Weights you can download, runtimes you can install and frameworks you can read — for privacy, cost control, or just not wanting a dependency on someone's API.
Flocci AI Tools lists 143 of them, ordered free tiers first: AFFiNE, DeepSeek Models, ERNIE 4.5 Open Models (Baidu), Falcon (TII) and HuggingChat. 141 of the 143 are free or have a free tier. Each entry states what it uniquely does rather than a score.
120 on this page are marked fully free with no paid plan at all: AFFiNE, DeepSeek Models, ERNIE 4.5 Open Models (Baidu), Falcon (TII) and HuggingChat. The remaining 23 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, DeepSeek Models, ERNIE 4.5 Open Models (Baidu), Falcon (TII) and HuggingChat all work in a browser tab with no install needed — just open the site and go. 37 of the 141 free Open-Source & Locally-Run AI Tools listed here are browser-based.
AFFiNE, Kimi, Qwen (Alibaba), Qwen Chat and Cloudflare Agents SDK support Google sign-in, so you can start without creating a new account. That's 7 of the 141 free Open-Source & Locally-Run AI Tools on this page.
AFFiNE, DeepSeek Models, Kimi, Microsoft Translator and Qwen (Alibaba) have an iOS or Android app. 23 of the 141 free Open-Source & Locally-Run AI Tools here can run on your phone.
ACE-Step, AgenticSeek, Agno, Aider and Anarlog (Hyprnote) can be self-hosted or run locally without a browser — useful for privacy, air-gapped networks, or avoiding API rate limits. 85 of the 141 free Open-Source & Locally-Run 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 |
| DeepSeek Models | Free | Notable Open Models | DeepSeek V4-Pro and V4-Flash open-weight MoE models, MIT-licensed |
| 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 |
| 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 |
| Kimi | Free | General Purpose Chatbots | Free access to Moonshot's Kimi K3 and K2-series agentic models |
| Kortix (Suna) | Free | General Autonomous Agents | Open-source agent platform (formerly Suna) that runs specialist agents on isolated cloud computers |
| LibreTranslate | Free | Translation & Language AI | Self-hostable open-source machine translation API and web UI |
| Microsoft Translator | Free | Translation & Language AI | Free app and web translator for text, speech, images and multi-person live conversations |
| 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 |
| 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 |
| 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 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 |
| OpenHands | Free | Autonomous Coding Agents | Self-hosted control center for coding agents with GUI, CLI and SDK surfaces |
| 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 |
| Riffusion | Free | AI Music & Audio | Riffusion's Producer was acquired by Google and now continues as Flow Music |
| Seed-OSS (ByteDance) | Free | Notable Open Models | Seed-OSS-36B open reasoning LLM with native 512K-token context, Apache 2.0 |
| sherpa-onnx | Free | Speech & Transcription Engines | Offline speech-to-text, text-to-speech, VAD and speaker diarization without internet |
| Step (StepFun) | Free | Notable Open Models | Step-3.7-Flash open multimodal model with FP8, NVFP4 and GGUF builds |
| Xiaomi MiMo | Free | Notable Open Models | MiMo-V2.6-Pro (1T parameters) and V2.6-Flash (311B) open-weight reasoning and agent models |
| Youdao Translate | Free | Translation & Language AI | NetEase Youdao's free translator for Chinese, English and 100+ languages |
| ACE-Step | Free | AI Music & Audio | Open-weight (Apache-2.0) music foundation model that generates full songs with vocals from text and lyrics |
| Agent Zero | Free | General Autonomous Agents | Agent framework that gives the agent a full Linux desktop and browser to work in |
| 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 |
| Aider | Free | Terminal & CLI Agents | Open-source AI pair programmer in your terminal |
| 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 |
| AWS Strands Agents | Free | Agent Frameworks (Developers) | Open-source (6,800+ stars) Python and TypeScript SDK from AWS |
| Basic Memory | Free | Agent Memory & RAG-as-a-Service | MCP server that stores AI conversation memory as local Markdown notes |
| BitNet | Free | Local LLM Runners | Official inference framework for 1-bit (ternary) LLMs |
| CAMEL | Free | Agent Frameworks (Developers) | Open-source multi-agent framework focused on scaling agent societies and role-playing |
| 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 |
| Cloudflare Agents SDK | Free | Agent Frameworks (Developers) | Framework for building and deploying stateful AI agents on Cloudflare Workers |
| ComfyUI | Free | AI Image Generation | Node-graph interface for building image, video, audio and 3D generation workflows without code |
| 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 |
| 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 |
| faster-whisper | Free | Speech & Transcription Engines | Whisper reimplementation on CTranslate2, up to 4x faster with less memory |
| Firebase Genkit | Free | Agent Frameworks (Developers) | Open-source framework for AI apps in JavaScript, Go, Dart and Python |
| 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 |
| FunASR | Free | Speech & Transcription Engines | Open-source speech recognition toolkit with Paraformer and SenseVoice models |
| Gemma (Google) | Free | Notable Open Models | Google's lightweight open models (Gemma 4) |
| 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 |
| GPT-OSS (OpenAI) | Free | Notable Open Models | OpenAI's Apache-2.0 open-weight reasoning models (120B and 20B) |
| GPT4All | Free | Local LLM Runners | Private local chat with your documents |
| 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 |
| 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 |
| IBM Granite | Free | Notable Open Models | Apache 2.0 licensed enterprise-grade model family |
| 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 |
| Kimi K3 (Moonshot AI) | Free | Notable Open Models | Open-weight multimodal MoE with about 2.8T total and 104B active parameters, 1M-token context |
| KoboldCpp | Free | Local LLM Runners | Ships as a single portable executable with a bundled web UI (KoboldAI Lite) |
| 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 |
| 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 |
| LTX-2 (Lightricks) | Free | AI Video Generation | Open DiT audio-video model generating synchronized sound and video in one pass |
| Mastra | Free | Agent Frameworks (Developers) | Open-source TypeScript framework (Apache 2.0) for agents, workflows and RAG |
| 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 |
| 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 |
| 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 |
| Moonshine | Free | Speech & Transcription Engines | Small streaming speech-recognition models for phones, browsers and low-power devices |
| 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 |
| Ollama | Free | Local LLM Runners | The default way to run LLMs locally |
| Open Interpreter | Free | General Autonomous Agents | Lets an LLM run code locally to do tasks on your computer, in a terminal chat |
| Open WebUI | Free | Local LLM Runners | Self-hosted ChatGPT-style interface |
| 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 |
| OpenManus | Free | General Autonomous Agents | Open-source general agent framework built as a free alternative to Manus |
| OpenSandbox (Alibaba) | Free | Agent Frameworks (Developers) | Secure, fast runtime for executing untrusted AI-generated code |
| OpenWhispr | Free | Voice Dictation & Speech-to-Text | Voice-to-text dictation with local Parakeet or Whisper, or cloud models |
| 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 |
| Perplexica | Free | AI Search & Answer Engines | MIT-licensed, fully self-hostable open-source Perplexity clone |
| Phi (Microsoft) | Free | Notable Open Models | MIT-licensed small language models for on-device and edge use |
| Piper TTS | Free | AI Voice & Speech | Fast, fully offline neural TTS for many languages and voices |
| Pleias | Free | Notable Open Models | Fully open-weight, open-dataset small language models (350M-3B) explicitly built for EU AI Act compliance |
| Pydantic AI | Free | Agent Frameworks (Developers) | Type-safe Python agent framework from the Pydantic team, validated structured outputs |
| Qwen-Agent | Free | Agent Frameworks (Developers) | Agent framework built on Qwen 3+ with function calling, MCP and code interpreter |
| 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 |
| SGLang | Free | Local LLM Runners | RadixAttention for automatic prefix-cache reuse across requests |
| smolagents | Free | Agent Frameworks (Developers) | Extremely minimal open-source library (~1,000 lines) from Hugging Face |
| Stable Diffusion (Stability AI) | Free | AI Image Generation | Open-source, run locally for unlimited free use |
| Tabby | Free | Code Autocomplete & Assistants | Self-hosted AI coding assistant with completion and chat |
| TimesFM (Google Research) | Free | Notable Open Models | Pretrained decoder-only foundation model for time-series forecasting |
| 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 |
| 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 |
| 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 |
| 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 |
| AppFlowy | Freemium | AI Note-Taking & Docs | Open-source AI workspace for docs, wikis and project boards |
| AssemblyAI | Freemium | Speech & Transcription Engines | Speech-to-text with audio intelligence |
| Deepgram | Freemium | Speech & Transcription Engines | Fast, accurate speech-to-text API |
| DeepSeek | Freemium | General Purpose Chatbots | Free web and app chat on DeepSeek's V4-series models |
| ElevenLabs Scribe | Freemium | Speech & Transcription Engines | Scribe v2 Realtime transcribes in under 150ms latency |
| FLUX (Black Forest Labs) | Freemium | AI Image Generation | Open-weight models you can run locally for free |
| GLM (Z.ai) | Freemium | Notable Open Models | GLM-5.x flagship and Flash models released as open weights on Hugging Face |
| Mistral Voxtral | Freemium | Speech & Transcription Engines | Apache 2.0 open-weight models (24B and 3B) downloadable from Hugging Face |
| n8n | Freemium | Workflow Automation | Open-source, self-hostable automation |
| Soniox | Freemium | Speech & Transcription Engines | Real-time speech-to-text priced well under typical competitor rates |
| Speechmatics | Freemium | Speech & Transcription Engines | Free starting credit with no card required, 56+ language support |
| Anytype | Freemium | AI Note-Taking & Docs | Local-first, end-to-end encrypted workspace built around typed objects |
| CrewAI | Freemium | Agent Frameworks (Developers) | Role-based multi-agent 'crews' |
| Dyad | Freemium | App Builders & Vibe Coding | Fully open-source, runs locally on your machine with offline capability |
| LlamaIndex | Freemium | Agent Frameworks (Developers) | Leading framework for RAG and data agents |
| Meetily | Freemium | Meeting Assistants & Transcription | Fully local real-time transcription with Whisper or Parakeet |
| Mistral OCR 4 | Freemium | AI OCR & Document Extraction | Self-hostable single-container OCR model for regulated industries |
| Msty | Freemium | Local LLM Runners | Nexus module: unified gateway for managing model connections, credentials and usage policy across providers |
| Obsidian | Freemium | AI Note-Taking & Docs | Local-first markdown knowledge base |
| Tabnine | Freemium | Code Autocomplete & Assistants | Privacy-first completions (can run air-gapped) |
| VoiceInk | Freemium | Voice Dictation & Speech-to-Text | Offline dictation app for Mac using local Whisper models |
| Lokalise | Paid | Translation & Language AI | Context-aware AI translation with multi-LLM smart routing across providers |
| Claude Cowork | Paid | General Autonomous Agents | Runs in the Claude desktop app (Mac/Windows) |