No paid plan attached at all — every tool on this page is listed as free, not as a free trial and not as a free tier that upsells.
Flocci AI Tools lists 396 of them, ordered free tiers first: AFFiNE, Ai2 Paper Finder (Asta), Aila (Oak National Academy), AlphaFold Server and alphaXiv. Every one of them is free or has a free tier. Each entry states what it uniquely does rather than a score.
396 on this page are marked fully free with no paid plan at all: AFFiNE, Ai2 Paper Finder (Asta), Aila (Oak National Academy), AlphaFold Server and alphaXiv. The remaining 0 are freemium, trial or paid, and each is labelled with its exact tier so nothing surprises you at sign-up.
Free tools first, then freemium, then trial, then paid, and alphabetically inside each tier. Nobody pays to appear higher: Flocci AI Tools carries no ads, no sponsored slots and no paid listings, so the order reflects price and nothing else.
AFFiNE, Ai2 Paper Finder (Asta), Aila (Oak National Academy), AlphaFold Server and alphaXiv all work in a browser tab with no install needed — just open the site and go. 128 of the 396 free Completely Free AI Tools listed here are browser-based.
AFFiNE, alphaXiv, Chat2DB, Google AI Mode and Google Opal support Google sign-in, so you can start without creating a new account. That's 23 of the 396 free Completely Free AI Tools on this page.
AFFiNE, Bhashini, Chatbox, DeepSeek Models and Goblin Tools have an iOS or Android app. 50 of the 396 free Completely Free AI Tools here can run on your phone.
ACE-Step, Affinity by Canva, Agent2Agent (A2A) Protocol, AgenticSeek and Agno can be self-hosted or run locally without a browser — useful for privacy, air-gapped networks, or avoiding API rate limits. 222 of the 396 free Completely Free AI Tools here run offline.
| Tool | Pricing | Type | Listed for |
|---|---|---|---|
| AFFiNE | Free | AI Note-Taking & Docs | Open-source workspace that merges docs, whiteboards and databases |
| Ai2 Paper Finder (Asta) | Free | Academic Research | Agentic literature-search tool built by Ai2, now folded into the broader 'Asta' research-agent platform |
| Aila (Oak National Academy) | Free | AI for Teachers & Classrooms | Generates lesson plans, slides, quizzes and worksheets |
| AlphaFold Server | Free | Science & Research AI | Free browser-based access to AlphaFold 3-class structure prediction for non-commercial research |
| alphaXiv | Free | Academic Research | Free overlay for arXiv papers with public discussion/comment threads per paper |
| Apertus Chat (Public AI) | Free | General Purpose Chatbots | Chat directly on Apertus 1.5, the fully open Swiss model from ETH, EPFL and CSCS (released 2026-07-24) |
| Arize Phoenix | Free | LLM Eval & Observability | Fully open-source, self-hostable with zero setup via `uvx` (pip/conda also supported) |
| AutoGPT | Free | General Autonomous Agents | Open-source platform for building and running continuous AI agents |
| Bhashini | Free | Translation & Language AI | Government of India's free national language platform: text, speech-to-text, text-to-speech and translation across 22 Indian languages |
| Bing Image Creator | Free | AI Image Generation | Free text-to-image with Microsoft MAI-Image-2.5-Flash and MAI-Image-2e |
| Biomni | Free | Science & Research AI | General-purpose biomedical agent combining LLM planning with code execution |
| Blinko | Free | AI Note-Taking & Docs | Self-hosted personal note tool with AI retrieval over your notes (RAG) |
| Bolna | Free | Real-Time Voice Agents | Open-source framework for phone voice agents, from an India-based team |
| CADAM (Adam) | Free | 3D & CAD Generation | Open-source web app turning natural-language descriptions into parametric OpenSCAD models |
| Chat2DB | Free | AI Database & SQL Copilots | Cross-platform database client with natural-language SQL generation and optimisation |
| Chatbox | Free | Multi-Model Aggregators & Universal Clients | Open-source (GPL-3.0) desktop and mobile client for OpenAI, Claude, Gemini and Ollama with local data storage |
| Cloudflare VibeSDK | Free | App Builders & Vibe Coding | Open-source vibe coding platform you deploy to your own Cloudflare account |
| Copilot 3D | Free | 3D & CAD Generation | One-click conversion of a JPG or PNG (under 10MB) into a downloadable GLB 3D model |
| Copilot Audio Expressions | Free | AI Voice & Speech | Turns text into expressive speech using Microsoft's MAI-Voice models |
| Daydream | Free | AI Shopping Assistants | Proprietary fashion-trained AI understands cut/color/occasion, not generic product search |
| DeepSeek Models | Free | Notable Open Models | DeepSeek V4-Pro and V4-Flash open-weight MoE models, MIT-licensed |
| DeepWiki | Free | AI Docs & Codebase Q&A | Auto-generates conversational, up-to-date wikis for any public GitHub repo |
| Design Arena | Free | Leaderboards & Benchmarks | Crowdsourced Bradley-Terry (Elo-style) ranking of AI models specifically on design/aesthetic quality, not raw capability |
| dots.ocr (dots.mocr) | Free | AI OCR & Document Extraction | 3B vision-language model for layout parsing across many scripts |
| Eclipse Theia IDE | Free | AI IDEs & Editors | Open-source, vendor-neutral IDE with AI agents built on Theia AI |
| Epoch AI | Free | Leaderboards & Benchmarks | Independent, non-vendor research institute tracking AI compute, training cost and capability trends over time |
| ERNIE 4.5 Open Models (Baidu) | Free | Notable Open Models | ERNIE-4.5 family including 21B-A3B Thinking and VL-424B-A47B multimodal MoE |
| Falcon (TII) | Free | Notable Open Models | Falcon-H1 hybrid Transformer-Mamba family for efficient long-context inference |
| Falcon LLM Chat (TII) | Free | General Purpose Chatbots | Free public playground for Abu Dhabi TII's open-weight Falcon models |
| FinGPT | Free | Finance & Accounting AI | Open financial LLMs for sentiment analysis and stock forecasting |
| Flowise | Free | Workflow Automation | Drag-and-drop builder for chatbots, agents and RAG flows |
| FunClip | Free | Video Editing & Repurposing | Open-source local tool from Alibaba's speech lab: transcribe video, pick text/speakers, click to cut clips |
| Genmo (Mochi 1) | Free | AI Video Generation | Fully open-source text-to-video model (Mochi 1) with downloadable weights |
| Gitingest | Free | AI Docs & Codebase Q&A | Swap 'hub' for 'ingest' in a GitHub URL to get a prompt-friendly repo digest |
| Goblin Tools | Free | Email, Scheduling & Tasks | Magic ToDo breaks a task into tiny steps with adjustable spiciness |
| Google AI Mode | Free | General Purpose Chatbots | Conversational AI search inside Google powered by Gemini with follow-up questions |
| Google LearnLM | Free | AI Tutors & Learning | Learning-tuned tutoring in Gemini |
| Google Opal | Free | Workflow Automation | Describe an app in plain language and Opal builds a shareable multi-step AI workflow |
| Google Pomelli | Free | Presentations & Design | Scans your website to build a Business DNA brand profile (tone, fonts, palette, imagery) |
| Google Stax | Free | LLM Eval & Observability | Build evals with human raters or LLM autoraters on your own data |
| Google TextFX | Free | Copywriting & Writing | Ten AI writing tools for wordplay, similes, chains and rhymes |
| Google Translate | Free | Translation & Language AI | Free text, image, document, website and conversation translation in 240+ languages |
| HuggingChat | Free | General Purpose Chatbots | Completely free and open-source |
| Hunyuan (Tencent) | Free | Notable Open Models | Open-weight Hunyuan Hy3 and Hy4-preview flagship text models |
| Jais Chat | Free | General Purpose Chatbots | Bilingual Arabic/English chatbot built on Jais 30B/70B, the leading Arabic-trained LLM family |
| K2 Think | Free | General Purpose Chatbots | MBZUAI/G42 chat app for the open Apache-2.0 K2 Think V2 reasoning model, served on Cerebras |
| Kagi Translate | Free | Translation & Language AI | Free LLM-powered translation for text, web pages and documents across 240+ languages |
| Karakeep | Free | AI Note-Taking & Docs | Self-hosted bookmark and notes app that auto-tags saved links with AI |
| Kimi | Free | General Purpose Chatbots | Free access to Moonshot's Kimi K3 and K2-series agentic models |
| Kokoro Web | Free | AI Voice & Speech | Free web front-end and API for the Kokoro-82M TTS model, self-hostable and OpenAI-compatible |
| Kortix (Suna) | Free | General Autonomous Agents | Open-source agent platform (formerly Suna) that runs specialist agents on isolated cloud computers |
| Kyutai Unmute | Free | Real-Time Voice Agents | Wraps any text LLM with Kyutai's streaming speech-to-text and text-to-speech for voice conversation |
| Laminar | Free | LLM Eval & Observability | Open-source observability and evals platform for AI agents (Apache-2.0) |
| LangBot | Free | Workflow Automation | Builds AI bots for WeChat, QQ, Discord, Slack, Telegram and other chat platforms |
| LangExtract (Google) | Free | AI OCR & Document Extraction | Python library extracting structured data from unstructured text with LLMs |
| Langflow | Free | Workflow Automation | Open source with 138k GitHub stars, free desktop app and free cloud account |
| LibreTranslate | Free | Translation & Language AI | Self-hostable open-source machine translation API and web UI |
| Little Language Lessons | Free | Language Learning AI | Tiny Lesson: situational vocabulary and grammar on demand |
| LiveBench | Free | Leaderboards & Benchmarks | Continuously refreshed questions to avoid benchmark contamination |
| LLaMA-Factory | Free | Fine-Tuning & Training Frameworks | Zero-code Web UI (LLaMA Board) for fine-tuning 100+ open models without writing training scripts |
| LMArena (Arena.ai) | Free | Leaderboards & Benchmarks | Crowd-voted 'Battle Mode' blind head-to-head comparisons across text, image, and coding/agent models |
| MAGI-1 (Sand AI) | Free | AI Video Generation | Apache-2.0 autoregressive video model generating chunk by chunk for text, image and video-to-video |
| Magika (Google) | Free | Security & IT Operations | Deep-learning file-content type detection across 200+ types |
| marimo | Free | AI Data Analysts | Reactive Python notebook stored as plain .py files, git-friendly |
| MCP Registry (Official) | Free | MCP Ecosystem | The canonical open-source specification and docs for the Model Context Protocol |
| MemOS | Free | Agent Memory & RAG-as-a-Service | Memory operating system for LLM agents with hybrid retrieval and persistent memory |
| Meta AI | Free | General Purpose Chatbots | Free assistant now powered by Meta's Muse Spark models |
| Meta Vibes | Free | AI Video Generation | Text-to-video and image-to-video generation with a remix feed |
| Metabase | Free | Business Intelligence | Self-hostable open-source BI with dashboards and questions |
| Metaso AI Search (Mita) | Free | AI Search & Answer Engines | Ad-free AI search with direct answers |
| Microsoft Translator | Free | Translation & Language AI | Free app and web translator for text, speech, images and multi-person live conversations |
| Mike (open-source legal AI) | Free | Legal AI | Open-source legal AI for document review, research, contract drafting and workflows |
| MinerU | Free | AI OCR & Document Extraction | Parses PDFs, images and Office files into Markdown, JSON, HTML or LaTeX |
| MiniMax M2 (open weights) | Free | Notable Open Models | MiniMax's open-weight M-series: M3 multimodal MoE with very long context, plus M2.x agentic-coding checkpoints |
| MiroThinker | Free | Deep Research & Documents | Deep research agent with up to 300 tool calls per task and 256K context |
| Mistral Open Models (Magistral, Devstral, Voxtral) | Free | Notable Open Models | Open-weight Mistral Medium 3.5, Small 4 and Large 3 general models |
| Morphic | Free | AI Search & Answer Engines | Open-source, Apache 2.0, self-hostable generative-UI search engine |
| NextChat | Free | Multi-Model Aggregators & Universal Clients | MIT-licensed lightweight AI chat client with one-click Vercel deployment and roughly 5MB desktop apps |
| NVIDIA Canary-Qwen 2.5B | Free | Speech & Transcription Engines | Speech-recognition plus LLM hybrid model that transcribes and can summarize or answer questions about audio |
| NVIDIA Cosmos | Free | Robotics & Embodied AI | Open platform of world foundation models, datasets and tools for physical AI |
| NVIDIA Parakeet | Free | Speech & Transcription Engines | Tops the Hugging Face Open ASR Leaderboard with 6.05% average WER at 0.6B params |
| OLMo (Ai2) | Free | Notable Open Models | Only major model family shipping full pretraining data (Dolma), code and intermediate checkpoints, not just weights |
| olmOCR | Free | AI OCR & Document Extraction | Apache 2.0 open-source OCR toolkit from Ai2, 19.3k GitHub stars |
| Open ASR Leaderboard (Hugging Face) | Free | Leaderboards & Benchmarks | Ranks speech-recognition models by word error rate and real-time speed across English and multilingual sets |
| OpenBB | Free | Finance & Accounting AI | Connect-once financial data layer for Python, Excel, REST and MCP |
| OpenHands | Free | Autonomous Coding Agents | Self-hosted control center for coding agents with GUI, CLI and SDK surfaces |
| OpenShorts | Free | Video Editing & Repurposing | MIT open-source clip generator: AI moment detection, face-tracked 9:16 crops and subtitles |
| PaddleOCR-VL | Free | AI OCR & Document Extraction | 1B-parameter document parsing VLM (NaViT encoder + ERNIE-4.5-0.3B) |
| Penpot | Free | Presentations & Design | Open-source (MPL-2.0) browser design and prototyping tool with real-time collaboration |
| Phia | Free | AI Shopping Assistants | Chrome extension + iOS app that surfaces resale/secondhand alternatives while shopping |
| Pi (Inflection AI) | Free | General Purpose Chatbots | Fully free personal-AI chatbot with no subscription tier at all — unlimited conversations, no paywall |
| PicLumen | Free | AI Image Generation | Genuinely free image generation |
| Podcastfy | Free | AI Music & Audio | Python package and free HF demo that turns websites, PDFs, images and YouTube into multi-speaker podcasts |
| Presenton | Free | Presentations & Design | Open-source (Apache-2.0) AI presentation generator with desktop app and Docker deployment |
| Qwen (Alibaba) | Free | Notable Open Models | Open Qwen3.x family from phone-sized to multi-trillion-parameter MoE, Apache 2.0 |
| Qwen Chat | Free | General Purpose Chatbots | Free access to Alibaba's latest Qwen3.x models, including the Max tier |
| Qwen-Image | Free | AI Image Generation | Image model family with strong in-image text rendering; Qwen-Image-2512 and Qwen-Image-2.1 (Sep 2026, 7B, transparent RGBA output) |
| RAGFlow | Free | Agent Memory & RAG-as-a-Service | Open-source RAG engine with deep document parsing and agent workflows |
| Reactive Resume | Free | Career & Job Search | Free, open-source resume builder with no paywalls or watermarks |
| Repomix | Free | AI Docs & Codebase Q&A | Packs an entire repository into one AI-friendly file |
| ResearchRabbit | Free | Academic Research | Visual citation-network mapping across 310M+ papers |
| Riffusion | Free | AI Music & Audio | Riffusion's Producer was acquired by Google and now continues as Flow Music |
| Sakana Chat | Free | General Purpose Chatbots | Free general-public chat service from Sakana AI, built on its own Namazu model |
| Sapling AI Detector | Free | AI Content Detection & Humanizers | Free probability score that text is AI-generated, with sentence-level highlighting |
| Scira | Free | AI Search & Answer Engines | Free, no credit card required |
| Seed-OSS (ByteDance) | Free | Notable Open Models | Seed-OSS-36B open reasoning LLM with native 512K-token context, Apache 2.0 |
| Segment Anything Playground | Free | AI Image Editing & Enhancement | Browser playground to try Meta SAM 3, SAM 3D and SAM Audio |
| Semantic Scholar | Free | Academic Research | Fully free AI-powered search across 237M+ scientific papers |
| Semrush AI Visibility Checker | Free | AI Search Visibility & GEO Tracking | Score of brand visibility across ChatGPT, Gemini, AI Mode and AI Overviews |
| sherpa-onnx | Free | Speech & Transcription Engines | Offline speech-to-text, text-to-speech, VAD and speaker diarization without internet |
| Sim | Free | Workflow Automation | Visual canvas for building, deploying and monitoring AI agents and workflows |
| Step (StepFun) | Free | Notable Open Models | Step-3.7-Flash open multimodal model with FP8, NVFP4 and GGUF builds |
| STORM (Stanford) | Free | Deep Research & Documents | MIT-licensed open-source system that researches a topic and writes a full cited report |
| Strix | Free | Security & IT Operations | Open-source autonomous agents that probe apps and validate vulnerabilities with proof-of-concept exploits |
| SWE-bench | Free | Leaderboards & Benchmarks | The standard benchmark for evaluating autonomous coding agents on real GitHub issue resolution |
| Tongyi DeepResearch | Free | Deep Research & Documents | 30.5B-parameter MoE agent (3.3B active) with 128K context for long-horizon research |
| Treblo (formerly Sonauto) | Free | AI Music & Audio | Free AI song generator with vocals from prompts or lyrics, reported without a credit system |
| Twenty CRM | Free | Sales & Customer Intelligence | Open-source CRM with custom objects, fields and views |
| Univer | Free | AI for Spreadsheets & Excel | Open-source spreadsheet, docs and slides engine for AI agents |
| Vespa | Free | Vector Databases & RAG Infra | Open-source AI search platform combining vector, text and structured search |
| Windmill | Free | Workflow Automation | Open-source, self-hostable with unlimited executions on the free tier |
| Wonderplan | Free | Travel Planning | Day-by-day itineraries from destination, budget and interests |
| Xiaomi MiMo | Free | Notable Open Models | MiMo-V2.6-Pro (1T parameters) and V2.6-Flash (311B) open-weight reasoning and agent models |
| Xiaomi MiMo Studio | Free | General Purpose Chatbots | Xiaomi's web chat for its open-source MiMo MoE models (MIT license) with classic, deep-reasoning and web-search modes |
| Youdao Translate | Free | Translation & Language AI | NetEase Youdao's free translator for Chinese, English and 100+ languages |
| YuE | Free | AI Music & Audio | Open Apache-2.0 lyrics-to-song foundation model producing multi-minute songs with vocals and accompaniment |
| Zero | Free | Email, Scheduling & Tasks | Fully open-source (MIT license), self-hostable AI email client |
| Zonos | Free | AI Voice & Speech | Apache-2.0 TTS with emotion, pitch and speaking-rate conditioning |
| ACE-Step | Free | AI Music & Audio | Open-weight (Apache-2.0) music foundation model that generates full songs with vocals from text and lyrics |
| Ada Health | Free | Health & Fitness AI | AI symptom assessment based on your answers, available in many languages |
| Affinity by Canva | Free | AI Image Editing & Enhancement | Professional photo, vector and layout suite now free for everyone |
| Agent Zero | Free | General Autonomous Agents | Agent framework that gives the agent a full Linux desktop and browser to work in |
| Agent2Agent (A2A) Protocol | Free | MCP Ecosystem | Open protocol for agents from different vendors to discover and talk to each other |
| AgenticSeek | Free | General Autonomous Agents | Fully local autonomous agent that browses, codes and plans without cloud APIs |
| Agno | Free | Agent Frameworks (Developers) | Open-source (Apache-2.0) Python framework, 41.7k GitHub stars |
| AI Scientist-v2 | Free | Science & Research AI | Agentic tree search proposes ideas, runs experiments and writes papers |
| AI Toolkit (Ostris) | Free | Fine-Tuning & Training Frameworks | All-in-one trainer for LoRAs on diffusion and video models (FLUX, Wan and more) |
| Aider | Free | Terminal & CLI Agents | Open-source AI pair programmer in your terminal |
| Alibaba Page Agent | Free | Browser & Computer-Use Agents | JavaScript in-page GUI agent that controls web interfaces via natural language |
| Alibaba Quark AI Assistant | Free | General Purpose Chatbots | 200M+ existing users of Quark's browser/search app now get a free Qwen3-powered chat assistant |
| Amazon Nova | Free | General Purpose Chatbots | Amazon's web playground to chat with Nova models (Nova 2 Lite and others) with a model dropdown |
| Amazon Nova Act SDK | Free | Browser & Computer-Use Agents | Python SDK for building reliable browser-automation agents on Amazon Nova |
| Amazon Rufus | Free | AI Shopping Assistants | Amazon's AI shopping assistant, now branded Alexa for Shopping (formerly Rufus) |
| Anarlog (Hyprnote) | Free | Meeting Assistants & Transcription | On-device meeting transcription and AI summaries without a bot joining the call |
| AnythingLLM | Free | Local LLM Runners | All-in-one local RAG and agents app |
| Argos Translate | Free | Translation & Language AI | Offline open-source translation library and GUI using OpenNMT models |
| AudioCraft (Meta) | Free | AI Music & Audio | Open-source library with MusicGen, AudioGen and EnCodec |
| Auto-Editor | Free | Video Editing & Repurposing | Free open-source CLI that automatically cuts silent or motionless sections from video and audio |
| AWS Strands Agents | Free | Agent Frameworks (Developers) | Open-source (6,800+ stars) Python and TypeScript SDK from AWS |
| Axolotl | Free | Fine-Tuning & Training Frameworks | Config-file-driven fine-tuning workflow (YAML) covering LoRA, QLoRA, full fine-tuning, preference tuning and RL |
| BAGEL (ByteDance) | Free | AI Image Editing & Enhancement | Apache-2.0 7B-active unified model for understanding, text-to-image and image editing |
| Baichuan Bai Xiao Ying (百小应) | Free | General Purpose Chatbots | Free consumer assistant from Baichuan, built on the Baichuan 4 base model |
| Baidu AI Search | Free | AI Search & Answer Engines | Ad-free AI answers built on Baidu Search, Wenku, Health and Law content |
| Baidu Ernie Bot (Wenxin Yiyan) | Free | General Purpose Chatbots | Baidu's flagship consumer chatbot built on its Ernie model family |
| Basic Memory | Free | Agent Memory & RAG-as-a-Service | MCP server that stores AI conversation memory as local Markdown notes |
| BiRefNet | Free | AI Image Editing & Enhancement | MIT-licensed high-resolution segmentation and matting model for clean background removal |
| BISHENG | Free | Workflow Automation | Open-source platform for building LLM workflows, RAG and multi-agent apps |
| BitNet | Free | Local LLM Runners | Official inference framework for 1-bit (ternary) LLMs |
| bolt.diy | Free | App Builders & Vibe Coding | Community fork of Bolt.new that lets you pick any LLM provider |
| Boltz | Free | Science & Research AI | First fully open-source model to approach AlphaFold3-level structure prediction, MIT-licensed |
| BrowserOS | Free | Browser & Computer-Use Agents | Open-source Chromium browser with a built-in AI agent that automates web tasks |
| CAMEL | Free | Agent Frameworks (Developers) | Open-source multi-agent framework focused on scaling agent societies and role-playing |
| Chatterbox (Resemble AI) | Free | AI Voice & Speech | MIT-licensed, fully open-source TTS/voice-cloning family (Turbo/Nano/Multilingual V3) |
| Cherry Studio | Free | Multi-Model Aggregators & Universal Clients | Free, open-source (AGPL-3.0) desktop client unifying OpenAI, Claude, Gemini, DeepSeek, Qwen and local Ollama/LM Studio models in one window |
| Claude Agent SDK | Free | Agent Frameworks (Developers) | MIT-licensed Python and TypeScript SDKs exposing the agent loop that powers Claude Code |
| Cline | Free | Terminal & CLI Agents | Open-source autonomous coding agent for VS Code |
| ClipsAI | Free | Video Editing & Repurposing | MIT Python library that finds clips in podcasts, interviews and talks using WhisperX transcripts |
| Cloudflare Agents SDK | Free | Agent Frameworks (Developers) | Framework for building and deploying stateful AI agents on Cloudflare Workers |
| Cognee | Free | Agent Memory & RAG-as-a-Service | Open-source memory platform that turns data into a knowledge graph plus vectors for agents |
| CogVideoX (Zhipu) | Free | AI Video Generation | Open text-to-video and image-to-video models (2B under Apache-2.0, 5B under CogVideoX license) |
| ComfyUI | Free | AI Image Generation | Node-graph interface for building image, video, audio and 3D generation workflows without code |
| Continue | Free | Code Autocomplete & Assistants | Apache-2.0 open-source coding agent for VS Code, JetBrains and the CLI |
| CosyVoice | Free | AI Voice & Speech | Multilingual voice generation with zero-shot voice cloning |
| CowAgent | Free | General Autonomous Agents | Open-source agent that plans tasks, runs tools and builds long-term memory |
| Coze Studio | Free | Workflow Automation | Open-source version of ByteDance's Coze agent builder with visual workflows |
| Crush | Free | Terminal & CLI Agents | Terminal coding agent from Charm with LSP-aware context |
| DaVinci Resolve (free) | Free | Video Editing & Repurposing | Free professional editor with AI-assisted tools added in version 20 (IntelliScript, animated subtitles, Audio Assistant, Magic Mask v2) |
| DB-GPT | Free | AI Data Analysts | Asks questions over databases, CSV and Excel files in natural language |
| DeepEval | Free | LLM Eval & Observability | Open-source LLM evaluation framework with pytest-style tests and 50+ metrics |
| DeepSeek-OCR | Free | AI OCR & Document Extraction | Vision-language OCR that compresses document context optically |
| DeepWiki-Open | Free | AI Docs & Codebase Q&A | Open-source self-hostable wiki generator for GitHub, GitLab and Bitbucket repos |
| DeerFlow (ByteDance) | Free | General Autonomous Agents | Open-source long-horizon SuperAgent harness that researches, codes and creates |
| Demucs | Free | AI Music & Audio | Hybrid Transformer Demucs separates songs into vocals, drums, bass and other stems |
| DiffRhythm | Free | AI Music & Audio | Open-source latent-diffusion model generating full-length songs with vocals in seconds |
| Docling | Free | AI OCR & Document Extraction | MIT-licensed, 64.7k GitHub stars, IBM Research-originated, now under LF AI & Data Foundation |
| Dolphin (ByteDance) | Free | AI OCR & Document Extraction | Two-stage document-type and layout analysis then element parsing |
| DSPy | Free | Agent Frameworks (Developers) | Open-source (MIT) framework from Stanford NLP, 37k+ GitHub stars |
| EleutherAI LM Evaluation Harness | Free | LLM Eval & Observability | Standard open framework for running hundreds of benchmarks (MMLU, GSM8K and more) against any LLM |
| Evo 2 | Free | Science & Research AI | DNA language model at single-nucleotide resolution with 1M base-pair context |
| EXAONE (LG AI Research) | Free | Notable Open Models | EXAONE 4.5: LG's first open-weight vision-language model for industrial use cases |
| exo | Free | Local LLM Runners | Links everyday devices (Macs, PCs, phones) into one cluster to run models too large for a single machine |
| F5-TTS | Free | AI Voice & Speech | Flow-matching TTS with zero-shot voice cloning from a few seconds of audio |
| faster-whisper | Free | Speech & Transcription Engines | Whisper reimplementation on CTranslate2, up to 4x faster with less memory |
| FastMCP | Free | MCP Ecosystem | Pythonic framework for building MCP servers and clients in a few lines |
| Firebase Genkit | Free | Agent Frameworks (Developers) | Open-source framework for AI apps in JavaScript, Go, Dart and Python |
| Firefox Smart Window | Free | Browser Extensions & Copilots | Built-in Firefox AI assistant that answers questions about the page and open tabs and searches browsing history in natural language |
| FLUX.2 [klein] | Free | AI Image Generation | 4B-parameter Apache-2.0 FLUX.2 variant for text-to-image and editing, released Jan 2026 |
| Fooocus | Free | AI Image Generation | Midjourney-like prompt-only UI on top of SDXL with built-in prompt expansion |
| Fun-CosyVoice 3 | Free | AI Voice & Speech | Alibaba Tongyi lab's 0.5B TTS covering 9 languages and 18+ Chinese dialects |
| FunASR | Free | Speech & Transcription Engines | Open-source speech recognition toolkit with Paraformer and SenseVoice models |
| garak (NVIDIA) | Free | Security & IT Operations | Open-source scanner probing LLMs for prompt injection, jailbreaks, leakage and toxicity |
| Gemini CLI | Free | Terminal & CLI Agents | Open-source terminal agent from Google |
| Gemini in Chrome | Free | Browser Extensions & Copilots | Gemini side panel that answers questions about the current tab and across tabs |
| Gemma (Google) | Free | Notable Open Models | Google's lightweight open models (Gemma 4) |
| Genesis | Free | Robotics & Embodied AI | Unified multi-physics simulation engine plus photorealistic renderer for robotics/embodied-AI training, fully open source |
| GitHub MCP Server | Free | MCP Ecosystem | GitHub's official MCP server for repos, issues, PRs and Actions |
| Google Agent Development Kit (ADK) | Free | Agent Frameworks (Developers) | Open-source Python/Java framework from Google for building multi-agent systems |
| Google AI Edge Eloquent | Free | AI Note-Taking & Docs | On-device Gemma ASR transcribes speech offline and strips filler words |
| Google AI Edge Gallery | Free | Local LLM Runners | Runs Gemma models fully on-device on Android and iOS, offline after one model download |
| Google Dreambeans | Free | Email, Scheduling & Tasks | Proactively builds 10-14 personalized story collections per day |
| Goose | Free | Terminal & CLI Agents | Open-source agent (now under Agentic AI Foundation/Linux Foundation) usable as CLI, desktop app or API |
| GPT Researcher | Free | Deep Research & Documents | Planner and executor agents gather from 20+ web sources |
| GPT-OSS (OpenAI) | Free | Notable Open Models | OpenAI's Apache-2.0 open-weight reasoning models (120B and 20B) |
| GPT-SoVITS | Free | AI Voice & Speech | Few-shot voice cloning and TTS from as little as one minute of audio |
| GPT4All | Free | Local LLM Runners | Private local chat with your documents |
| Graphiti | Free | Agent Memory & RAG-as-a-Service | Framework for building real-time temporal knowledge graphs for AI agents |
| GuideGeek | Free | Travel Planning | 1M+ consumer users per vendor, live since April 2023 (longer track record than most AI trip tools) |
| Handy | Free | Voice Dictation & Speech-to-Text | Free open-source speech-to-text that runs fully offline |
| Haystack | Free | Agent Frameworks (Developers) | Apache-2.0 framework for context-engineered, production RAG and agent pipelines |
| Hermes Agent | Free | General Autonomous Agents | MIT self-improving agent by Nous Research that writes skills from experience |
| HiDream-I1 | Free | AI Image Generation | 17B-parameter MIT-licensed image model with Full, Dev and Fast variants |
| HiDream-O1-Image | Free | AI Image Generation | MIT-licensed unified model for text-to-image, image editing and subject personalization up to 2048x2048 |
| Higgs Audio | Free | AI Voice & Speech | Open Apache-2.0 audio foundation model for expressive speech and multi-speaker dialogue |
| HolmesGPT | Free | AI DevOps & SRE | Open-source SRE agent that investigates alerts and incidents across your observability stack |
| Hunyuan Image (Tencent) | Free | AI Image Generation | Open-sourced 80B-parameter MoE text-to-image model (weights on Hugging Face) |
| Hunyuan-MT (HY-MT) | Free | Translation & Language AI | Tencent's open 7B translation models covering 33 languages including Chinese minority languages |
| Hunyuan3D-2 (Tencent) | Free | 3D & CAD Generation | Open-weight two-stage shape generation + high-res texture synthesis pipeline |
| HunyuanImage 3.0 (Tencent) | Free | AI Image Generation | Open-weights native multimodal image generation model |
| HunyuanVideo (Tencent) | Free | AI Video Generation | Open-weights text-to-video and image-to-video models from Tencent |
| HunyuanVideo 1.5 | Free | AI Video Generation | 8.3B-parameter open text-to-video and image-to-video model |
| HunyuanVideo-Foley | Free | AI Music & Audio | Generates synced sound effects and ambience for silent video from video plus text description |
| HunyuanWorld 1.0 | Free | 3D & CAD Generation | Generates explorable 3D worlds from text or image via 360 panorama then layered meshes |
| IBM Granite | Free | Notable Open Models | Apache 2.0 licensed enterprise-grade model family |
| ima.copilot (Tencent ima) | Free | Deep Research & Documents | AI workbench that searches, reads and writes from a personal knowledge base |
| IndexTTS | Free | AI Voice & Speech | Bilibili's zero-shot TTS with precise duration control and emotion control (IndexTTS2) |
| InfiniteTalk | Free | AI Avatars & Headshots | Apache-2.0 audio-driven generator: image-to-video talking avatars and video-to-video dubbing of unlimited length |
| InvokeAI | Free | AI Image Generation | Open-source web UI with unified canvas for generation, inpainting and outpainting |
| Jan | Free | Local LLM Runners | Open-source, offline ChatGPT alternative |
| Jupyter AI | Free | AI Data Analysts | Connects AI agents (Claude, Gemini and others) to JupyterLab via Agent Client Protocol |
| K8sGPT | Free | AI DevOps & SRE | Scans Kubernetes clusters and explains issues in plain language |
| Kandinsky 5.0 | Free | AI Video Generation | MIT-licensed family: Video Pro (19B), Video Lite (2B) and Image Lite (6B) |
| Khoj | Free | AI Note-Taking & Docs | Self-hostable second brain that answers from your notes and the web |
| Kimi Code CLI | Free | Terminal & CLI Agents | MIT-licensed terminal coding agent from Moonshot AI that edits files, runs shell commands and uses MCP |
| Kimi K3 (Moonshot AI) | Free | Notable Open Models | Open-weight multimodal MoE with about 2.8T total and 104B active parameters, 1M-token context |
| KittenTTS | Free | AI Voice & Speech | Ultra-small (tens of MB) Apache-2.0 TTS models that run on CPU |
| KoboldCpp | Free | Local LLM Runners | Ships as a single portable executable with a bundled web UI (KoboldAI Lite) |
| Kokoro TTS | Free | AI Voice & Speech | Only 82M parameters yet ranks near top of the TTS Arena leaderboard for quality |
| Krita AI Diffusion | Free | AI Image Editing & Enhancement | Free plugin adding generative inpaint, outpaint, ControlNet and upscaling to Krita |
| Kyutai TTS & STT | Free | AI Voice & Speech | Streaming TTS and STT models built on delayed-streams modeling, from the French Kyutai lab |
| LanceDB | Free | Vector Databases & RAG Infra | Embedded, developer-friendly retrieval library for multimodal AI |
| LangChain | Free | Agent Frameworks (Developers) | MIT-licensed framework of model, tool and retrieval integrations for agents |
| LangChain Deep Agents | Free | Agent Frameworks (Developers) | Batteries-included agent harness with planning, sub-agents and a virtual file system |
| LangGraph | Free | Agent Frameworks (Developers) | Build stateful, multi-agent apps as graphs |
| LeRobot (Hugging Face) | Free | Robotics & Embodied AI | Open PyTorch library for training real-world robot control policies (ACT, Diffusion Policy, VLA models) |
| LibreChat | Free | Multi-Model Aggregators & Universal Clients | Fully open-source, self-hostable ChatGPT-style interface connecting to OpenAI, Anthropic, Gemini, Bedrock, OpenRouter and more from one UI |
| LightRAG | Free | Agent Memory & RAG-as-a-Service | Simple, fast graph-based RAG from HKU Data Science lab (EMNLP 2025) |
| LitGPT | Free | Fine-Tuning & Training Frameworks | Clean from-scratch implementations of 20+ LLMs for pretraining, fine-tuning and deployment |
| LiveKit Agents | Free | Real-Time Voice Agents | Apache-2.0 open-source framework, fully self-hostable on your own servers |
| LivePortrait (Kuaishou) | Free | AI Avatars & Headshots | Animates a still portrait (human, cat or dog) from a driving video or expression controls |
| Llama (Meta) | Free | Notable Open Models | Meta's flagship open-weight family (Llama 4) |
| llama.cpp | Free | Local LLM Runners | Pure C/C++ inference engine with minimal dependencies, runs on CPU-only hardware |
| llamafile | Free | Local LLM Runners | Packs model weights and runtime into one executable that runs on macOS, Windows and Linux |
| LM Studio | Free | Local LLM Runners | Polished desktop GUI for local models |
| LocalAI | Free | Local LLM Runners | Drop-in OpenAI-compatible API server running models on your own hardware, CPU or GPU |
| Logseq | Free | AI Note-Taking & Docs | Privacy-first outliner and knowledge graph stored as local Markdown |
| LongCat (Meituan) | Free | Notable Open Models | LongCat-2.0 open-weight 1.8T-parameter model with FP8 and INT8 builds |
| LongCat Chat (Meituan) | Free | General Purpose Chatbots | Web chat for Meituan's open-source LongCat-Flash models (MIT license, 560B MoE) |
| LongCat-Image (Meituan) | Free | AI Image Generation | 6B Apache-2.0 bilingual (Chinese-English) text-to-image and image editing model |
| LTX-2 (Lightricks) | Free | AI Video Generation | Open DiT audio-video model generating synchronized sound and video in one pass |
| Magenta RealTime | Free | AI Music & Audio | Open-weights live music generation model steered by text or audio prompts |
| MagenticLite | Free | Browser & Computer-Use Agents | Open-source agent working across the browser and local files |
| Marker | Free | AI OCR & Document Extraction | Apache-2.0 code, 38.7k GitHub stars, converts PDFs/DOCX/PPTX/XLSX to markdown/JSON |
| MarkItDown | Free | AI OCR & Document Extraction | Converts PDF, Office files, images, audio and HTML into LLM-friendly Markdown |
| Mastra | Free | Agent Frameworks (Developers) | Open-source TypeScript framework (Apache 2.0) for agents, workflows and RAG |
| MCP Inspector | Free | MCP Ecosystem | Visual testing and debugging tool for MCP servers |
| MCP Python SDK | Free | MCP Ecosystem | Official Python SDK for MCP servers and clients |
| MCP TypeScript SDK | Free | MCP Ecosystem | Official TypeScript SDK for MCP servers and clients |
| mcp-use | Free | MCP Ecosystem | Fullstack framework for building MCP servers and MCP Apps for ChatGPT and Claude |
| MedGemma (Google) | Free | Healthcare & Clinical | Gemma 3 variants tuned for medical text and imaging (4B multimodal, 27B text and multimodal) |
| MediaPipe (Google AI Edge) | Free | Local LLM Runners | Cross-platform on-device ML for vision, audio, text and LLM inference |
| Memvid | Free | Agent Memory & RAG-as-a-Service | Packs agent memory into a single portable file with no server or database |
| Meta Edits | Free | Video Editing & Repurposing | Free mobile video editor from Instagram with frame-accurate timeline |
| Meta Seamless Communication | Free | Translation & Language AI | SeamlessM4T translates speech and text across ~100 languages: S2ST, S2TT, T2TT, ASR |
| MetaMCP | Free | MCP Ecosystem | Aggregates many MCP servers behind one endpoint with a web UI |
| Microsoft Agent Framework | Free | Agent Frameworks (Developers) | Unified open-source framework for building and orchestrating multi-agent systems in Python and .NET |
| Microsoft AutoGen | Free | Agent Frameworks (Developers) | Multi-agent conversation framework |
| Microsoft GraphRAG | Free | Vector Databases & RAG Infra | Builds knowledge graphs and community summaries from private text for RAG |
| Microsoft OmniParser | Free | Browser & Computer-Use Agents | Parses UI screenshots into structured interactable elements |
| Milvus | Free | Vector Databases & RAG Infra | Cloud-native Apache-2.0 vector database for large-scale similarity search |
| Ming-Image (Ant Group) | Free | Presentations & Design | MIT-licensed 6B model that generates UI screens, infographics and posters with readable text |
| mini-SWE-agent | Free | Autonomous Coding Agents | Roughly 100-line agent that solves GitHub issues or works in your command line |
| MiniMax Music 3 (open weights) | Free | AI Music & Audio | Open-weights model producing full songs up to five minutes from lyrics with section tags and a style description |
| Mistral Vibe | Free | Terminal & CLI Agents | Apache-2.0 minimal terminal coding agent built around Devstral models |
| MLC LLM | Free | Local LLM Runners | Compiles and runs LLMs natively on iOS, Android, browsers (WebGPU), Mac, Windows and Linux |
| MLX-LM (Apple) | Free | Local LLM Runners | Purpose-built for Apple Silicon's unified memory architecture, faster than llama.cpp for many models on Mac |
| MMAudio | Free | AI Music & Audio | Generates synchronised sound effects for a video and/or text prompt (video-to-audio and text-to-audio) |
| MONAI | Free | Healthcare & Clinical | PyTorch-based open framework for medical imaging AI, including segmentation and classification |
| Moonshine | Free | Speech & Transcription Engines | Small streaming speech-recognition models for phones, browsers and low-power devices |
| MOSS-TTS Family | Free | AI Voice & Speech | Apache-2.0 model family: long-form TTS, MOSS-TTSD multi-speaker dialogue (up to ~60 minutes), voice design from text, streaming TTS, and sound-effect generation |
| ms-swift (ModelScope) | Free | Fine-Tuning & Training Frameworks | Fine-tuning and deployment framework supporting hundreds of LLMs and multimodal models |
| MuJoCo | Free | Robotics & Embodied AI | Fast, accurate physics engine for robotics and biomechanics research |
| MuseTalk (Tencent) | Free | AI Avatars & Headshots | MIT-licensed real-time lip-sync model (30+ fps on a V100) for Chinese, English and Japanese audio |
| Nano AI Search (360) | Free | AI Search & Answer Engines | Calls 16+ Chinese large models (Doubao, Ernie, Qwen, MiniMax) in one search |
| Nanobot | Free | General Autonomous Agents | Ultra-light self-hosted personal agent with memory, tools and cron scheduling |
| Nanobrowser | Free | Browser & Computer-Use Agents | Chrome extension that runs a multi-agent team to automate browsing tasks |
| Nemotron (NVIDIA) | Free | Notable Open Models | NVIDIA's open Nemotron 3 family of efficient agentic models |
| NeuTTS | Free | AI Voice & Speech | On-device TTS with instant voice cloning from three seconds of audio |
| Nuclei | Free | Security & IT Operations | Template-based vulnerability scanner with thousands of community templates |
| NVIDIA Broadcast | Free | Meeting Assistants & Transcription | Free AI noise and echo removal for mics and speakers |
| NVIDIA Isaac GR00T | Free | Robotics & Embodied AI | Open, Apache-2.0-licensed vision-language-action foundation model for generalist humanoid robots (GR00T N1.7) |
| NVIDIA Isaac Lab | Free | Robotics & Embodied AI | GPU-accelerated framework for robot reinforcement and imitation learning on Isaac Sim |
| Official MCP Reference Servers | Free | MCP Ecosystem | Reference MCP servers such as filesystem, git, fetch and memory |
| Ollama | Free | Local LLM Runners | The default way to run LLMs locally |
| OmniGen2 | Free | AI Image Editing & Enhancement | Apache-2.0 model for text-to-image, instruction editing and in-context generation from multiple references |
| Open Interpreter | Free | General Autonomous Agents | Lets an LLM run code locally to do tasks on your computer, in a terminal chat |
| Open Notebook | Free | Deep Research & Documents | Self-hosted NotebookLM alternative over PDFs, video, audio and web pages |
| Open SWE | Free | Autonomous Coding Agents | Open-source asynchronous coding agent from LangChain |
| Open WebUI | Free | Local LLM Runners | Self-hosted ChatGPT-style interface |
| Open-AutoGLM | Free | Browser & Computer-Use Agents | Phone agent that reads the screen and taps through apps to finish natural-language tasks |
| OpenAI Agents SDK | Free | Agent Frameworks (Developers) | Lightweight agent orchestration from OpenAI |
| OpenAI Whisper | Free | Speech & Transcription Engines | Open-source speech-to-text, run locally free |
| OpenClaw | Free | General Autonomous Agents | MIT-licensed personal AI agent running on your own hardware with a local gateway |
| OpenCode | Free | Terminal & CLI Agents | Fully open-source terminal/IDE/desktop coding agent, MIT licensed |
| OpenEvidence | Free | Healthcare & Clinical | Point-of-care medical answers with citations |
| OpenLLMetry (Traceloop) | Free | LLM Eval & Observability | OpenTelemetry-based instrumentation for LLM calls, vector DBs and frameworks |
| OpenManus | Free | General Autonomous Agents | Open-source general agent framework built as a free alternative to Manus |
| openpi (Physical Intelligence) | Free | Robotics & Embodied AI | Open-source weights and code for pi0, pi0-FAST and pi0.5 vision-language-action models |
| OpenSandbox (Alibaba) | Free | Agent Frameworks (Developers) | Secure, fast runtime for executing untrusted AI-generated code |
| OpenVoice | Free | AI Voice & Speech | Instant voice cloning that transfers tone colour to multilingual speech |
| OpenWhispr | Free | Voice Dictation & Speech-to-Text | Voice-to-text dictation with local Parakeet or Whisper, or cloud models |
| Opera Browser AI (Aria) | Free | Browser Extensions & Copilots | Free, native AI assistant built into Opera's mainstream and GX browsers, no separate app needed |
| Orpheus TTS | Free | AI Voice & Speech | Llama-based speech LLM with human-like intonation and emotion tags |
| Page Assist | Free | Browser Extensions & Copilots | Open-source (MIT) sidebar and ChatGPT-style web UI for local models via Ollama, LM Studio or Chrome's built-in Gemini Nano |
| PandasAI | Free | AI Data Analysts | Open-source Python library: ask natural-language questions over dataframes/CSVs/warehouses |
| PaperQA2 | Free | Academic Research | RAG over PDFs with in-text citations grounded in passages |
| PentestGPT | Free | Security & IT Operations | Agentic framework automating penetration-testing and CTF tasks with LLMs |
| Perplexica | Free | AI Search & Answer Engines | MIT-licensed, fully self-hostable open-source Perplexity clone |
| pgvector | Free | Vector Databases & RAG Infra | Open-source vector similarity search extension for Postgres |
| Phi (Microsoft) | Free | Notable Open Models | MIT-licensed small language models for on-device and edge use |
| Pipecat | Free | Real-Time Voice Agents | BSD-2-Clause open-source Python framework for real-time voice/multimodal agents |
| Piper TTS | Free | AI Voice & Speech | Fast, fully offline neural TTS for many languages and voices |
| Playwright MCP | Free | Browser & Computer-Use Agents | Official Microsoft MCP server exposing Playwright browser control to any MCP client |
| Pleias | Free | Notable Open Models | Fully open-weight, open-dataset small language models (350M-3B) explicitly built for EU AI Act compliance |
| PR-Agent | Free | AI Code Review | Open-source AI reviewer that describes, reviews and suggests improvements on pull requests |
| Pydantic AI | Free | Agent Frameworks (Developers) | Type-safe Python agent framework from the Pydantic team, validated structured outputs |
| Qwen Code | Free | Terminal & CLI Agents | Open-source terminal CLI adapted from Gemini CLI, tuned for Qwen3-Coder models |
| Qwen-Agent | Free | Agent Frameworks (Developers) | Agent framework built on Qwen 3+ with function calling, MCP and code interpreter |
| Qwen3-TTS | Free | AI Voice & Speech | Alibaba Qwen open TTS family with voice cloning and text-described voice design |
| rembg | Free | AI Image Editing & Enhancement | MIT-licensed CLI, Python library and HTTP server for automatic background removal |
| Resume Matcher | Free | Career & Job Search | Runs locally to tailor a resume and cover letter to a job description |
| RVC (Retrieval-based Voice Conversion) | Free | AI Voice & Speech | Train a voice-conversion model on 10 minutes or less of audio and convert speech or singing |
| SANA (NVIDIA) | Free | AI Image Generation | Apache-2.0 linear-diffusion family for text-to-image up to 4K, with SANA-Sprint one-step generation |
| Sarvam Indus | Free | General Purpose Chatbots | Free (beta) chat assistant natively handling all 22 official Indian languages plus Hinglish code-switching |
| Sarvam Open Models (30B / 105B) | Free | Notable Open Models | Sarvam-105B and Sarvam-30B open models built for Indian languages, with FP8 and GGUF builds |
| Semantic Kernel | Free | Agent Frameworks (Developers) | MIT SDK for integrating LLMs into C#, Python and Java apps |
| Sesame CSM | Free | AI Voice & Speech | Open Apache-2.0 conversational speech model generating context-aware, natural speech |
| SGLang | Free | Local LLM Runners | RadixAttention for automatic prefix-cache reuse across requests |
| SiYuan | Free | AI Note-Taking & Docs | Privacy-first, self-hostable knowledge workspace with block-level references |
| SkyReels V2 | Free | AI Video Generation | Open-source autoregressive diffusion-forcing model for long video (up to 60s) |
| smolagents | Free | Agent Frameworks (Developers) | Extremely minimal open-source library (~1,000 lines) from Hugging Face |
| Snapchat My AI | Free | General Purpose Chatbots | Free chatbot inside Snapchat for everyone since 2023 |
| SoulX-Podcast | Free | AI Voice & Speech | Generates multi-speaker podcast conversations up to 90+ minutes with stable voices |
| Spark-TTS | Free | AI Voice & Speech | LLM-based TTS with BiCodec single-stream tokens |
| Stable Audio Open | Free | AI Music & Audio | Open-weight text-to-audio model for sound effects, samples and short music clips |
| Stable Diffusion (Stability AI) | Free | AI Image Generation | Open-source, run locally for unlimited free use |
| Stagehand | Free | Browser & Computer-Use Agents | Open-source SDK adding act, extract and observe AI primitives on top of Playwright |
| Step1X-3D | Free | 3D & CAD Generation | Apache-2.0 two-stage geometry plus texture generator (1.3B and 3.5B models) for textured 3D assets |
| Step1X-Edit | Free | AI Image Editing & Enhancement | Apache-2.0 instruction-based image editing model from StepFun |
| SurfSense | Free | AI Note-Taking & Docs | Open-source NotebookLM-style research assistant over your own sources |
| SWE-agent | Free | Autonomous Coding Agents | Takes a GitHub issue and tries to fix it automatically with your LM of choice |
| Tabby | Free | Code Autocomplete & Assistants | Self-hosted AI coding assistant with completion and chat |
| TEN Framework | Free | Real-Time Voice Agents | Open-source framework for real-time conversational voice and multimodal agents |
| TimesFM (Google Research) | Free | Notable Open Models | Pretrained decoder-only foundation model for time-series forecasting |
| TradingAgents | Free | Finance & Accounting AI | Analyst, trader and risk agents debate market conditions |
| Trae Agent | Free | Terminal & CLI Agents | Open-source CLI agent for general software-engineering tasks |
| TRELLIS (Microsoft) | Free | 3D & CAD Generation | Open-weight model outputting radiance fields, 3D Gaussians AND meshes from one representation |
| TRELLIS.2 (Microsoft) | Free | 3D & CAD Generation | 4B-parameter MIT-licensed image-to-3D model producing PBR textured assets |
| TRL (Hugging Face) | Free | Fine-Tuning & Training Frameworks | Post-training library covering SFT, DPO, GRPO and reward modeling for open LLMs |
| txtai | Free | Vector Databases & RAG Infra | All-in-one embeddings database for semantic search, LLM orchestration and workflows |
| UI-TARS Desktop (ByteDance) | Free | Browser & Computer-Use Agents | Open-source multimodal agent stack that controls desktop and browser from screenshots |
| Ultimate Vocal Remover | Free | AI Music & Audio | Free desktop GUI bundling multiple separation models (MDX-Net, Demucs, VR) |
| Unsloth | Free | Fine-Tuning & Training Frameworks | Fine-tunes LLMs, diffusion, TTS and embedding models 2x faster with ~70% less VRAM than standard Hugging Face training |
| Upscayl | Free | AI Image Editing & Enhancement | Free open-source desktop app (Windows, macOS, Linux) using Real-ESRGAN on a Vulkan GPU |
| Vanna AI | Free | AI Database & SQL Copilots | Fully open-source text-to-SQL agent, self-hostable with no vendor lock-in |
| Vercel AI SDK | Free | Agent Frameworks (Developers) | TypeScript toolkit for streaming text, tool calls and agents across many model providers |
| Vibe | Free | Meeting Assistants & Transcription | Desktop app that transcribes audio and video offline using Whisper |
| VibeVoice (Microsoft) | Free | AI Voice & Speech | Open-source TTS generating up to 90 minutes of speech with up to 4 speakers |
| vLLM | Free | Local LLM Runners | PagedAttention memory management for high-throughput multi-request GPU serving |
| VoltAgent | Free | Agent Frameworks (Developers) | Open-source TypeScript agent framework with memory, tools and sub-agents |
| WeKnora (Tencent) | Free | AI Docs & Codebase Q&A | Turns raw documents into a queryable RAG knowledge base with agent mode |
| whisper.cpp | Free | Speech & Transcription Engines | C/C++ port of OpenAI Whisper running on CPU, Metal, Core ML, CUDA and Vulkan |
| WhisperX | Free | Speech & Transcription Engines | 70x real-time transcription speed via batched inference on top of Whisper |
| XiaoZhi AI | Free | Real-Time Voice Agents | Open-source ESP32 voice chatbot with wake word, Opus streaming and a display |
| YouTube Create | Free | Video Editing & Repurposing | Free mobile editor from YouTube with an 'Edit with AI' first-draft feature |
| Z-Image | Free | AI Image Generation | 6B-parameter Apache-2.0 model family: Z-Image, Z-Image-Turbo, editing variant |
| Zhipu AutoGLM | Free | General Autonomous Agents | Free foundation-agent system for autonomous GUI control (web + Android) |