Open Source AI Development Apps

Mesh LLM pools GPUs and memory across every machine you own into one OpenAI-compatible API, so agents tap distributed compute instead of a single GPU box or a metered cloud bill.

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

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

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

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.

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.

A pure-C, zero-dependency inference engine that runs GLM-5.2's 744-billion-parameter mixture-of-experts model on consumer hardware with roughly 25GB of RAM by streaming experts from disk like a JIT compiler stages hot code.

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

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

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

An open-source, plugin-based agent harness from DeepSeek AI that runs coding and automation agents across web, desktop, CLI, and SDK surfaces.

An Apache-incubated agent workspace that treats every model call, tool run, and permission decision as an append-only, replayable event log instead of disposable chat history.

A self-hosted, OpenAI-compatible LLM gateway that puts one endpoint in front of 40+ providers, with virtual API keys, per-user budgets enforced before spend, and full usage tracking.

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

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.