AI Open Source

Signup

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

AI Open Source

Explore top-tier open-source AI tools, freely accessible and highly customizable. Leverage active communities, transparent development, and powerful algorithms to implement state-of-the-art solutions without licensing constraints.

Signup & Stay Updated on the latest AI Tools

AI Open Source

### AI Tools available

AlphaClaw Apex

AlphaClaw Apex centralizes AI analytics, automates workflows, and delivers concise insights to speed decisions and reduce operational costs.

AI Skills Manager

AI Skills Manager unifies skills across AI coding agents, lets you copy skills between agents and install from GitHub repos. Free for Windows - streamlines managing varied formats and folders.

Scheduled

Scheduled is an open-source AI agent inside Gmail: reads threads, checks your calendar, and drafts meeting replies in your voice for quick review (draft-only) or autonomous sending-no extra app or links.

Lore

Lore is a local, free, open-source memory assistant that answers questions from your notes and journals with one keystroke. 100% private, no cloud or API keys; fast local LLM search for researchers, devs, and thoughtful users.

Parallax

Parallax is a local AI coding agent that turns Linear or GitHub issues into task plans, waits for your approval, implements changes in isolated branches, and opens a reviewable PR so you keep control of planning and review.

Masko Code

Masko Code overlays animated mascots on macOS 14+ to supervise AI agent sessions: speech-bubble notifications, one-key approvals (⌘1), session jumps (⌘M) and quick shortcuts. 100% local, open-source (MIT), customizable mascots.

Google Workspace CLI

AI tool for Google Workspace CLI

OpenMolt

OpenMolt is an open-source Node.js framework for programmatic AI agents. Define agents in code with instructions and tools to gather data, call APIs, generate outputs and update systems.

Phi-4-reasoning-vision

Phi-4-reasoning-vision: a compact open-weight multimodal model using mid-fusion to combine rapid visual perception with deep chain-of-thought, enabling efficient computer-use agents and precise complex-math problem solving.

LTX Desktop

LTX Desktop is a free, open-source local video editor built on the LTX-2.3 engine, optimized for NVIDIA GPUs. Edit and render on-device with no cloud dependency or per-generation fees-keep your data local and workflows private.

Vet

Vet is a fast, local, open-source code-review tool from Imbue that verifies coding agents using conversation history, catching silent failures, unrun tests, logic errors, and missing edge-case handling in PRs.

Step 3.5 Flash

Step 3.5 Flash: 196B sparse MoE (11B active/token) delivering high-throughput coding (up to 350 tok/s), 74.4% SWE-bench, clean long-context handling and seamless OpenClaw/OpenRouter integration for reliable agentic workflows.

Context Gateway

Context Gateway is a context-compression proxy that reduces token costs, lowers latency, and improves model accuracy for agents (Claude Code, OpenClaw, Codex). Includes instant compaction, spend caps, Slack alerts; core code open source.

Personal AI Memory

Personal AI Memory silently captures and indexes your chats locally - no servers or API keys - so you never lose context across LLMs or browsers. Import or export ChatGPT and Google Takeout data with one click.

DialogLab

DialogLab is an open-source framework to author, simulate, and test multi-party conversations with humans and AI. Use a visual scene builder, phase-based flow control, human-in-the-loop testing and verification dashboard.

OpenObserve

OpenObserve: a cloud-native observability platform (Rust) that unifies logs, metrics and traces in one high-performance, stateless engine. Store petabytes on S3/MinIO/GCS and query everything with SQL while keeping infrastructure minimal.

Springfield Oracle

Springfield Oracle is a free, open-source database that verifies viral Simpsons clips and claims. Every entry is sourced to original episodes, checked against real events, and open to community submissions.

PromptURLs

Type a prompt once to generate pre-filled, shareable links for ChatGPT, Claude, Gemini, Perplexity, Grok and more. Compare outputs instantly, save to Notion, build a one-click prompt library. Free, browser-only, no sign-up, open source.

IronClaw

IronClaw isolates and protects API keys while proxying AI requests, preventing key leaks and providing secure, drop-in integration with OpenAI-compatible services.

Claudebin

Easily share Claude conversations. Claudebin captures prompts, responses, and edits for seamless collaboration and review of your AI sessions. Open source.

Mengram

Mengram - open-source memory API capturing semantic, episodic and procedural memories. When an AI completes a task, Mengram saves the steps as reusable procedures so agents recall optimal workflows. Free; 60-sec setup.

Kollect Voice Agent

Kollect Voice Agent converts static forms into real-time AI conversations: speak answers, the AI listens and guides the survey, and you can generate forms by describing them. Open-source and feedback welcome.

Baseline Core

Baseline Core: free open-source skills system that wires your business context into any AI tool. Run a command, answer a few questions, and AI agents produce product work-research, PRDs, sprints, user flows, design, prototypes.

ClawMetry for OpenClaw

ClawMetry for OpenClaw: real-time observability-inspect sub-agent activity, files, commands, tool calls, thoughts, session timelines and per-session cost. Open-source; pip install clawmetry.

claude-devtools

claude-devtools reconstructs Claude Code sessions from local logs: shows file reads with syntax highlighting, inline diffs, tool calls and per-turn context breakdown. Open-source, local-only, zero network calls.

MiniMax-M2.5

MiniMax-M2.5: an open coding model with SOTA SWE-Bench 80.2%-the first open model to beat Sonnet; only Anthropic's Opus and OpenAI's GPT-5.2 Codex score higher. Try it free for a week on Kilo Code (offer ends Feb 19).

OpenBug

OpenBug is an open-source CLI+GUI AI that diagnoses bugs by reading logs and code, generates code diffs to fix issues, saves fixes as runbooks in Git, and runs in your terminal with no SDK or config.

Atomic Bot

Atomic Bot gets you from download to a running OpenClaw agent on your Mac in ~60 seconds-local execution keeps your workspace private and setup is simple so you can focus on tasks, not configuration.

TexTab

TexTab: Select text, hit a shortcut, get AI responses without opening a browser. Open source, BYO API keys (OpenAI, Anthropic, Gemini, OpenRouter), no subscriptions - you own your data and control costs.

claw.fm

claw.fm lets autonomous AI agents produce and sell music on Base. Use the built-in CLI or connect music APIs; earn USDC tips and sales (75% to agent, 20% royalty pool, 5% platform). Open-source-one skill file to start.

ClawApp

ClawApp - an open-source desktop app that makes OpenClaw easy to install, configure, and run locally. No toolchains or deep systems knowledge required; get a guided local AI agent up and running in minutes.

Agentset

Agentset - open-source RAG that runs in production out of the box. Scales to millions of docs with agentic reasoning, hybrid search+reranking, automatic citations and multimodal support.

Moltbot

Moltbot is a self-hosted AI agent that runs locally, connects LLMs to your OS, performs real actions (browse, fill forms, run commands, edit files), keeps memory, and integrates with messaging apps-private, extensible, runs on Mac/Win/Linux.

Doclific

Doclific consolidates scattered internal docs, KT notes, diagrams and Google Docs into one searchable, free knowledge base-easy to maintain so teams keep documentation current and accessible. Brutally honest: Yes - I would use it if it reliably c...

Mastra

Mastra (YC W25) v1.0: a developer-first framework for building AI apps and agents-SDKs, agent orchestration, and production-ready tooling. Trusted by 300k+ weekly npm users and 19.4k+ GitHub stars.

FastMCP 3.0

FastMCP 3.0 is a durable, future-proof platform for Context Applications that delivers the right information to agents. Source components, compose and transform data, personalize views, track session state, control access, run background tasks.

Preloop

Preloop enforces pre-execution human approval for AI agents - approve code deployments, refunds, or data changes from phone, Slack, or Teams. MCP-native proxy that adds approval gates to existing automations.

Edit Mind

Edit Mind transcribes and indexes videos using multimodal embeddings and frame analysis, plus a chat assistant for fast image and text search, retrieval, and context-aware video exploration.

Coderrr

Coderrr: open-source, CLI-first AI coding partner in your terminal. Read and modify your codebase, generate or refactor code, explain bugs, and automate common dev tasks without a heavy IDE.

flins

flins - a CLI that treats agent skills as dependencies. Like npm for AI agents, it lets teams add, update and manage skills across agents to keep setups consistent and shareable.

Translator

Translator: private, open-source video translation with a two-pass workflow (GPT-5.1 then Claude Opus 4.5) for natural, edited subtitles. Free video download and subtitle editing; pay only for AI features or bring your own API keys.

Sled

Sled provides a secure voice interface to your local coding agent: speak from your phone, the agent runs on your computer and reports what it did. Code stays on-device via Tailscale. Open-source; set up in about five minutes.

1Code

1Code runs and manages multiple AI coding agents-launch Claude Code in remote sandboxes, run QA and bug-finder agents, debug and test code via API. Open-source core with paid tiers.

Design in Figma using Cursor Agent + MCP

Use Cursor Agent + MCP to control Figma via natural language-bulk-edit text, update components, create frames, annotations and exports. Open-source, deploy in 5 minutes and free to run.

Awesome Gemini Prompts

Awesome Gemini Prompts: a curated library of cleaned, community-sourced Gemini prompts-well formatted and LLM-refined so you can reuse top prompts and get better results faster.

NexTalk

NexTalk is an open-source Linux voice input tool offering 100% offline privacy, sub-20ms latency, a minimalist capsule UI, and Fcitx5/Wayland integration for fast, reliable dictation.

youtube-mcp-server

youtube-mcp-server: an MCP server for YouTube metadata extraction and multilingual, GPU-accelerated transcriptions using in-memory processing, Silero VAD, yt-dlp integration, translation and file caching for fast, scalable agent access.

Chatterbox Turbo

Chatterbox Turbo: 350M open-source TTS with paralinguistic tags (laughs, sighs), zero-shot voice cloning, runs 6x real-time, and built-in PerTh watermarking for safe, fast, expressive speech synthesis.

Molmo 2

Molmo 2 is an open-weights vision-language suite that analyzes videos and multiple images at once, with open training data and code for transparent model development and customization.

Plannotator

Plannotator is a local Claude Code plug-in (via hooks) to review, annotate and share plans with teammates. Runs locally with no backend; shared links embed compressed content and annotations. Source code on GitHub.

CrowdSynthetic

CrowdSynthetic predicts crowd congestion, creates heatmaps, scores real-time risk, and triggers evacuation logic - an open-source, local simulator that runs without cloud to help organizers spot hazards before they form.

Alpie Core

Alpie Core is a 32B reasoning model trained and served at 4-bit, offering multi-step reasoning, coding, and analytic performance with a 65K context. OpenAI‑compatible, Apache‑2.0 open source, and optimized to run on lower-end GPUs.

GetProfile

GetProfile: self-hosted, open-source user profiles and long-term memory for AI agents. Extracts natural-language summaries, typed traits with confidence scores, and prioritized memories into your PostgreSQL database.

Grov

Grov syncs AI learnings with your Git codebase, capturing architecture decisions and the "why" from chats and repos. It cuts redundant agent exploration, saves tokens, and helps teams ship faster.

MiMo-V2-Flash

MiMo-V2-Flash (309B MoE, 15B active) is an ultra-fast, efficient foundation LLM by Xiaomi, optimized for advanced reasoning, coding, and agentic workflows and ideal as a general-purpose assistant.

Agent Starter Pack

Agent Starter Pack: one command to scaffold a production-ready agent (ADK or LangGraph) with Terraform infra, CI/CD (Cloud Build or GitHub Actions), OpenTelemetry tracing, session management and evaluation tooling in 60 seconds.

Vectorly

Vectorly records web interactions, reverse-engineers APIs and compiles dependable scripted flows via CDP and LLMs, providing programmatic access to web apps through reusable, open-source automation.

xPrivo

xPrivo keeps AI chats private by storing conversations locally or running an assistant entirely on your device. Open-source; use anonymous web access if needed. Funded by non-personal ads or optional PRO upgrades.

Peargent

Peargent uses AI to summarize documents, answer questions, and extract key insights from your files, streamlining workflows and speeding decision-making.

Proofly

Proofly is a privacy-first, open-source writing assistant that runs entirely in Chrome using on-device AI (Gemini Nano). No accounts, telemetry, or servers-works offline after model download and provides lightweight, noninvasive proofreading.

Papr

Papr unifies RAG + memory in one API, structuring context into a vector index and knowledge graph queryable via GraphQL or natural language, reduces hallucinations, delivers 91%+ STaRK accuracy and <100ms latency for private multi-tenant agents.

Agenta

Agenta is an open-source platform for AI teams to ship reliable LLM apps: collaborate on prompts, deploy changes without code, run test cases, and monitor production errors, feedback and costs.

Container Diet

Container Diet inspects local Docker images with GPT-4o, identifies bloat and security risks, and provides clear, actionable fixes with a slightly cheeky persona. Fix oversized layers, exposed secrets and root/777 issues-no push needed.

Layrr

Layrr is a browser coding agent that lets you visually edit live code-drag, resize, and reposition elements, edit text, and convert Figma designs to React, Vue, Svelte or plain HTML in your project.

agor

Agor: real-time collaboration with instant cursor sync, mobile agent prompting, built-in scheduler, MCP-backed self-aware agents, session trees on canvas, and shared dev environment management.

Everywhere

Everywhere brings an AI assistant into your OS - it sees your screen and helps in-place so you don't switch apps or copy text. Lightweight, privacy-aware, and community-built to streamline everyday tasks.

Packmind Open Source

Packmind Open Source manages Context Engineering: versioning, distributing, and enforcing organizational coding standards across repos and AI coding assistants, keeping AI-generated code consistent and compliant.

MCP Playground

MCP Playground - web app to connect to any MCP server with zero setup. Inspect and run exposed tools, resources and prompts interactively, view request/response logs, and test securely (OAuth, AES-256-GCM). Open source (MIT).

mTarsier

mTarsier - free, open-source desktop app that auto-detects AI clients (Claude Desktop, Cursor, Windsurf, VS Code) and centralizes MCP server configs, marketplace installs, and one-click backups on macOS, Windows, Linux.

BlogBowl

BlogBowl: Launch an open-source, plug-and-play blog with AI-assisted writing, built-in technical SEO, a Notion-style editor, and subscriber/newsletter management - go live in minutes with no coding.

Secure MCP Framework by Arcade.dev

Secure MCP Framework by Arcade.dev simplifies secure deployment of MCP servers with built-in delegated access and secret management, removing auth barriers for production hosting.

Usage4Claude

Usage4Claude displays your Claude usage quota in the Mac menu bar with color alerts, adaptive refresh, and Keychain‑encrypted local storage. Free, open-source, lightweight Swift app to avoid unexpected usage limits.

Parallax by Gradient

Parallax by Gradient: a free framework that serves LLMs across multiple devices-combining laptops, servers, and teammates' machines to scale private, local inference. Distributes model serving regardless of hardware or location.

Metorial

Metorial is an open-source MCP-powered platform to build AI agents with 600+ integrations in hours. It automates OAuth, monitoring and deployment. Python & TypeScript SDKs; self-hostable.

nanochat

nanochat: a ~1,000-line full-stack LLM (Python/Rust/HTML/Shell). Run tokenization, pretraining, finetuning, evaluation, inference and a web UI on one 8×H100 node for under $1,000-learn LLM internals by building.

Strix

Strix is an open-source AI penetration-testing agent that finds and validates vulnerabilities, produces PoCs and compliance-ready reports to accelerate security testing.

VibeSDK by CloudFlare

VibeSDK by CloudFlare: open-source full-stack AI coding platform-one-click Cloudflare deployment with AI code generation, isolated sandboxes, previews, GitHub export, observability and multi-model support for safe, scalable app building.

Nexa SDK

Nexa SDK is an on-device AI toolkit for developers to run LLaMA, Qwen, Gemma, Parakeet and Stable Diffusion locally with CPU, GPU (CUDA/Metal/Vulkan) and NPU acceleration for fast, private inference.

Sentient Chat

Sentient Chat: part of GRID. Aggregates 100+ partner data, agents and models to provide concise, accurate answers. Fully open-source platform with shareable Spaces that compress complex workflows into a single side pane.

tambo

Tambo turns natural-language input into React UIs: register components once, connect APIs/MCPs, and let Tambo render interactive UI flows so users act instead of read, speeding development and improving feature discovery.

ROMA

ROMA is an open-source framework for creating customizable multi-agent AI systems. It supports any model and data source, enabling development of versatile agents like task solvers, research assistants, and finance advisors for specialized applica...

Solid

Solid is a production-ready AI development platform offering full control with React, Node.js, and Postgres. Build scalable, extendable apps without backend limits or vendor lock-in. Own your code and deploy anywhere with a free, open stack.

Onyx

Onyx is a secure chat-based GenAI hub that links your team's data, LLMs and web research so you can ask context-aware questions, analyze CSVs, extract action items from Slack/Drive, and automate routine tasks.

AbleMouse AI edition

AbleMouse AI edition controls the cursor by pointing your nose - open-source AI that moves the pointer to any screen spot naturally and reduces eye strain. Sub-products and compatibility info on the project site.

AgentSea

AgentSea offers a secure AI chat platform with access to the latest models, community-built agents, and integrated search and image tools—all while protecting your data with Secure Mode that ensures privacy using open-source or in-house hosted mod...

Onlook for Web

Onlook for Web is an open source visual builder that streamlines design-to-development handoffs by creating production-ready apps directly from code, ensuring zero translation errors and seamless collaboration across product teams.

Giselle

Giselle is an open-source visual node editor for AI workflows, enabling you to mix models from multiple providers, monitor execution in real time, and run pipelines without infrastructure setup.

Grok 2.5 (OSS Ver.)

Grok 2.5 (OSS Ver.) is an open-source AI model offering advanced language understanding and generation capabilities, enabling developers to build intelligent applications with a proven, reliable foundation from xAI’s top-performing model.

GraphBit

GraphBit: build production-ready AI agents with Rust speed and safety and Python-friendly bindings. Enterprise features include real-time observability, crash resilience, and multi-LLM orchestration for reliable, scalable deployments.

Disco.dev

Disco.dev is a personal MCP hub that simplifies AI agent tool integration with zero-setup servers, open-source connectors, and customizable, remixable servers—making it easy to discover, run, and tailor AI automations without infrastructure hassles.

Ito

Ito is a free, open-source Mac app that converts your voice into polished text across any application. Capture ideas, transcribe meetings, or write hands-free with accurate speech recognition and instant formatting, boosting productivity and creat...

Basedash Self-Hosted

Basedash Self-Hosted lets you run Basedash on your own infrastructure for full control and security. Deploy easily with a one-line agent, Docker, Kubernetes, or air-gapped setups, ensuring flexible and secure database management.

Omnara

Omnara lets you manage AI agents on the go with real-time alerts, one-tap approvals, and a full mobile interface. Compatible with Claude Code, n8n, and custom agents, it keeps your AI workflows moving without being tied to your desk.

Chord Mini

Chord Mini is an open-source tool that detects chords and beats in music tracks, providing accurate analysis to support music projects and research. Future updates will integrate additional models for enhanced music analysis capabilities.

TensorZero

TensorZero is an open-source LLM infrastructure offering a unified API for multiple providers, real-time observability, optimization through feedback, evaluation tools, and built-in experimentation to streamline industrial-grade large language mod...

Private Mind

Private Mind is a free, open-source app that runs AI locally on your device, ensuring complete privacy, fast responses without internet, and full control over your data. Experience powerful AI without compromising security or speed.

Hunyuan-GameCraft

Hunyuan-GameCraft lets you control and direct detailed game scenes from a single image using keyboard inputs, ensuring long-term consistency. Its open-weight, quantized model runs efficiently on consumer GPUs like the 4090 for accessible interacti...

Compozy

Compozy simplifies multi-agent AI orchestration with declarative YAML workflows, offering reliable, production-ready management without vendor lock-in. Built for speed and flexibility, it reduces dev time and supports seamless, language-agnostic A...

SelfHostLLM

SelfHostLLM simplifies planning for self-hosted AI by accurately estimating GPU needs and concurrency for models like Llama, Qwen, and Mistral. Now available for Mac, it supports custom configurations including Apple Silicon deployments.

mcp-use

mcp-use is an open-source SDK that helps development teams build, deploy, and manage custom AI agents with MCP servers efficiently, addressing configuration, authentication, access control, and observability challenges in a unified platform.

.

As seen on