Directory
AI coding and development covers assistants, code review tools, and machine learning projects aimed at developers. The topic mixes code completion services, agent frameworks, prompt and context templates, dataset tools, and research notebooks. They sit at different points in the workflow, so compare where each one fits: writing code, reviewing a change, or setting up a model to run yourself. Check the language and editor support, how the tool handles your code and where it sends it, and the licence attached to any generated output. Some entries are production products and others are experiments that may not run without setup.
Plandex is an open source AI coding agent built for large projects and real-world tasks. It includes smart context management for large codebases, configurable autonomy levels, and tools to support producing production-ready results.
Poirot is a native macOS companion app for Claude Code. Built with SwiftUI, it lets users browse sessions, explore diffs, and re-run commands. It also provides session analytics, usage limit gauges, conversation views, and search across sessions. The app requires no login and no analytics and works offline.
Prediction Guard is a self-hosted AI control plane described as enforcing NIST and OWASP-aligned runtime controls inside an organization's security boundary. It offers Agent Forge for creating interactive and autonomous agents, and an OpenAI, Anthropic and MCP compatible API. The site lists a Docker Verified Publisher agentic program entry and a verified Agent Control Kit on Docker Hub.
Build tool for data science pipelines.
Teaching page by John M. Zelle, Ph.D., for an introductory computer science textbook written in Python and published by Franklin, Beedle & Associates. It links edition-specific public resources for four editions and offers graphics.py, a simple graphics library released under the GPL for introducing object-oriented concepts. Instructor resources including problem solutions and exam questions are available from the publisher.
Qwen3-Coder is the code version of the Qwen3 large language model series from the Qwen team. It is offered in multiple sizes, including Qwen3-Coder-480B-A35B-Instruct, Qwen3-Coder-30B-A3B-Instruct and Qwen3-Coder-Next, and the repository supports platforms such as Qwen Code, CLINE and Claude Code.
Supports software work with AI-assisted coding, testing or application development.
ReviewCerberus is an AI-powered code review tool that analyzes git branch differences and generates review reports. It examines logic, security, performance and code quality, and supports AWS Bedrock and Anthropic API, according to the repository. A GitHub Action posts review comments on pull requests.
An AI-powered autonomous coding agent integrated directly into VS Code. opensource.
Rosebud AI is a game maker for creating playable games from AI prompts. Users describe an idea or choose a template, then build and deploy the game, with no coding required. The pricing page says a free start is followed by upgrades for more credits, private projects, commercial rights, code download and Windows export.
Zero-configuration MCP server that unifies multiple AI coding assistants (Claude Code, Cursor, Codex) through intelligent auto-discovery.
CodeFormer, developed by sczhou, is a robust open-source face restoration algorithm designed for restoring old photos and AI-generated faces. The associated web demo is intended for research purposes. It is available via the Replicate platform or for local deployment, runs on Nvidia L40S GPUs, and typically completes predictions in 3 seconds. The associated research was published at NeurIPS 2022.
Supports software work with AI-assisted coding, testing or application development.
Supports software work with AI-assisted coding, testing or application development.
Tabby is a self-hosted AI coding assistant presented as an open-source, on-premises alternative to GitHub Copilot. The project describes itself as self-contained, requiring no DBMS or cloud service, with an OpenAPI interface for integration with existing infrastructure such as cloud IDEs, and support for consumer-grade GPUs.
Tabnine is the AI code assistant that accelerates and simplifies software development while keeping your code private, secure, and compliant.
Your daily dose of AI research from AK.
Supports software work with AI-assisted coding, testing or application development.
Tura is an open-source agent runtime harness that turns a task into a runtime-managed command graph, avoiding repeated model round trips in a ReAct session. The documentation describes it as a terminal-native developer tool that turns intent into verified code changes, emphasizing reading the repository first, keeping an audit trail, and proving results.
A self-hosted copilot clone that uses the library behind llama.cpp to run the 6 billion parameter Salesforce Codegen model in 4 GB of RAM.
Supports software work with AI-assisted coding, testing or application development.
A plugin that rewrites AI-generated output to remove stock phrasing, sycophancy, hedging stacks and em-dash pileups while preserving code, URLs and headings. It is offered for Claude Code, Cursor, Windsurf, Codex, Cline, Copilot and Gemini.
Extension for Visual Studio Code - An open-source AI debugging agent.
WebscrapeAI is a no-code web data collection tool that automates gathering information from websites without requiring manual scraping or programming skills. It provides customizable, accurate, and fast data collection, with free trial access and paid monthly pricing plans available.
