication

Drop-in authentication and user management with prebuilt UI components.

Auth0

Authentication

Identity platform by Okta for authentication and authorization.

Auth.js

Authentication

Open-source authentication library (formerly NextAuth.js) for web frameworks.

Stripe

Payments

Payments infrastructure: checkout, subscriptions, invoicing and payment links.

Lemon Squeezy

Payments

Merchant of record for selling software and digital products, now part of Stripe.

Paddle

Payments

Merchant of record payments platform for SaaS businesses.

Resend

Email

Developer-focused email API with React Email support.

Postmark

Email

Transactional email delivery service focused on deliverability.

SendGrid

Email

Twilio's email API for transactional and marketing email.

PostHog

Analytics & Monitoring

Open-source product analytics suite with session replay, feature flags and experiments.

Sentry

Analytics & Monitoring

Application monitoring for error tracking, tracing and performance.

Plausible

Analytics & Monitoring

Lightweight, privacy-friendly, open-source web analytics.

Vani Code Agent

AI Editors & Agents

Free VS Code extension coding agent with diff review and command approval, backed by the Vani API.

Ellf

AI Editors & Agents

Explosion's tool that plugs into Claude Code, Codex or Copilot to plan, annotate, train and evaluate custom NLP systems.

Coderblock

AI Editors & Agents

Vibe-coding platform that builds full-stack web apps from chat with a team of specialist AI agents in a 3D office.

Farol

AI Editors & Agents

Free open-source macOS terminal for running Claude Code and Codex in parallel with status sidebar and git worktrees.

Kerno

Analytics & Monitoring

AI runtime QA for backends: tests user flows against your real stack from inside MCP-capable coding agents.

Reason

AI Editors & Agents

Autonomous software engineer for GitHub that opens evidence-backed pull requests; use it from the web, Mac app, terminal or Slack.

OpenCode

AI Editors & Agents

Open-source AI coding agent for terminal, desktop and web, with multi-session agents and 75+ model providers.

Tiden

Analytics & Monitoring

Intent verification for coding agents: keeps versioned specs beside your code and checks agent changes against what you asked for.

withHuman

AI Editors & Agents

Open-source human approval layer that intercepts AI agent tool calls, applies rules, and routes risky actions to reviewers.

Navige

Analytics & Monitoring

Sits between AI agents and the models they pay for to cut spend via caching, smart routing, context trimming and loop guards.

Deploys open-source apps (WordPress, Gitea, Grafana, Dify and dozens more) on a dedicated server with TLS and nightly backups, billed hourly with a monthly cap.

Readyset's open-source desktop agent that watches PostgreSQL or MySQL read-only, flags slow or regressed queries and proposes index, setting or rewrite fixes.

Proa

Frameworks & Dev Tools

Batteries-included Rust web framework with fast server rendering and multi-target rendering (HTML, Markdown and more) from one typed component.

Sygal

Frameworks & Dev Tools

Local-first Mac and Windows app plus CLI that converts PDFs, Office files, scans and web pages into clean Markdown or JSON for AI prompts and pipelines.

Open-source, read-only status board for TV or phone showing what your AI coding agent lanes and machines are doing and what is waiting on you.

Sphinx

Frameworks & Dev Tools

Free, MIT-licensed Git hook that quizzes you on what your coding agent's diff actually does before a push to protected branches goes through; works with Claude Code, Codex, Cursor or plain Git.

llmspeed

Frameworks & Dev Tools

Open-source simulator that lets you feel a local LLM's tokens/sec and time-to-first-token on a chosen GPU or Mac before you buy the hardware, based on community benchmarks.

Open-source (MIT) ESP32 emulator written in Rust that runs real firmware locally or in the browser, with no hardware or cloud needed.

Rust terminal system monitor for Apple Silicon Macs showing CPU, GPU, power, clocks, temperatures and processes, without sudo or telemetry.

Open-source (MIT), read-only MCP server you deploy to your own Cloudflare account so Claude Code or any MCP client can search and read your WhatsApp chats; it can't send messages and is unofficial (uses the WhatsApp Web protocol).

OmniPTY

Frameworks & Dev Tools

Open-source (MIT), GPU-rendered Rust terminal for macOS and Linux with built-in splits, pinnable workspaces, a vim-style file tree, copy mode and a git-aware status bar; no account or telemetry.

Glider

Databases & Backend

Open-source single-node vector database in Rust that makes every acknowledged write durable in S3-compatible storage, with filtered nearest-neighbor search over an HTTP API, a Python client and an MCP memory server for agents.

Open-source (MIT) libraries for TypeScript, Python and Rust that sign and verify webhooks with ed25519 asymmetric signatures and handle key management and rotation; early-stage but usable.

Open-source (MIT) multi-agent orchestrator for the Pi coding agent that runs Pi, Claude Code, Codex or OpenCode as parallel subagents in isolated copy-on-write Git worktrees inside Herdr panes.

KiviDB

Databases & Backend

Open-source (AGPL-3.0), multi-threaded Redis and Valkey alternative written in Rust that speaks RESP2/RESP3, so existing Redis clients work unchanged, with full-text and vector search built in; self-host it or use KiviDB Cloud.

Open-source (MIT) Vite plugin: click any element in your running app, type what should change, and get a prompt with the exact source file, line and column to paste into Claude Code, Cursor or Codex; local-only and dev-mode only.

Open-source (MIT) boilerplate for running Claude Code as a software factory: a sandboxed container, a deterministic bash-command regulator, lint hooks for custom rules and a multi-agent workflow generator.

Death Plan Switch

Frameworks & Dev Tools

Free, MIT-licensed, self-hosted dead man's switch for solo developers: it emails you weekly and, if you stop checking in, asks your next of kin and then notifies the contacts who need to take over; PHP 8.1+, no database.

Parseable

Analytics & Monitoring

Open-core (AGPL-3.0) observability platform written in Rust: logs, metrics and traces in one binary on S3-compatible object storage, with SQL and PromQL, OpenTelemetry-native ingest, self-hosted or as Parseable Cloud.

Bifrost

Frameworks & Dev Tools

Open-source (Apache-2.0) AI gateway from Maxim AI: one OpenAI-compatible API for thousands of models with failover, load balancing, semantic caching, virtual keys, budgets and an MCP gateway; Enterprise plan available.

Gauge CLI

Frameworks & Dev Tools

Open-source (MIT) CLI that runs real coding agents against your Skills, CLIs, SDKs, MCP servers and docs, captures where they get stuck and lets your own agent test fixes locally in Docker; part of the Gauge agent-led growth platform.

e2e by TesterArmy

Frameworks & Dev Tools

Open-source (Apache-2.0) end-to-end testing framework for web, iOS and Android: describe a goal in plain language, an agent drives the app, and assertions verify the result; recorded steps replay with no model calls. From YC-backed TesterArmy.

Chiplab

Frameworks & Dev Tools

MCP platform from Veecle that lets AI agents compile, simulate and validate firmware on the actual target chip without physical hardware; in beta.

Opper

Frameworks & Dev Tools

EU-hosted AI gateway: 700+ models behind one OpenAI-compatible API, pay-as-you-go, with spend caps, model allowlists and zero data retention; works with Claude Code, OpenCode and Cursor.

Durable Actors

Databases & Backend

Open-source (MIT) alternative to Cloudflare Durable Objects from Terse: stateful serverless actors with their own SQLite database and serialized execution, for chat, collaboration and multi-agent apps, with TypeScript and Python SDKs.

Reticle

Frameworks & Dev Tools

AI app testing that runs inside your app: it walks a flow like a user and reads network calls, app state and the console so your coding agent can verify its own work; free open-source SDK for Claude Code, Cursor and any MCP agent.

Pug

Analytics & Monitoring

Open-source (AGPL-3.0) product analytics with unified user profiles: autocapture, trends, funnels, retention and user flows; self-host it or start free on EU-hosted, cookieless Pug Cloud.

Tofu

Hosting & Deployment

Paste one message into your coding agent and your app goes live at its own link; Tofu also sets up saved data, sign-in, a custom domain and user emails in one account. Free for one app, paid plans from Starter.

Open-source (Apache-2.0) Mac app for planning a feature out loud: Luke reads your code while you talk and writes a plan you can paste into Claude Code or Codex.

Free, open-source pair programming app from the makers of CoScreen: low-latency, high-resolution window sharing with remote control, for Mac and Windows.

pocketty

Frameworks & Dev Tools

SSH terminal for iPhone and iPad made for herdr: end-to-end sealed alerts when a coding agent is blocked or done, keys in the Secure Enclave, and real keystrokes to answer it. 14-day trial, then a one-time purchase.

End-to-end encrypted shared scratchpad that lets Claude Code, Codex, Cursor, Gemini and other coding agents share notes and files, hand off work and review changes across machines; try it with npx jotbus.

k10s

Frameworks & Dev Tools

Open-source (Apache-2.0) Kubernetes terminal UI you can click: searchable, themeable, a single static binary for macOS, Linux and Windows, with an AI assistant that knows your cluster, namespace and selected object.

Mac app that gives AI agents their own desktop workspace to work in apps that have no API, while you keep using your Mac; connect Claude Code or Codex over MCP. Formerly Mecum.

DocuMemory

Frameworks & Dev Tools

Memory engine for AI-first engineers: distils Claude Code, ChatGPT and Cursor sessions into architecture decisions and prompt-injectable context blocks, recalled over MCP.

Etchv

Frameworks & Dev Tools

Invisible forensic watermarking API for images, PDFs and video, written by a neural model and detectable after resizing and cropping; SDKs for Python, Node.js, Go, Rust, C# and Java plus an MCP server.

Staffcoder

Frameworks & Dev Tools

Hands-on coding practice in a browser IDE: 1,000+ production-style challenges across 40+ learning paths, from React, Next.js and Spring Boot to DevOps and AI engineering.

Rinkata

AI Editors & Agents

Shared source of truth for teams building with coding agents: goals, specs, decisions and completion evidence that Codex, Claude, Cursor and other agents read and update; works with GitHub and your review habits.

Nace

Frameworks & Dev Tools

Execution layer for agents: a Perception API that reads any file and a Decision API that makes small calls in under 200 ms on fast, low-cost models, under one API key; Drex models with open weights.

Ask a technical question and get a personalized, narrated explainer video with diagrams, code and animations that you can interrupt with follow-up questions.

deCDN

Hosting & Deployment

Open-source peer-to-peer CDN where anyone can serve bytes, every chunk is BLAKE3-verified and clients pay per megabyte in USDC, targeting about $0.01/GB; currently on testnet.

ProvenMetal

Frameworks & Dev Tools

Quote and order assembled PCBs from Codex or Claude through the ProvenMetal MCP server, at JLCPCB's own instant price with design checks and sourcing of parts JLCPCB doesn't stock.

Costura

Analytics & Monitoring

Open-source (Apache-2.0), self-hosted AI spend attribution: imports read-only billing from OpenAI, Anthropic, Claude.ai, Codex, OpenRouter, Cursor and GitHub Copilot, attributes each dollar to a key, workspace and person, and ties totals out to each provider's report; in beta.

Pomerado

Frameworks & Dev Tools

Turns any website, from consumer sites to legacy portals, into a hosted API or MCP server for your agents, faster and more reliable than browser agents; open source and backed by Y Combinator.

NitroStack

Frameworks & Dev Tools

Full-stack MCP platform: open-source TypeScript and Python SDKs, an MCP CLI, the NitroStudio desktop app for testing and debugging, and NitroCloud managed hosting for production MCP servers and apps.

Context.dev

Frameworks & Dev Tools

Web data API for AI agents: scrape any URL into LLM-ready Markdown, search the live web, crawl and map sites, monitor pages for changes and pull brand data, with SDKs, a CLI and an MCP server; free credits to start.

Busabase

Databases & Backend

Open-source (MIT) database and workspace that acts as a system of record for AI agents: agents and people share data, docs, skills and apps, every change keeps its history, and important writes can wait for review; desktop, self-hosted or Busabase Cloud.

Zernio

Frameworks & Dev Tools

Marketing infrastructure for products and agents: one API and a hosted MCP server for social posts, ads, a unified inbox, WhatsApp, SMS and calls, built on official platform APIs; free up to two accounts.

Cekura

Analytics & Monitoring

Automated QA and observability for voice and chat AI agents: simulate conversations across personas before launch, monitor production calls for instruction-following and tool-call errors, and plug tests into CI/CD.

KloudMate

Analytics & Monitoring

AI-powered observability and SRE-Ops: logs, metrics, traces, infrastructure, Kubernetes, RUM, synthetic and database monitoring in one platform, with an AI assistant for root-cause analysis; Pro from $99/month.

Polylane

Analytics & Monitoring

AI SRE that connects your code, infrastructure and observability data, catches risky pull requests before they merge, investigates production issues and opens a pull request with the fix; free plan, paid from $80/month.

Alkera

Databases & Backend

Agentic data platform where data engineers, analysts and agents collaborate in multiplayer notebooks and chats, with column-level lineage and a knowledge base; built on the open-source Databench workspace, free tier available.

Inferock

Frameworks & Dev Tools

Accountable LLM inference: watch your own OpenAI, Anthropic or Gemini calls for failures and overbilling, run serverless inference with credits back on eligible failed calls, or rent dedicated capacity; open-source inferock-bench proxy.

RunInfra

Frameworks & Dev Tools

Open-model APIs built for agents: fast responses, warm replicas with up to 98% cache hits for repeated context, and one API key that works with the OpenAI and Anthropic SDKs. Backed by Y Combinator.

Buddy Sandboxes

Hosting & Deployment

Isolated Linux VMs for AI coding agents from Buddy: passwordless sudo, Docker, SSH, a 50 GB disk that survives restarts and public HTTPS endpoints, driven from a CLI, SDK, REST API or MCP tool call.

Gleap

Frameworks & Dev Tools

AI-native help desk for software teams: in-app bug reporting and session replay plus Kai agents that answer customers, investigate tickets and open code fixes your team reviews; plans from $29/month.

Beam

Frameworks & Dev Tools

Puts windows from one Mac onto another as native windows with real input, so agents and builds can keep running on a Mac mini or Studio while you work from your laptop; encrypted, direct over your own network, subscription or lifetime license.

walkai-talkai

AI Editors & Agents

Talk to Cursor, Claude Code or Antigravity over any handheld two-way radio: local Whisper transcription on your Mac types the command, and neural TTS reads the answer back with VOX tones; one-time lifetime license, Apple Silicon.

guilds.run

AI Editors & Agents

Open-source multi-agent teams you can inspect: debug every prompt, tool call, memory change and agent interaction, control permissions and pick the model per agent; self-host free, hosted plan from $19/month coming soon.

CoreSpeed

AI Editors & Agents

One MCP endpoint that gives Claude Code, Codex or Cursor your apps, your team's shared memory and built-in tools, with spend caps, approvals and an activity log; free plan, Pro $20/month.

Opengeni

AI Editors & Agents

Open-source cloud agent harness: every agent gets its own computer plugged into your repos and tools, runs for hours after you close the laptop, and the team shares the work; EU-hosted, any model, Pro from $20/month.

Dropstone

AI Editors & Agents

AI coding agent for the terminal and your IDE with one memory across chat, CLI and code: correct it once and it applies the lesson everywhere; runs on self-hosted models, plans from $5/month.

Invofox

Frameworks & Dev Tools

Document parsing API that turns invoices, payslips, contracts and any document into validated JSON or Markdown for RAG and LLM pipelines, with classification, splitting, confidence scores and continuous learning; SOC 2 and ISO 27001.

Siteprint

Frameworks & Dev Tools

Safari extension for Mac that measures any website's design (colours, type scale, spacing, corners and layout) and exports it as one exact prompt or DESIGN.md for Claude Code, Cursor or Codex; free to try, Pro $19.99 once.

Promptic

Analytics & Monitoring

Optimization platform for GenAI apps: OpenTelemetry-native LLM tracing, model benchmarking and one-click prompt and agent tuning scored on your own quality and cost metrics; free tier, team plans from €149/month.

Floot

AI Editors & Agents

Build full-stack apps from inside Claude, ChatGPT or Cursor: Floot handles the backend, database, logins, hosting and publishing to web, iOS and Android, with no AI credits to buy; backed by Y Combinator.

CtrlOps

Hosting & Deployment

Local-first desktop app for managing Linux servers: AI terminal that turns plain English into shell commands, one-click GitHub deploys, file manager, monitoring, security audits and SSH key management; from $7/month or $149 lifetime.

Opaline

Analytics & Monitoring

Team-wide, message-level analytics for Claude Code and Codex sessions: token cost, time and skill usage for every message across your team; open-source CLI, paid team plans.

Maximem Synap

Frameworks & Dev Tools

Memory and context layer for AI agents with entity resolution, temporal reasoning and scoping built in, sub-15ms recall and native support for 20+ frameworks including LangChain and the Claude Agent SDK; free tier, paid from $19/month.

AutonomyAI

AI Editors & Agents

Autonomous product delivery on your real codebase: research, plan the spec, build with your own components and conventions, verify in the running app and hand engineers a review-ready pull request.

Solid

AI Editors & Agents

AI agents with their own computers, accounts and budgets that build apps, automate workflows and run long jobs end to end, using your tools through APIs or a real browser; plans from $20/month.

Latitude

Analytics & Monitoring

Open-source observability and quality platform for AI agents: traces production runs, turns failures into tracked issues with evals attached and dispatches your coding agent to fix them; paid team plans.

Pulsetic

Analytics & Monitoring

Monitoring for websites, APIs and services: uptime, real user monitoring, SSL, domains, ports, cron jobs and status pages, with alerts everywhere plus an API and MCP server; free plan, paid from $9/month.

Hopscotch

Frameworks & Dev Tools

One API for 500+ models from Anthropic, OpenAI, Google and more, with spend limits per key, teammate and workspace, guardrails, fallbacks, request logs and bring-your-own-key; pay as you go at list price.

iFixAi

Frameworks & Dev Tools

Independent auditing for AI agents: finds where an agent hides information, overrides decisions or takes unauthorised actions behind a successful result, with recurring audits and reports per agent.

Coddy

Frameworks & Dev Tools

Learn to code with bite-sized interactive lessons and playgrounds for Python, JavaScript, SQL and 15+ languages, plus learning paths for software, web and game development; 5M+ learners, optional premium plan.

NOAN

Frameworks & Dev Tools

Fact infrastructure for agentic companies: one API over REST and MCP for your verified business facts, read live by every agent, app and site; free plan, paid from $99/month.

Whiteboard

AI Editors & Agents

Open-source canvas for thoughtful software design: review interactive visualizations, diffs and agent trajectories in one interface on macOS, Windows and Linux; by /dev/fast (YC W26).

Helo

Email

Email API and SMTP for transactional and broadcast email from former Postmark folks, focused on inbox placement, with analytics and simple usage-based pricing from $5/month.

Karada.ai

Frameworks & Dev Tools

Infrastructure for MCP: auto-compile APIs into Go MCP servers, keep tools in sync with CI/CD on every deploy, add composable plugins and multiplex everything behind one gateway; free Hobby plan, Pro from $19/month.

CoIsland

Frameworks & Dev Tools

Mac app that watches your engineering stack (GitHub Actions, Sentry and more), shows only what needs you and hands the work to Claude Code, Codex or Cursor; keys stay on your Mac, lifetime from $29.

ZooWork

AI Editors & Agents

AI agent delivery platform: domain experts build in the Builder UI while developers ship through the Managed Agent API, with approvals, security and control for real business operations.

Statable

Analytics & Monitoring

Privacy-friendly web analytics built for humans and AI agents: a simple dashboard, plus MCP access so Claude, Cursor or Codex can read reports and configure goals and funnels; no cookies, EU-hosted.

Activity Monitor alternative for Mac that groups processes by app, tracks coding agent sessions and AI usage limits, finds forgotten dev servers and exposes an MCP server; pay once, no subscription.

CybeDefend

Frameworks & Dev Tools

Security and business rules for AI coding agents: one command installs VibeDefend into Claude Code, Cursor, Copilot or Codex to scan each diff and block risky actions, with SAST, SCA, secrets and IaC scanning; free plan.

Open-source Agent Decision Record: a signed, append-only, hash-chained record of every decision an AI agent makes, verifiable offline; one line instruments Claude, OpenAI and LangGraph agents, with Python and TypeScript SDKs and plain files on storage you control. Apache-2.0, written in Rust.

Checks public evidence for an MCP server and returns PASS, REVIEW, BLOCK or UNKNOWN before you install or call it; lookup, preflight, whole .mcp.json config audits, a change feed, REST API and its own MCP endpoint, no account needed for stats.

Mac app and CLI that searches all your past coding-agent sessions before each prompt and hands your agent a short recollection with sources; works with Claude Code, Codex, Cursor, OpenCode, Amp and more, indexes locally, with shared team workspaces.

GitHub app whose agent analyzes, fixes and merges Dependabot PRs using static analysis plus AI, with a prioritized inbox and auto-merge policies you control; 25 free dependency PRs a month, paid plans from $10/month.

Open-source local MCP runtime that checks AI-agent tool calls against policy, gates risky actions on approval, verifies results and parks uncertain outcomes instead of blindly retrying after timeouts. Apache-2.0.

CLI to archive Claude Code, Codex and Cursor sessions to your own S3 or R2 bucket and hand a session's context off between agents or machines, plus browse history by topic, project, branch or PR. MIT-licensed, written in Go.

Open-source (MIT) desktop app for macOS and Linux to run parallel coding agents and multi-step Flows triggered by schedules, webhooks or events from Linear, Sentry, PostHog, Vercel and more, with approval steps and a Work Queue; runs locally with the AI coding tool you already use, no account.

Claude Code plugin that warns Claude at 50% context so it finishes its current piece, writes itself a handoff note and compacts at a clean break instead of mid-task. MIT-licensed.

Agentless desktop GUI for managing servers over plain SSH: files, editor, services, processes, containers, network, sessions, monitoring and a terminal in one window, with nothing installed on the server; macOS, Windows and Linux, Apache-2.0.

Open-source managed agent platform, pitched as a self-hostable alternative to Claude Managed Agents and OpenAI's Agents API: run AI agents on any model and any machine through an API and CLI, with tools, secrets, permissions and streaming built in. Self-host free under Apache-2.0 or use Omnara Cloud.

Runs Claude Code or OpenAI Codex CLI unattended on a brief, fenced to the folders you give it and under a per-run dollar budget enforced by a loopback API proxy, leaving one ledger line per run. Single Python file, standard library only, macOS only, Apache-2.0.

Native macOS agentic development environment for coordinating coding agents with controlled workflows, visual traces and cross-agent memory; drives harnesses such as Codex, Claude Code, OpenCode, pi and Antigravity. Apple Silicon, macOS 26+, MIT-licensed.

Open-source, self-hosted platform for running internal apps, including AI-built ones: point it at a git repo or image and it builds the app, scans it for vulnerabilities, runs it on an isolated network and puts it behind your SSO. Alpha, needs Docker; AGPL-3.0.

Local Azure emulator with a real identity plane and RBAC: Entra tokens, managed identity, ARM, Key Vault and Blob Storage behind one RBAC engine that returns 403 where Azure would, driven unmodified by az, the Azure SDKs and Terraform. Apache-2.0.

Minimalist, classless-first CSS framework: one file (6.7 KB min+gzip), no build step or JavaScript, automatic light/dark mode, theming via CSS custom properties and zero-specificity element styles that are easy to override. MIT-licensed.

Desktop workspace that runs Claude Code, Codex, Kimi and GLM side by side on the plans you already pay for, with up to 32 live panes, a local code index and context compression to cut token spend. The app is open source (Apache 2.0) on macOS, Windows and Linux; optional Halv Cloud routing is $10/month.

Claude Code mod that reads your plan's 5-hour and weekly usage and holds subagent fan-out, heavy-context prompts and retry loops before they spend your window, asking in Claude Code's own dialog. Local only, no network; MIT licensed.

Open-source, self-hostable alternative to Railway, Render and Heroku on Kubernetes: deploy from GitHub or an image, wire services on a visual canvas, managed Postgres with backups and PITR, per-branch preview environments and whole-stack rollbacks. Drive it from a coding agent skill, the canvas or a CLI; MIT licensed.

Open-source macOS app (Apple Silicon) that reads your local Claude Code, Codex and Cursor history to show agent activity, estimated human time, API-equivalent spend and how fast you are using your Claude and Codex limits. Apache-2.0.

One permanent webhook URL that routes Stripe, Paddle and other provider events to whichever branch deployment is active, switched from a dashboard, CLI or GitHub Action. Runs on Cloudflare's edge; free tier covers 1,000 webhooks a month.

Native macOS terminal built on libghostty that your coding agents can control and extend: ask an agent to build custom panels, commands and layouts in HTML, CSS and JavaScript, and see which agent is working in each pane. Requires macOS 27 on Apple silicon.