coding assistant
What is agentic engineering? - Agentic Engineering Patterns
Verified Spec-Driven Development. GitHub Gist: instantly share code, notes, and snippets.
LoKI is a local AI assistant for Linux and WSL that allows running LLM models locally. Supports HF and GGUF models, MCP tools, model quantization and Hugging Face integration.
First open-source code agent for Lean 4.
I realised that many companies offer no-code platforms to their users for automating workflows. The... Tagged with webdev, programming, javascript, ai.
AI-powered CLI for background agents. Contribute to rowboatlabs/rowboat development by creating an account on GitHub.
Connect AI agents to GitHub tools and context with OAuth, one-click setup, and automatic updates with GitHub’s hosted server.
We’ll decode these two tools—and show you how to use them both to work more efficiently.
Customize and extend Claude Code's behavior by registering shell commands
Global Claude Code commands and workflows. Contribute to badlogic/claude-commands development by creating an account on GitHub.
Kata Code for agentic developers, Kata Agents for knowledge workers, and Kata Symphony for issue-to-PR orchestration.
A full look at agent mode in GitHub Copilot, including what it can do, when to use it, and best practices.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server. - chopratejas/headroom
The research-plan-implement workflow I use to build software with Claude Code, and why I never let it write code until I've approved a written plan.
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman - JuliusBrussee/caveman
A completely private and local AI coding assistant, developed by Gensyn. It helps you practice programming problems and train a novel assistant to help you code. - gensyn-ai/codeassist
Fully open-source command-line AI assistant inspired by OpenAI Codex, supporting local language models. - codingmoh/open-codex
A lot of people seem convinced that the point of AI coding is to write low-quality code as fast as possible. Spew out barely-passable slop, open massive PRs, and merge them unvetted. Ship it! But the thing is, LLMs are very flexible. And you can use them just as effectively to write high-quality code more…
AI can produce work that looks expert without being expert. The failure arrives in two shapes, and both are reshaping the workplace.