OPEN SOURCE
150 items
123 posts, 27 tools
Open-source Firebase alternative built on Postgres. Auth, real-time subscriptions, storage, edge functions, and pgvector for AI embeddings. Generous free tier.
NVIDIA Nemotron 3 Super combines latent mixture of experts with hybrid Mamba layers - 120B total parameters, 12B active per token, 1M context and open weights.
NVIDIA Nemotron Nano 9B V2 is a hybrid Mamba-transformer small model that runs on consumer GPUs. See how its reasoning controls, open data and tool use work.
GPT-OSS is OpenAI's pair of open-weight 20B and 120B reasoning models under Apache 2.0. Hardware needs, benchmarks, hosting costs and how to run them locally.
Qwen 3 is Alibaba's family of eight Apache 2 licensed models, led by a 235B MoE flagship. How it compares to Llama 4, how hybrid thinking works, how to run it.
Unstract is an open-source, no-code platform that uses LLMs to extract structured JSON from PDFs, invoices and scans. How Prompt Studio and self-hosting work.
Google's open-source (Apache 2.0) terminal agent for Gemini models. Paid Gemini API, Vertex AI, and existing Code Assist Standard or Enterprise subscribers keep access (Google stopped selling new Code Assist subscriptions on October 9, 2026); unpaid tier and Google One users moved to Antigravity CLI on June 18, 2026.
Open-source AI pair programming in your terminal. Works with any LLM - Claude, GPT, Gemini, local models. Git-aware editing with automatic commits.
Open-source AI code assistant for VS Code and JetBrains. Bring your own model - local or API. Tab autocomplete, chat, inline edit. Fully customizable.
TypeScript-first AI agent framework. Agents, tools, memory, workflows, RAG, evals, tracing, MCP, and production deployment for Node.js apps.

Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.