Open Source AI Development Apps

A Microsoft-built training framework that optimizes AI agents with reinforcement learning, automatic prompt optimization, or supervised fine-tuning — with near-zero code changes to your existing agent, in any framework.

The open-source LLMOps platform unifying prompt engineering, evaluation, and observability for teams building reliable LLM applications.

An open source AI-native proxy that secures, observes, and governs agent-to-LLM, agent-to-tool, and agent-to-agent communication through MCP, A2A, and unified LLM routing.

Build, run, and manage agent platforms with a full production stack — SDK, runtime, and control plane included.

An all-in-one open-source training suite for finetuning diffusion models—FLUX, SDXL, Wan video, and audio—on consumer GPU hardware via CLI or web UI.

Collaborate on high-quality AI training data with a self-hosted annotation platform built for LLMs, NLP, and multimodal models.

Give your LLM agents on-the-job training—ART lets you apply GRPO reinforcement learning to any multi-step agentic workflow with minimal code changes.

Build autonomous and human-in-the-loop multi-agent AI systems with a layered, event-driven Python and .NET framework pioneered at Microsoft Research.

Give an AI agent a real LLM training setup and let it experiment autonomously overnight — you wake up to a log of experiments and (hopefully) a better model.

Run AI workloads at scale with a Pythonic serverless runtime that handles GPU inference, background jobs, and sandboxes with zero infrastructure overhead.

The open-source hub for building and deploying LLM-powered AI agents with TypeScript-first tooling, 40+ integrations, and a revolutionary code-execution agent framework.

Open-core workflow engine for building AI-powered automations in TypeScript that run natively inside Slack — no context switching required.

Give your AI coding agents persistent memory — claude-mem captures everything that happens during sessions, compresses it with AI, and surfaces the right context in every future session automatically.

A native, Ghostty-based macOS terminal with vertical tabs, agent-aware notifications, and a scriptable browser built for running many parallel AI coding agent sessions instead of juggling tmux panes.

An incremental data indexing engine that keeps AI agent context perpetually fresh by reprocessing only what changed.

An open-source CLI that packages machine learning models into standard, production-ready Docker containers — no Dockerfile wrangling, no CUDA version hell.

The most powerful node-based AI workflow engine for creating images, video, 3D models, and audio with full control over every generation step.

Open-source coding agent for VS Code, JetBrains, and CLI with support for 30+ LLM providers.

The batteries-included Python agent harness — planning, sub-agents, filesystem, shell, memory, and skills bundled in, built on LangGraph.

Visual LLM workflow platform with RAG pipelines, agent capabilities, and model management for building production AI applications.

Build AI-powered apps locally with your own keys, your own models, and zero cloud lock-in.

Build, debug, and deploy knowledge-based AI agents with a visual workflow editor, RAG retrieval, and support for any OpenAI-compatible LLM.

Turn any website into clean, LLM-ready data with a single API call — no proxy headaches, no scraping complexity.

Drag-and-drop visual builder for AI agents, RAG pipelines, and multi-agent systems—deploy anywhere in minutes.

An Apple-Silicon-native LoRA fine-tuning tool for Gemma on text, image, and audio data — with a wizard CLI, live browser-based training visualizer, and streaming from GCS/BigQuery for datasets too large for local disk.

Git, but better — a modern version control client with stacked branches, parallel workflows, unlimited undo, and first-class support for AI-powered development.

Turn any GitHub repository into an interactive architecture diagram in seconds

Run large language models privately on your laptop — no GPU, no cloud, no data leaving your device.

A Postgres-backed orchestration engine for background tasks, AI agents, and durable workflows that replaces Redis queues and multi-datastore durable execution platforms with a single self-hostable service.

Compress everything your AI agent reads — tool outputs, logs, RAG chunks, and files — before it reaches the LLM, achieving 60–95% fewer tokens with the same answers.

An open-source AI gateway and LLM observability platform that routes requests to 100+ models while logging cost, latency, and full traces for every call.

Build and run agentic workflows across channels with YAML, tools, and RAG

Turn plain HTML and CSS into deterministic, pixel-perfect MP4 videos — authored by humans or AI agents, rendered by headless Chrome and FFmpeg.

Self-hosted, open-source email API that automates DNS, manages SMTP delivery, and provides deep observability — replacing SES, Mailgun, and SendGrid with infrastructure you fully own.

Transform messy, unstructured documents into persistent, navigable memory that AI agents can actually use.

ktx builds a self-improving context layer over your data warehouse so AI agents like Claude Code and Codex query it with approved metric definitions instead of reinventing SQL logic from scratch.

Label Studio is an open-source, multi-type data labeling platform that lets teams annotate images, text, audio, video, and time series data with a configurable XML-based UI and export annotations in formats ready for any ML framework.

Open-source observability platform purpose-built for AI agents — trace, evaluate, debug, and monitor at scale with SQL access and real-time replay.

Open-source, embedded vector database built on the Lance columnar format for fast multimodal search across billions of vectors, backed by Y Combinator (W23).

Build, test, and deploy AI agents and RAG workflows visually with native API and MCP server export.

Open source AI engineering platform for LLM observability, prompt management, evaluation, and debugging — self-host in minutes or use Langfuse Cloud.

Open-source AI-powered platform that generates and deploys full-stack web applications from natural language prompts, built natively for Cloudflare Workers.

Open source AI gateway and Python SDK that gives you one OpenAI-compatible interface to call 100+ LLM providers, with built-in routing, cost tracking, guardrails, and virtual keys.

Generate multi-file web apps from a single prompt using open-source LLMs — an open-source alternative to Claude Artifacts.

One API endpoint for 25+ LLM providers — route, track costs, enforce compliance, and switch models without changing your code.

A fully local web research assistant that iteratively searches, summarizes, and refines markdown reports using any Ollama or LMStudio model—no cloud or API keys required.

Build enterprise-grade AI agents with RAG, workflows & multi-modal support

High-performance in-memory graph database for AI context and real-time analytics

Local-first AI memory with verbatim storage, pluggable backends, and 96.6% retrieval recall on LongMemEval — no API key required.

The open source operating system and SDK that lets developers build one app and run it across smart glasses from Even Realities, Vuzix, Mentra Live, and more.

A universal swarm intelligence engine that spawns thousands of autonomous AI agents to simulate and predict how real-world events unfold across social, financial, and political domains.

The open source AI engineering platform for debugging, evaluating, monitoring, and optimizing production LLMs and agents at scale.

A local-first AI memory sidecar that extracts entities, builds a persistent knowledge graph, and injects ranked context into any LLM pipeline — no cloud required.

Run LLM-generated Python code safely inside your agent—no containers, no CPython, no compromise—with sub-microsecond startup.

Morphik is an AI-native ingestion and retrieval engine that lets developers store, search, and reason over visually rich documents — scanned PDFs, manuals, slides, and video — without duct-taping together OCR, an embedding model, and a vector database.

Turn coding agents into real teammates — assign issues, track progress, and compound reusable skills across a vendor-neutral, self-hosted platform.

Build and deploy an open-source analytics agent that understands your data warehouse and answers business questions in plain English.

Run AI coding agents like OpenClaw and Hermes securely inside NVIDIA OpenShell sandboxes with a hardened blueprint, routed inference, and lifecycle management through a single CLI.

A single graph+vector+temporal database for AI workloads — Neo4j-compatible, sub-millisecond hybrid search, and built-in memory decay.

Turn AI-written code into real apps — an open-source, self-hostable backend with Database, Auth, Storage, Memory, Functions, Assets, AI Gateway, and cron built for AI coding agents.

Run Llama, Gemma, DeepSeek, and other open LLMs on your own machine with one command and an OpenAI-compatible API.

An open-source AI app builder that scrapes a live website and recreates it as a modern React app through chat — built by Firecrawl as a self-hostable example of the Lovable.dev workflow.

The self-hosted developer control center for running AI coding agents — locally, in Docker, on VMs, or across cloud backends — with automation workflows for GitHub, Slack, and more.

An open-source context database that gives AI agents a unified filesystem for memory, resources, and skills with hierarchical tiered retrieval.

An open-source build system that turns written specs and architecture into working code — an LLM generates code under tight constraints, task by task with narrow context windows, instead of attempting an entire codebase at once.

Open-source LLMOps platform for prompt management, AI observability, intelligent caching, and real-time cost tracking across LLM providers.

Run ML training and LLM inference natively inside PostgreSQL with GPU acceleration — no data movement required.

The open-source API layer that turns local LLMs into production private AI applications with full Claude API compatibility

An open-source CLI and library for evaluating and red-teaming LLM applications — replace trial-and-error prompt engineering with systematic evals, vulnerability scanning, and CI/CD integration.

Open-source vector database and search engine built in Rust for production-grade AI applications — from semantic search to RAG pipelines and recommendation systems.

Rasa Open Source is a Python machine learning framework for building contextual, multi-turn chatbots and voice assistants that understand natural language and maintain conversation state.

Build deterministic, versioned agent skills from natural language—run them anywhere from Claude Code to Slack.

Build, test, and deploy multi-agent AI workflows with a visual editor, RAG data sources, MCP tool integration, and a production-ready REST API.

Drop your files and search them instantly — no vector DB, no indexing pipeline, just raw data queried by a self-evolving intelligence layer.

The state-of-the-art memory and context engine for AI agents — ranked #1 on all three major AI memory benchmarks.

Orchestrate an army of AI coding agents—Claude Code, Codex, Gemini CLI, and more—running simultaneously in isolated git worktrees from a single Electron desktop app.

Symphony turns your issue tracker into an autonomous implementation engine—spawning isolated coding agents per ticket so your team manages work, not agents.

An open-source visual canvas for building AI workflows by connecting nodes across 35+ model providers with drag-and-drop simplicity.

AI-Native Distributed SQL Database for Agentic Workloads

A pretrained decoder-only foundation model by Google Research that delivers zero-shot time series forecasting with calibrated quantile prediction intervals — no training required.

All-in-one self-hostable platform for hybrid search, RAG, recommendations, and analytics built on Rust and Qdrant.

Build and deploy fully-managed AI agents and background jobs in TypeScript — with no timeouts, durable retries, real-time observability, and elastic scaling built in.

Build sophisticated chatbots visually, embed them anywhere without iframes, and own your data — fully self-hostable with a modular block system and 30+ integrations.

Baidu's open-source OCR model for "one-shot, long-horizon parsing" — published with an arXiv paper, a Hugging Face model release, and vLLM inference support, aimed at document understanding beyond typical page-by-page OCR limits.

Clone voices, dictate anywhere, and give AI agents your voice — all locally.

An open-source TypeScript framework for Electron apps that ship raw, uncompiled source, hot-reload instantly, and let users hack and extend running code via plugins.