Explore our latest articles and technical deep dives.
Sourcegraph's AI code assistant with deep codebase context — understanding your entire repository for context-aware code generation and answers.
A VS Code and JetBrains extension providing code completion, chat, and agent capabilities with support for any LLM backend.
A self-hostable VS Code extension with FIM ghost-text autocomplete for 6 languages and RAG-based context retrieval — fully free with no API keys required.
Open Interpreter lets LLMs run code to control your computer — Python, JavaScript, and Shell for file operations, web browsing, and data analysis.
OpenAI's open-source Symphony framework that monitors Linear boards, spawns autonomous coding agents, and delivers proof-of-work — without a single GPU.
A fully local terminal coding agent with bundled llama.cpp inference — no cloud dependency, no per-token billing, and as little as 12GB VRAM required.
An open-source alternative to Cursor — a VS Code fork with a deeply integrated AI agent where the loop, diff, and indexing engine communicate via gRPC.
Princeton's autonomous software engineering agent for real GitHub issues — SWE-agent achieves 12.5% on SWE-bench by treating repos as interactive environments.
A self-hosted AI coding assistant with no database, no cloud, and no API keys — Tabby provides code completion for 15+ languages with a consumer-grade GPU.