# Open-Source & Locally-Run AI Tools

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.

## Stats

- 143 tools listed
- 141 free or freemium
- 120 with no paid plan at all
- 29 sub-categories covered

## FAQ

### What are the best free Open-Source & Locally-Run AI Tools?

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.

### Which of these are completely free?

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.

### How is this list ordered?

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.

## Quick picks

### Which Open-Source & Locally-Run AI Tools work in a browser with no install?

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.

### Which Open-Source & Locally-Run AI Tools let you sign in with Google?

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.

### Which Open-Source & Locally-Run AI Tools have a mobile app?

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.

### Which Open-Source & Locally-Run AI Tools can you self-host or run offline?

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.

## Tools

- [AFFiNE](https://aitools.flocci.in/tool/affine) — Free — Open-source workspace that merges docs, whiteboards and databases
- [DeepSeek Models](https://aitools.flocci.in/tool/deepseek-models) — Free — DeepSeek V4-Pro and V4-Flash open-weight MoE models, MIT-licensed
- [ERNIE 4.5 Open Models (Baidu)](https://aitools.flocci.in/tool/ernie-4-5-open-models-baidu) — Free — ERNIE-4.5 family including 21B-A3B Thinking and VL-424B-A47B multimodal MoE
- [Falcon (TII)](https://aitools.flocci.in/tool/falcon-tii) — Free — Falcon-H1 hybrid Transformer-Mamba family for efficient long-context inference
- [HuggingChat](https://aitools.flocci.in/tool/huggingchat) — Free — Completely free and open-source
- [Hunyuan (Tencent)](https://aitools.flocci.in/tool/hunyuan-tencent) — Free — Open-weight Hunyuan Hy3 and Hy4-preview flagship text models
- [Kimi](https://aitools.flocci.in/tool/kimi) — Free — Free access to Moonshot's Kimi K3 and K2-series agentic models
- [Kortix (Suna)](https://aitools.flocci.in/tool/kortix-suna) — Free — Open-source agent platform (formerly Suna) that runs specialist agents on isolated cloud computers
- [LibreTranslate](https://aitools.flocci.in/tool/libretranslate) — Free — Self-hostable open-source machine translation API and web UI
- [Microsoft Translator](https://aitools.flocci.in/tool/microsoft-translator) — Free — Free app and web translator for text, speech, images and multi-person live conversations
- [MiniMax M2 (open weights)](https://aitools.flocci.in/tool/minimax-m2-open-weights) — Free — 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)](https://aitools.flocci.in/tool/mistral-open-models-magistral-devstral-voxtral) — Free — Open-weight Mistral Medium 3.5, Small 4 and Large 3 general models
- [Morphic](https://aitools.flocci.in/tool/morphic) — Free — Open-source, Apache 2.0, self-hostable generative-UI search engine
- [NVIDIA Canary-Qwen 2.5B](https://aitools.flocci.in/tool/nvidia-canary-qwen-2-5b) — Free — Speech-recognition plus LLM hybrid model that transcribes and can summarize or answer questions about audio
- [NVIDIA Parakeet](https://aitools.flocci.in/tool/nvidia-parakeet) — Free — Tops the Hugging Face Open ASR Leaderboard with 6.05% average WER at 0.6B params
- [OLMo (Ai2)](https://aitools.flocci.in/tool/olmo-ai2) — Free — Only major model family shipping full pretraining data (Dolma), code and intermediate checkpoints, not just weights
- [OpenHands](https://aitools.flocci.in/tool/openhands) — Free — Self-hosted control center for coding agents with GUI, CLI and SDK surfaces
- [Presenton](https://aitools.flocci.in/tool/presenton) — Free — Open-source (Apache-2.0) AI presentation generator with desktop app and Docker deployment
- [Qwen (Alibaba)](https://aitools.flocci.in/tool/qwen-alibaba) — Free — Open Qwen3.x family from phone-sized to multi-trillion-parameter MoE, Apache 2.0
- [Qwen Chat](https://aitools.flocci.in/tool/qwen-chat) — Free — Free access to Alibaba's latest Qwen3.x models, including the Max tier
- [Riffusion](https://aitools.flocci.in/tool/riffusion) — Free — Riffusion's Producer was acquired by Google and now continues as Flow Music
- [Seed-OSS (ByteDance)](https://aitools.flocci.in/tool/seed-oss-bytedance) — Free — Seed-OSS-36B open reasoning LLM with native 512K-token context, Apache 2.0
- [sherpa-onnx](https://aitools.flocci.in/tool/sherpa-onnx) — Free — Offline speech-to-text, text-to-speech, VAD and speaker diarization without internet
- [Step (StepFun)](https://aitools.flocci.in/tool/step-stepfun) — Free — Step-3.7-Flash open multimodal model with FP8, NVFP4 and GGUF builds
- [Xiaomi MiMo](https://aitools.flocci.in/tool/xiaomi-mimo) — Free — MiMo-V2.6-Pro (1T parameters) and V2.6-Flash (311B) open-weight reasoning and agent models
- [Youdao Translate](https://aitools.flocci.in/tool/youdao-translate) — Free — NetEase Youdao's free translator for Chinese, English and 100+ languages
- [ACE-Step](https://aitools.flocci.in/tool/ace-step) — Free — Open-weight (Apache-2.0) music foundation model that generates full songs with vocals from text and lyrics
- [Agent Zero](https://aitools.flocci.in/tool/agent-zero) — Free — Agent framework that gives the agent a full Linux desktop and browser to work in
- [AgenticSeek](https://aitools.flocci.in/tool/agenticseek) — Free — Fully local autonomous agent that browses, codes and plans without cloud APIs
- [Agno](https://aitools.flocci.in/tool/agno) — Free — Open-source (Apache-2.0) Python framework, 41.7k GitHub stars
- [Aider](https://aitools.flocci.in/tool/aider) — Free — Open-source AI pair programmer in your terminal
- [Anarlog (Hyprnote)](https://aitools.flocci.in/tool/anarlog-hyprnote) — Free — On-device meeting transcription and AI summaries without a bot joining the call
- [AnythingLLM](https://aitools.flocci.in/tool/anythingllm) — Free — All-in-one local RAG and agents app
- [Argos Translate](https://aitools.flocci.in/tool/argos-translate) — Free — Offline open-source translation library and GUI using OpenNMT models
- [AWS Strands Agents](https://aitools.flocci.in/tool/aws-strands-agents) — Free — Open-source (6,800+ stars) Python and TypeScript SDK from AWS
- [Basic Memory](https://aitools.flocci.in/tool/basic-memory) — Free — MCP server that stores AI conversation memory as local Markdown notes
- [BitNet](https://aitools.flocci.in/tool/bitnet) — Free — Official inference framework for 1-bit (ternary) LLMs
- [CAMEL](https://aitools.flocci.in/tool/camel) — Free — Open-source multi-agent framework focused on scaling agent societies and role-playing
- [Claude Agent SDK](https://aitools.flocci.in/tool/claude-agent-sdk) — Free — MIT-licensed Python and TypeScript SDKs exposing the agent loop that powers Claude Code
- [Cline](https://aitools.flocci.in/tool/cline) — Free — Open-source autonomous coding agent for VS Code
- [Cloudflare Agents SDK](https://aitools.flocci.in/tool/cloudflare-agents-sdk) — Free — Framework for building and deploying stateful AI agents on Cloudflare Workers
- [ComfyUI](https://aitools.flocci.in/tool/comfyui) — Free — Node-graph interface for building image, video, audio and 3D generation workflows without code
- [DSPy](https://aitools.flocci.in/tool/dspy) — Free — Open-source (MIT) framework from Stanford NLP, 37k+ GitHub stars
- [EleutherAI LM Evaluation Harness](https://aitools.flocci.in/tool/eleutherai-lm-evaluation-harness) — Free — Standard open framework for running hundreds of benchmarks (MMLU, GSM8K and more) against any LLM
- [EXAONE (LG AI Research)](https://aitools.flocci.in/tool/exaone-lg-ai-research) — Free — EXAONE 4.5: LG's first open-weight vision-language model for industrial use cases
- [exo](https://aitools.flocci.in/tool/exo) — Free — Links everyday devices (Macs, PCs, phones) into one cluster to run models too large for a single machine
- [faster-whisper](https://aitools.flocci.in/tool/faster-whisper) — Free — Whisper reimplementation on CTranslate2, up to 4x faster with less memory
- [Firebase Genkit](https://aitools.flocci.in/tool/firebase-genkit) — Free — Open-source framework for AI apps in JavaScript, Go, Dart and Python
- [FLUX.2 [klein]](https://aitools.flocci.in/tool/flux-2-klein) — Free — 4B-parameter Apache-2.0 FLUX.2 variant for text-to-image and editing, released Jan 2026
- [Fooocus](https://aitools.flocci.in/tool/fooocus) — Free — Midjourney-like prompt-only UI on top of SDXL with built-in prompt expansion
- ... and 93 more — see the full list on the page.
---

Source: Flocci AI Tools — https://aitools.flocci.in/best/open-source-and-local-ai-tools

Facts last verified: October 2026