AI Developer Tools

Signup

Go to: All AI Tools AI Tools by Tool Type AI Tools by Job Type

AI Developer Tools

Dive into the newest AI developer tools designed to simplify and accelerate your coding workflow. Automate debugging, enhance software deployment, and stay ahead in development using these cutting-edge resources.

Signup & Stay Updated on the latest AI Tools

AI Developer Tools

### AI Tools available

Radar

Radar is an open-source, local-first Kubernetes UI that consolidates cluster workflows: ownership-aware topology, live watches, Helm + GitOps, traffic flows, cost insights and audits-no signup required.

Mistral Medium 3.5

Mistral Medium 3.5 is a 128B merged model for instruction-following, reasoning and coding, with a 256k context window, configurable per-call reasoning, 77.6% on SWE-Bench Verified, and self-hosted on four GPUs.

Tabstack

Tabstack: web data + automation API with intelligence in every call. Returns cleaned, structured JSON/Markdown/research or runs browser automation so your product receives ready-to-use data-no scrapers, no pipelines.

Crin AI

Crin AI visualizes LLM internals with an animated node graph: see text → tokens → numbers → meaning as live data flows. Learn how models process language step by step, without diagrams or hand‑waving.

Tinfoil

Tinfoil: private AI chat (browser & iOS) and inference API that runs open-source models inside hardware secure enclaves. End-to-end encrypted data with verifiable remote attestation so your prompts stay private.

SimCam

SimCam lets you use your Mac camera or inject images/videos as the iOS Simulator camera, control front and back feeds, generate and inject QR codes, and automate sources via CLI-test camera features without app changes or extra dependencies.

MaxHermes by Minimax

MaxHermes by Minimax: a cloud sandbox AI agent that autonomously extracts reusable skills from completed tasks, persists and refines them across sessions for steadily improving automation-no setup or servers required.

Actian VectorAI DB

Portable vector DB for edge, on‑prem, and cloud with a single API. Low-latency, high-throughput from Raspberry Pi to Jetson; runs in Docker, Python/JS SDKs, LangChain/LlamaIndex support, SOC2/HIPAA/GDPR-ready.

Plurai

Plurai trains production-grade evals and guardrails from a task description, no labeled data. It generates training data, validates via multi-agent debate, and deploys a small LLM in minutes, cutting failures and cost to run on every interaction.

WUPHF by Nex.ai

WUPHF by Nex.ai: a self-hosted, open-source Slack-style hub for AI agents, to coordinate multiple models, run playbooks, and auto-build a git-backed team wiki so agents onboard themselves.

Euphony

Euphony is an open-source tool that renders Harmony JSON/JSONL and Codex logs into interactive timelines. Load files or paste, filter with JMESPath, inspect metadata, edit in-browser, embed as a Web Component; client-side by default.

Jitera

Jitera turns AI into a teammate via a Context Graph that links code, docs, decisions and tribal knowledge so agents share context, keep teams aligned, and preserve organizational learning.

QuickCompare by Trismik

QuickCompare by Trismik tests your dataset across 50+ LLMs, giving side-by-side scores for quality, cost and latency, with no scripts required-so teams can pick the best model for their prompts.

Codex 3.0 by OpenAI

Codex 3.0 by OpenAI: with GPT-5.5 it autonomously builds, tests, debugs and iterates apps-using vision, browser interaction, console and network logs to fix flows and manage files across apps.

Monid

Monid is a wallet for AI agents to purchase paid APIs from one balance. 215+ endpoints, no subscriptions, centralized billing and spend tracking so agents access premium social, blockchain, and ecommerce data.

CodeHealth MCP Server by CodeScene

CodeHealth MCP Server by CodeScene injects code-health metrics into CI and AI workflows, reducing AI-driven defects and token waste so teams can scale AI safely and keep technical debt under control.

The Autonomous Stack

The Autonomous Stack is a reference architecture for running Claude agents: canonical prompts, launchd schedules, approval inbox, scoreboard templates, alignment-scan, deployment guide and cost-control patterns for safer, auditable automation.

Logic

Logic converts a structured spec into a fully managed AI agent with built-in evals, observability, model routing and logging-so you can deploy callable agents without wiring prompts, retries or custom infra.

Agent Context

Agent Context attaches external folders as first-class reference context in your workspace so AI tools can access code without copying files or polluting your repo.

Free LLM API

Free LLM API aggregates free tiers from major LLM providers into one open-source API. Plug in your keys and get routing, rate limiting, and automatic fallback for prototyping without billing or credit cards.

kimiflare

kimiflare: open-source Claude/Kimi code clone running Kimi K2.6 on Cloudflare Workers AI. Self-hosted, low-latency code assistant for private, fast code generation; MVP was built recursively using kimiflare itself.

IgnitionRAG

IgnitionRAG: a production-ready RAG backend for enterprise document AI-upload docs, tune retrieval (11 features, A/B test), deploy widget agents, API/SDK and no-code dashboard. BYOK, GDPR-ready, self-hostable.

ml-intern

ml-intern automates the ML research loop: finds papers, pulls datasets, runs GPU experiments on Hugging Face, iterates models, and produces research-backed models via CLI and web app.

Design.MD

Design.MD is a compact DESIGN.md file that encodes a brand's visual language-colors, typography, layout, components, motion and voice-for AI coding agents. Drop it in your repo so agents generate UI that matches your brand identity.

Loomal

Loomal gives AI agents a real identity: DKIM-signed inboxes, per-agent AES-256 encrypted vault, scoped TOTP 2FA and audit logs - one MCP API so agents can act and remain auditable.

Fabi

Fabi automates and owns end-to-end developer workflows. It accesses systems, uses a browser, writes code, connects APIs, runs tasks and monitors processes, replacing manual glue work.

Pioneer

Pioneer converts a plain-English task prompt into a fine-tuned model in under 10 minutes-auto-generating training data, selecting hyperparameters, training on cloud GPUs, evaluating vs frontier models, deploying and continuously retraining.

Chat Skills for AI Agents

Chat Skills for AI Agents supplies framework-specific skill files so your coding agent (Claude, Copilot, Cursor, VS Code) auto-configures CometChat UIs-SSR, env vars and login/init sequencing managed; ready in under 15 minutes.

YourMemory

YourMemory filters agent context with biological decay, letting noise fade while reinforcing frequently used facts. Local-first DuckDB storage and a graph engine surface architectural neighbors for higher recall and fewer stale hallucinations.

QA Crow

QA Crow: write plain-English test plans, get them QA-reviewed for free, then an AI-driven browser runs tests on your live app and returns structured bugs, screenshots and repro steps. Pay-as-you-go-no seats, no minimums; $10 free credit.

PangeAI

PangeAI lets AI agents automate geospatial work - coordinate reprojection, format conversion and spatial queries - so teams skip tedious GIS chores and get accurate maps and transformed datasets faster.

Fixa.dev

Fixa.dev is an autonomous cloud developer that browses docs, installs languages/deps, builds production-ready backends, wires databases, and deploys full-stack apps with one-click integrations (Stripe, Supabase, Clerk, OpenAI, Vercel).

Katzilla

Katzilla is a single API for 250,195+ US government datasets, scrapes, watches and NL queries, returning structured citations (source URL, retrieval timestamp, SHA-256) so agents stop hallucinating and cite primary sources.

Is Your Site Agent-Ready? by Cloudflare

Scan and score your site for AI agent compatibility. Audits MCP, Agent Skills, robots.txt, sitemaps, Markdown negotiation, APIs/OAuth and bot rules, then gives actionable fixes for developers, founders and site owners.

Claude Code Rendering

Claude Code Rendering virtualizes the terminal viewport for Claude Code CLI, eliminating flicker and adding mouse support (click-to-position, expand results, URL/file clicks), smooth scrolling and transcript search - no external TUI or new depende...

Android CLI

Android CLI brings agentic Android development to the terminal: manage SDKs, scaffold projects, run emulators and deploy via CLI. Cuts token use and speeds tasks ~3x, grounded with official Android skills and auto-updating best-practice guidance.

Hacktron

Hacktron detects hidden security vulnerabilities with validated findings and concrete, actionable fixes, reducing false positives and delivering clear, evidence-backed remediation and reasoning for confident, efficient patching.

Navox Agents

Navox Agents runs eight specialist Claude Code agents as an engineering team-each owns a task, passes structured briefs, and requires approvals. It preserves decisions, enforces tests, recommends stacks (defaults to Vercel) and speeds deployments.

Claude Opus 4.7

Claude Opus 4.7 automates complex long workflows with self-verification, consistent multi-step reasoning, high-res vision, session memory and coding/agent tools like /ultrareview-letting teams delegate harder engineering and knowledge tasks.

Dune

Dune is a context-aware Mac keypad: three keys that auto-update to show the most relevant actions for the active app. Comes with built-in workflows and supports custom scripts and agents for fast, app-specific control.

BAND

BAND provides interaction infrastructure for multi-agent AI systems-routing, shared context, security, and observability so agents across frameworks can discover, coordinate, and scale reliably.

Google Gemini 3.1 Flash TTS

Google Gemini 3.1 Flash TTS: preview via Gemini API, AI Studio, and Vertex AI. Use natural-language inline audio tags to control tone, pacing and accents mid-sentence, cast multiple speakers, and export configs for consistent API reuse.

Agent Card

Agent Card issues single-use virtual Visa cards so AI agents can pay securely. Fund via Stripe, create a one-time card via CLI/API, which auto-cancels after a single payment.

ClawTab

ClawTab manages AI agent tmux sessions: auto-yes runs unattended batches overnight, and decision cards deliver prompts to your phone for quick approvals. Pane-splitting and multi-model support simplify running and responding without a laptop.

SureThing.io

Turn any GitHub repo into a one-click, production-ready AI employee with memory, a live dashboard and your business context-so founders and teams deploy open-source AI fast, no setup.

Chinilla

Chinilla is a visual flight-sim for distributed systems: drag-and-drop components, define behaviors, run simulations to watch packets flow, spot bottlenecks and queue pressure, then iterate. Paste text or code and AI maps your architecture.

Reka Edge

Reka Edge is a 7B vision-language model for Physical AI. Its ConvNeXt V2 encoder uses 3× fewer image tokens for sub-second video analysis, low-latency object detection and agentic tool use on edge devices.

Subspace

Subspace is an Agent Workspace that bundles agents, terminals, docs, and a browser per project. Persistent memory lets agents recall past work across sessions so you can resume tasks without repeating context.

Astropad Workbench

Astropad Workbench - Apple-native remote access for Mac AI agents. Monitor, nudge, or restart stuck tasks from iPhone/iPad, dictate commands by voice, and stream with LIQUID. Free 20 min/day; upgrade to unlimited.

Astra

Astra intercepts prompts to mask sensitive values so agents see token placeholders; real data resolves only at execution, reducing exposure and enabling safe agent workflows on regulated data.

Claude Code Desktop App Redesigned

Claude Code Desktop App Redesigned streamlines parallel agent coding: session sidebar, side chat, integrated terminal/editor, drag-and-drop layouts, and view modes for managing multiple repos and PRs. Requires Pro/Max/Team/Enterprise.

DataGrout

DataGrout is a unified access layer that provides AI agents a single endpoint to connect enterprise apps, cutting integration time from weeks to minutes and enabling fast, developer-friendly agent workflows.

Geekflare Scraping API v2

Geekflare Scraping API v2 extracts AI-ready content (markdown-llm, text-llm, html-llm), stripping navbars, footers, ads and scripts to return only relevant context-cutting token usage by up to 85% and reducing LLM costs.

Crazzy

Crazzy converts your GitHub username into an interactive 3D portfolio website in about 30 seconds. It syncs with GitHub in real time so commits and new repos appear instantly. Free to start.

Clide

Clide: native macOS terminal with an AI pair-developer in a side panel. Reads shell panes, types commands (exec after you confirm), previews/edits files, accepts screenshots/files, and enforces zero telemetry.

CC-BEEPER

CC-BEEPER: a floating retro pager for Claude Code that surfaces agent status, permission prompts and results, with voice dictation, spoken recaps, hotkeys and auto-accept modes. Runs locally in Swift-no accounts, telemetry, or API keys.

Caveman

Caveman: a Claude prompt that removes verbosity for coding tasks-≈75% fewer tokens, ≈3x faster responses, plus terse commits and one-line PR comments. Free, MIT, one-line install.

ElevenAgents Guardrails 2.0

ElevenAgents Guardrails 2.0 provides a real-time safety layer for voice agents: system-prompt hardening, user-input and agent-response validation, and natural-language policies that block unsafe or noncompliant replies before delivery.

Figma for Agents

Figma for Agents lets AI agents edit real Figma files using your components, variables and auto layout, guided by Skills markdown so outputs match your design system and sync design tokens with code.

Open Agents

Open Agents is an open-source reference platform to build and deploy cloud coding agents with agent brains, durable workflows, secure sandboxes and a multi-model AI gateway-optimized for large monorepos, integrations and institutional knowledge.

SuperHQ

SuperHQ runs coding agents in isolated Debian microVMs, mounting projects with tmpfs overlays so your host is untouched. View unified diffs to accept or discard changes; API keys never enter VMs-they're swapped in by a local auth gateway.

ContextPool

ContextPool is a local persistent memory layer for AI coding agents: it extracts actionable engineering insights from past sessions and auto-loads relevant context while keeping raw transcripts local.

Assemble

Assemble: a config-first AI work system that routes tasks by difficulty, keeps cross-session memory, and converts complex jobs into spec-driven workflows with review and test boards-zero dependencies, multi-platform.

Claude Code ultraplan

Claude Code ultraplan moves planning from CLI to your browser: run /ultraplan, generate cloud-hosted implementation plans, then review, comment, react per section, and iterate in claude.ai while your terminal remains free.

FlutterAIDev

FlutterAIDev turns ideas into working Flutter apps: generate code, preview UI, iterate quickly, and export source. Simplify app development to save time, cut costs, and lower technical barriers.

RevoClaw

RevoClaw: a production-ready AI agent platform that isolates agents, provides governance, long-term memory, scalable worker templates, secure server access, reliable scheduling and audit trails, built for predictable, maintainable automation.

Buildermark

Buildermark matches agent diffs to commits to calculate what percent of your code was written by AI, and archives all agent conversations (Claude, Codex, Gemini, Cursor) for audit-ready records.

Ovren

Ovren automates backlog execution: assign scoped frontend or backend tasks and get reviewable code updates from AI engineers working in your repo-fast fixes, refactors, integrations, tests and cleanup so teams ship more work.

Architecto

Architecto turns natural-language specs into reviewable cloud architectures-auto-diagrams, cost/security/compliance checks, docs, and governance in one platform.

Elytro Agent Wallet

Elytro Agent Wallet: a self-custodial Ethereum smart-account wallet that gives AI agents secure, rule-driven access to funds-enabling agents to send/swap tokens, pay services, and trade without exposing private keys.

WinScript

WinScript: a Windows-native automation API served as an MCP server, enabling AI agents to run scripts, modify system settings, and execute real desktop workflows with direct system-level access.

Rosentic

Rosentic checks every PR against all active branches to detect cross-branch conflicts before merge. Deterministic scans, one YAML install, no signup - catch compatibility issues before they hit main.

Codentis

Codentis is a CLI AI assistant that brings agentic workflows, streaming output, memory, and actionable terminal commands-helping developers execute tasks, debug faster, and stay focused without constant context switches.

Labelsets

Labelsets: a marketplace for labeled datasets with an automated Label Quality Score (7 checks). Objectively compare vendors, preview free 1,000-row samples by email, and pick higher-quality data for model training.

Plow

Plow: sandboxed OpenClaw for macOS-install in seconds. Easy, isolated setup with direct access to the Plow engineering team. Seeking 100 alpha co-developers to help get OpenClaw running on your Mac.

Cyris

Cyris logs every LLM call with two lines of code to a tamper-proof, hash-chained audit trail-auto-fills security evidence, offers a shareable live trust center URL, and reconstructs decision chains across agents for audit-ready AI.

Grass

Grass keeps coding-agent conversations in sync between phone and laptop, provides a free pre-configured VM with 10 free compute hours, and uses BYOK so your API keys never leave your device.

Marmot

Marmot is a lightweight, open-source data catalog (single binary + Postgres) that indexes 25+ sources, provides full lineage and an MCP server so LLMs query a single source of truth - deployable in minutes.

AI Designer MCP

AI Designer MCP gives agents the tools to create codebase-aware, polished frontend UI inside your existing client-replacing generic gradients and icons with clean, product-fit layouts that integrate with your codebase.

OpenBrowser-AI

OpenBrowser-AI gives LLMs direct Chrome control via raw CDP, running Python in a persistent namespace to batch actions and compress page state-using ~2.6x fewer tokens for faster, efficient browser automation.

TestRelic AI

TestRelic AI converts live Playwright data into dashboards, reports, slides and test plans from plain-English queries-no setup. Reduce time finding failures and let QA focus on fixing issues with clear user-impact insights.

/dev for Claude Code

/def for Claude Code turns Claude into a Tech Lead: PRD alignment, architecture and task decomposition, isolated worker worktrees, QA checks, security audits, and structured code review. Open-source (MIT).

OpenRouter Model Fusion

OpenRouter Model Fusion runs prompts through multiple SOTA models, pre-evaluates their outputs, then a chosen fuse model synthesizes a single, controllable final answer. Mix open or closed models; free options let you test.

Open Claude in Chrome

Open Claude in Chrome: open-source (MIT) clean-room clone of the Claude extension. Adds browser automation with 18 tools: click/type/screenshots/JS/eval/accessibility/console+network. Chrome & other Chromium browsers; no domain blocklist.

Mesh LLM

Mesh LLM runs LLM inference across volunteer devices, accelerating throughput and reducing server costs so teams can run large-scale AI inference using crowd-sourced compute.

Google Gemma 4

Google Gemma 4 - an open (Apache 2.0) model family for advanced reasoning, multimodal inputs, 256K-context and agentic workflows. Offers frontier-level intelligence-per-parameter that runs efficiently on phones, laptops and local servers.

Trinity-Large-Thinking by Arcee

Trinity-Large-Thinking by Arcee: an open-source SOTA model for developers who want models they can inspect, post-train, host, distill and own. Ranked #2 on PinchBench (KiloClaw); $0.90 per 1M output tokens (~96% cheaper).

Claude Code Voice Mode

Claude Code Voice Mode is a two-way spoken interface for web and mobile, offering hands-free continuous listening with optional push-to-talk, natural voice replies, seamless text-voice switching, and auto-saved transcripts to capture ideas faster.

tama96

tama96 is a programmable Tamagotchi-style virtual pet for desktop, terminal, or AI agents. Your care choices shape its behavior. Includes pixel desktop app, single-binary terminal client, and MCP server with per-action permissions.

Skills Janitor

Skills Janitor cleans your skills folder: finds unused, duplicate or broken skills, previews proposed removals, and safely prunes them. Single-file bash+python3 (no deps), MIT-licensed, free, no telemetry-reclaim context space and tidy your setup.

Baton

Baton centralizes Claude Code agents into a single dashboard, letting you view, review and manage agents and their code changes, and launch new instances across IDEs and terminals without switching windows.

OpenBox

OpenBox: a trust platform for agentic AI that enforces identity, authorization, policy and risk at runtime. Provides cryptographic audit trails, an OPA-based policy engine and a single SDK with no stack changes.

OpenGyver

OpenGyver is a free, open-source CLI and Claude Code skill that converts formats and units-currency, color codes, timestamps, images, JSON, UUIDs-extensible via modules for custom conversion commands.

OpenClawCloud

OpenClawCloud: zero-setup cloud VM with a ready OpenClaw agent, preinstalled skills and unlimited GLM-4.7/GLM-5 tokens. Start free (7 days + unlimited GLM-4.7); no API keys, configs, or per-token billing.

folio

Folio is a free macOS app that loads thousands of unstructured files into a table for scalable, SQL-filtered bulk LLM analysis. Batch transforms, estimate and manage costs, and verify results locally with agent support via modal.

Arlopass

Arlopass is a browser extension that lets web apps use your AI providers without exposing API keys-approve requests, pick models, and route calls locally. No server proxies; keys remain in your OS keychain.

Notion MCP

Notion MCP connects AI agents like Claude, ChatGPT and Cursor to your Notion workspace in real time, giving AI read/write access to notes, docs and workflows for context-aware results, multi-agent support, admin controls and easy setup.

Ollang DX

Ollang DX: one API/SDK to localize any file-video, audio, DOCX, PDF, SRT, JSON-into 240+ languages with dubbing, subtitles and i18n. MCP/Skills integrations let agents localize files directly within their workflows.

Google Ads MCP Server

Google Ads MCP Server applies opinionated practitioner defaults and policy-safe guardrails to the Google Ads API, automating campaign setup. Paste a URL, connect your account, and prompt-no terminal or JSON.

.

As seen on