1,037 tools and products — trending open source, and what gets used in AI and other work.
ChatDev is an open-source multi-agent framework from OpenBMB. Its original ChatDev 1.0 design models a virtual software company in which role-based agents such as a CEO, CTO, and programmer collaborate through specialized functional seminars to carry out software development tasks including design, coding, testing, and documentation. The current ChatDev 2.0, called DevAll, is a zero-code multi-agent orchestration platform. Users configure agents, workflows, and tasks to build and run customized multi-agent systems for scenarios such as software development, data visualization, 3D generation, and deep research.
Semantic Kernel is an open-source SDK developed by Microsoft for building AI applications that combine large language models with conventional code, memory, and external connectors. It provides orchestration primitives, memory abstractions, tooling for prompts and skills, and SDKs for .NET and Python.
Flowise is a visual, low-code platform for building AI agents and agentic workflows by connecting models, components, and third-party integration nodes through a graphical interface. Its monorepo contains a Node.js backend for API logic, a React frontend, component integrations, and autogenerated Swagger API documentation. It can be installed with npm, run with Docker, deployed self-hosted, or used through Flowise Cloud. The repository is archived and its source code is released under the Apache License 2.0.
An AI-assisted design tool aimed at non-designers that generates design outputs intended to resemble the work of professional designers.
Magic Patterns is an AI design tool for product teams that converts text prompts into production-ready user interfaces. It supports use of an organization's design system, rapid prototype generation, and collaborative workflows.
Runway (formerly RunwayML) is a company that develops generative and multimodal machine learning models and a web-based creative platform for image and video editing and generation. It provides tools and services—accessible via runway.com—for tasks such as text-to-image and text-to-video generation, video editing, and other creative AI workflows.
Netic is an AI operations platform for essential-service companies that mediates customer interactions and deploys AI agents across voice, text, and websites. It applies operational rules, coordinates labor, and supports inbound, outbound, and analytical workflows.
Lassie is an AI-driven healthcare administration platform for medical practices. It automates patient enrollments, payment posting, and electronic funds transfer (EFT) reconciliation to reduce manual billing, revenue-cycle, and administrative work, allowing clinical teams to focus on patient care.
1X Neo is a humanoid home and service robot product from 1X, an AI and robotics company based in Palo Alto, California. The robot is designed to perform household and commercial chores and provide personalized assistance, and 1X positions the platform as open to third-party developers and external AI models for custom applications.
NVIDIA Dynamo is a developer toolkit from NVIDIA for managing distributed key–value (KV) context caches used in large‑language‑model inference. It provides KV‑aware routing, cache offloading, and prefill/decode disaggregation to move KV cache and related activation/state across GPU clusters, reducing memory pressure and supporting scalable LLM serving. It is intended for integration into GPU‑based inference and serving stacks.
Kie.ai is an API service that provides unified access to multiple AI models for chat, video, image, and music generation. The site advertises a free API key, stable performance, and pricing positioned as lower than competitors such as Replicate.
A local Model Context Protocol (MCP) bridge that connects Claude Cowork to Kie AI's image, video, and audio generation tools.
Bolt is an AI-powered builder for creating websites, web apps, and prototypes from natural-language prompts. The service is presented at bolt.new and positions itself as a tool to rapidly generate high-performing web projects.
llama.cpp is a C/C++ implementation for running large language and vision-language model inference locally or in the cloud, including on CPUs, GPUs, laptops, Apple silicon devices, and small computers such as Raspberry Pis. The project is built on the ggml library and uses integer quantization from 1.5-bit through 8-bit to reduce memory use and accelerate inference, with CPU, CUDA, HIP, Metal, Vulkan, SYCL, OpenCL, and other hardware backends. It supports hybrid CPU-GPU inference for models larger than available VRAM and includes command-line tools, a built-in web interface, and an OpenAI-compatible REST API server. The project is distributed as source code, Docker images, and pre-built binaries, with installation instructions at llama.app.
Orgo is a provider of instant cloud computers designed for use by AI agents. It offers full Linux and Windows desktops accessible through an API, advertised as ready in under a second and controllable by autonomous software.
Clawtag was an AI Slack bot that persistently monitored configured company channels, stored messages in a database, and inserted itself into discussions; it was later changed to respond only when explicitly invoked by users.
A workflow orchestration component of Microsoft's AutoGen framework for building directed agent workflows. It supports sequential and parallel steps, conditional branching, and loops.
An AI-agent development tool that compiles natural-language skills into structured Python programs. It applies schema, safety, security, and guardian-hook checks during compilation.
A managed inference service from Red Hat for running enterprise AI inference workloads without directly selecting or managing GPUs. It provides usage-based scaling while abstracting underlying GPU capacity.
RouteLLM is an open-source framework from lm-sys for serving and evaluating routers that direct requests between stronger and cheaper language models. It provides trained routers, a drop-in replacement for the OpenAI client, and an OpenAI-compatible server; routing decisions use configurable cost thresholds that can be calibrated for a target share of requests sent to the stronger model. The framework supports comparing routers across benchmarks and extending it with additional routers, model pairs, and providers.
FoundationPose is an NVIDIA Research implementation of a unified foundation model for 6D object pose estimation and tracking of novel objects. It supports model-based operation from a CAD model and model-free operation from a small set of reference images, applying to a new object at test time without fine-tuning. A neural implicit representation provides novel-view synthesis while keeping the downstream pose-estimation modules shared across both setups; the system uses large-scale synthetic training, a transformer-based architecture, contrastive learning, and language-model assistance. The repository includes robotic and augmented-reality demos and provides Docker-based setup instructions and downloadable model weights.
A multi-model orchestration platform attributed to Sakana AI that routes requests among multiple AI models through an API.
HeyGen is an AI-powered video generation platform that creates videos from text, image, or audio inputs. The service provides virtual presenters (avatars), narration, captions, and visual animations for producing short marketing, training, and social videos.
GuideLLM is an open-source platform for benchmarking and evaluating real-world LLM inference deployments. It simulates end-to-end interactions with OpenAI-compatible and vLLM-native servers, using real or synthetic text and multimodal datasets and configurable execution profiles such as synchronous, concurrent, throughput, constant-rate, Poisson, and sweep workloads. It measures SLO-oriented latency and token statistics, including time to first token, inter-token latency, and end-to-end behavior, then produces console, JSON, CSV, or HTML reports for deployment tuning, capacity planning, and regression tracking. The tool provides both a CLI and API, with multiprocessing, threading, asynchronous execution, and Hugging Face, file, synthetic, or custom data sources.
Paper is a web-based design tool for creating, sharing, and shipping design work. It is presented on its official site as a platform for designers to produce and collaborate on visual and product designs.
Conductor is an AI agent interface from Paper for creating Paper design frames, generating variations, and addressing design comments.
Composer 2.5 is an AI model from Cursor designed for fast, precise work across large numbers of artboards.
A development tool that automatically enforces the red-green-refactor test-driven development cycle for AI coding agents.
Probity is an open-source project by Nizar Selander that provides tooling to enforce test-driven development (TDD) guardrails for AI coding agents. It is designed to run and validate automated tests and checks against code produced by AI agents to ensure adherence to TDD workflows.
Claude Max is a subscription plan for Anthropic's Claude AI assistant. It provides access to the underlying AI models used in experiments. The plan is part of Anthropic's Claude product offerings.
An AI voice-agent platform for building and deploying phone-based conversational agents. It supports agents that conduct automated interviews and other business conversations over telephone calls.
Custom GPTs is a feature of OpenAI's ChatGPT that lets users create and configure customized GPT instances with tailored instructions, behaviors, and integrations. It is provided by OpenAI to enable creation of conversational agents without writing code.
Futuredia is a digital agency that offers web development, design (UI/UX), and digital marketing services. It operates as a customer-facing creative and technology provider rather than a single software product.
Superhuman is a commercial email and productivity suite developed by Superhuman, Inc. It provides a fast email client (Mail), collaborative documents (Docs), and built-in AI features for drafting, summarization, and triage that operate on users' connected email accounts and documents. The product runs as a web service with native desktop and mobile apps and is distributed as a paid subscription.
Fish Audio is an AI text-to-speech and voice cloning service that provides studio-grade TTS with emotion control and a large library of voices across multiple languages. The service is presented at fish.audio and markets features such as voice cloning and an industry-leading voice generator.
An AI-powered website builder and hosting service from Hostinger that generates, edits, publishes, hosts, and supports local lead-generation websites. It supports connecting custom domains.
Obsession Audit is an AI-powered service that analyzes a user's life and activities to identify personal obsessions that could be developed into business ideas. The site describes it as a tactical audit that 'reads your life back to you' to find the obsession worth building a business around.
Rork is an AI-powered mobile-app builder for creating iPhone and Android applications from natural-language descriptions without traditional coding. It generates mobile app projects and is aimed at users without software-development experience.
Tinker is a post-training API from Thinking Machines Lab for customizing machine-learning models through a closed-loop workflow. Applications and coding harnesses submit training or customization jobs and receive updated model weights for deployment.
CoreWeave is a cloud infrastructure provider for AI, offering compute clusters that companies can obtain for AI workloads instead of using a compute marketplace.
Groq (Groq Inc.) is a U.S.-based company that designs AI accelerator hardware and provides a cloud-based inference platform. The company builds a tensor-streaming architecture and ships hardware and software for high-throughput, low-latency machine learning inference. Its public site describes a "neocloud" offering for inference and infrastructure.
A service that provides cybersecurity defenders with access to the Mythos Preview model and the latest GPT models.
Wegic is an AI-powered website builder and hosting platform (wegic.ai) that generates custom websites without coding. It advertises fast, stable hosting, SEO-ready site output, and a free tier for launching business sites.
An open-weight AI safety guardrail for security operations centers (SOCs), designed to be independently deployed rather than used solely through a hosted service. Its specific detection inputs and supported deployment integrations are not established here.
Phoenix is an open-source AI observability platform developed by Arize for experimenting with, evaluating, and troubleshooting LLM applications and agents. It traces application runtime with OpenTelemetry-based instrumentation, supports response and retrieval evaluations, and provides versioned datasets, experiment tracking, prompt management, and a playground for comparing models, adjusting parameters, and replaying traced calls. Phoenix also includes PXI, an AI engineering agent for debugging traces and iterating on prompts, plus a remote MCP server for querying traces, datasets, and experiments from MCP clients. It can run locally, in containers, through Kubernetes and Helm, or in the cloud, and is distributed through the `arize-phoenix` Python package, Conda, Docker images, and related TypeScript and Python packages.
Accio Work is an AI-driven platform from Accio that provides agentic teams to execute business tasks. The service offers built-in skills and connectors to integrate with external services and perform actions beyond conversational chat, aiming to automate workflows and run business operations.
Build business apps with AI – that are actually secure. Internal-only or external-facing business apps. Softr is a no-code (now AI-native) platform for building custom web applications, client portals, internal tools, dashboards, membership sites, CRMs, directories, and operational systems — without writing code. What it does You connect existing data sources (or create new ones inside Softr) and then either: Use a visual drag-and-drop builder with pre-built blocks (lists, tables, forms, charts, Kanban boards, calendars, detail views, etc.), or Describe what you want in plain language using the AI Co-Builder, which generates the database structure, UI, business logic, authentication, and permissions. The result is a responsive web app (with PWA support) that can be published with a custom domain, user logins, granular permissions, and branding.
Murmell is a cloud platform for running and coordinating AI coding agents (for example Codex, Claude, and Kimi). It provides a shared cloud sandbox for collaborative coding, real-time file-path locking to prevent merge conflicts, and tools to deploy from any terminal.
Inventory is a menu-bar application that indexes and lets users search local AI and IDE conversation histories (for tools such as Cursor, Claude Code, Zed, Codex, Kiro and Antigravity). It stores data locally, requires no signup or cloud account, and is offered for a one-time fee.
Airtop is a platform for building and deploying AI-driven web agents. It compiles workflows described in natural language into deterministic agents that can log in, browse, and perform actions at scale.
AgentSky is a cloud API platform that lets developers run and manage multiple coding agents (for example, Claude Code, Codex, Hermes, OpenClaw, and Pi) through a single endpoint. It is intended to let users start agents or integrate agents into their products.
A local Windows workbench for running multiple coding agents side by side in a single arranged window. It saves and tracks agent sessions, alerts users when an agent requires approval, and allows the same command-line interface to use different models.
NudgeForMe is an AI-powered follow-up assistant for email. It scans a user's sent conversations to identify stalled deals, proposals, client requests, introductions, and approvals, and drafts suggested next follow-up messages.
Port22 is a tool for remotely running and controlling code-focused AI agents. It uses a Mac agent paired with a phone to drive agents such as Claude Code, Codex, OpenCode, and Aider, providing live transcripts, in-phone approval, LAN support, and an end-to-end encrypted relay.
Cleanlist is an AI-powered B2B data enrichment platform aimed at go-to-market (GTM) teams. The service provides contact and firmographic enrichment from a claimed 15+ data sources and advertises metrics such as 98% email accuracy and 85% direct-dial coverage; customers listed on the site include Proposify, Float, and Warp.
Halo is a live-call monitoring product from ScamAI that detects deepfakes, forged identity documents, and AI-generated fraud in real time during voice and video calls. It is offered as part of ScamAI's suite and API for KYC, claims verification, and content moderation.
Reasonix is an open-source AI coding agent built around a local engine and distributed as a self-contained static Go binary. It is designed for DeepSeek, with DeepSeek provided as a preset, while configuration can target OpenAI-compatible endpoints and optionally use separate executor and planner models. The agent can be used through a terminal or desktop app, in a browser, or from an editor through ACP; it provides plan mode, permissions, workspace sandboxing, per-turn checkpoints, and MCP- or extension-based plugins. Its context maintenance is designed around prefix-cache stability, including a stable startup environment summary and pruning of stale tool output before compaction.
Omnigent is an open-source AI agent framework and meta-harness that provides a common orchestration layer for Claude Code, Codex, Cursor, OpenCode, Hermes, Pi, and custom agents. It allows agents to be swapped or combined without rewriting integrations, supports multi-agent supervision and collaboration, and keeps messages, sub-agents, terminals, and files synchronized across terminal, browser, phone, and desktop sessions. The framework can run agent sessions in disposable cloud sandboxes and applies governance policies at the server, agent, or chat level, including approval gates for risky actions, spending limits, and tool restrictions. It supports compatible model gateways and optional integrations for model providers, sandbox providers, SDK harnesses, storage, and memory. Omnigent is distributed as an open-source Python package requiring Python 3.12 or later, with installation through its installer, uv, pip, Homebrew, or the Git repository.
MiroFish is an open-source multi-agent prediction engine that builds simulated digital worlds from source materials such as news, policy drafts, financial signals, reports, or stories. Its workflow extracts entities and relationships into a knowledge graph, injects individual and collective memory through GraphRAG, generates agent personas and configurations, and runs parallel simulations in which agents with independent personalities, long-term memory, and behavioral logic interact and evolve. Users can describe prediction requirements in natural language, introduce variables during a simulation, chat with agents in the simulated world, and receive a generated prediction report.
AutoGPT is an open-source platform for building, deploying, and running AI agents that carry out complete workflows. Users can describe an outcome in plain English, or use its visual builder to drag, connect, branch, and inspect workflow blocks. Agents can run on demand, on schedules, or from event triggers, and the marketplace provides ready-made agents that can be added and customized. The hosted platform is a paid, usage-based service that manages infrastructure, model access, credentials, and updates; the self-hosted path is free of license fees but requires users to provide infrastructure and model API keys and maintain the deployment.