Open Source AI Coding Tools - Page 10
Sort By:
AI Coding Tools
View 319 business solutions-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
1
Claude of Death is a desktop coding assistant with GUI powered by the Anthropic Claude API. Users supply their own API key — all billing is handled directly with Anthropic. 4-24-26: Just added memory to it, like Claude Code. Also improved the save function. 4-25-26: Fixed save function for Macs. 4-28-26: Added Save Code as File, in addition to already present Generate File. 5-9-26: Renamed from Code of Death to Claude of Death.
-
2
Code World Model (CWM)
Research code artifacts for Code World Model (CWM)
CWM (Code World Model) is a 32-billion-parameter open-weights language model. It is developed by Meta for enhancing code generation and reasoning about programs. It is explicitly trained on execution traces, action-observation trajectories, and agentic interactions in controlled environments. It has been developed to better capture how code, actions, and state interact over time. The repository provides inference code, reproducibility scripts, prompt guides, and more. It has model cards, utilities, demos, and evaluation artifacts. Inference scripts and utilities for code generation tasks. Evaluation benchmarks on code, mathematics, and reasoning tasks. Demos, serving code, and evaluation pipelines. -
3
Codeball AI
AI Code Review that finds bugs and fast-tracks your code
Codeball is a code review AI that scores pull requests on a grade from 0 (needs careful review) to 1. Use Codeball to add labels to help you focus, auto-approve PRs, and more. The Codeball action is easy to use (sane defaults) and is highly customizable to fit your workflow when needed. Label PRs when you should review them with caution. Stay sharp, don't let the bugs pass through. Identifies and approves or labels safe PRs. Save time by fast-tracking PRs that are easy to review. Fully customizable and programmable with GitHub Actions. Codeball Actions are built on multiple smaller building blocks, that are heavily configurable through GitHub Actions. Codeball uses a deep learning model that has been trained on over 1 million Pull Requests. For each contribution, it considers hundreds of inputs. Codeball is optimized for precision, which means it only approves contributions that it's really confident in. -
4
Codeflash
Optimize your code automatically with AI
Codeflash is a general-purpose optimizer for Python that uses advanced large language models (LLMs) to automatically generate, test, and benchmark multiple optimization ideas, then creates merge-ready pull requests with the best improvements for your code. Optimize an entire existing codebase by running codeflash --all. Automate optimizing all future code you will write by installing Codeflash as a GitHub action. Optimize a Python workflow python myscript.py end-to-end by running codeflash optimize myscript.py. Optimizing the performance of new code for a Pull Request through GitHub Actions. This lets you ship code quickly while ensuring it remains performant. -
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
5
CodiumAI PR-Agent
AI-Powered tool for automated pull request analysis
CodiumAI PR-Agent is an open-source tool aiming to help developers review pull requests faster and more efficiently. It automatically analyzes the pull request and can provide several types of commands. See the Usage Guide for instructions how to run the different tools from CLI, online usage, Or by automatically triggering them when a new PR is opened. You can try GPT-4 powered PR-Agent, on your public GitHub repository, instantly. Just mention @CodiumAI-Agent and add the desired command in any PR comment. The agent will generate a response based on your command. -
6
Composer API
OpenAI-compatible API proxy for Cursor Composer
Composer API is an OpenAI-compatible API proxy for Cursor Composer. It is designed for developers who want to interact with Cursor’s Composer-style agent workflow through a familiar API surface. The project acts as a translation layer, letting compatible clients send requests in an OpenAI-like format while routing them toward the Composer backend behavior. This makes it useful for experimentation, automation, or tool integrations that already understand OpenAI-style chat completion patterns. Its scope appears focused and lightweight rather than being a broad AI gateway or multi-provider orchestration platform. Composer API is best suited for technical users who understand Cursor-related workflows and want a programmable bridge into that environment. -
7
Context Engineering Template
Context engineering is the new vibe coding
Context Engineering Template is a comprehensive template and workflow repository designed to teach and implement context engineering, a structured approach to preparing and organizing the information necessary for AI coding assistants to complete complex tasks reliably. Instead of relying solely on short prompts, this project encourages developers to create rich, structured context files that include project rules, examples, and validation criteria so that AI systems can act more like informed collaborators and less like general-purpose generators. The repository provides templates such as CLAUDE.md for defining global project rules, INITIAL.md for feature requests, and folders for examples, PRPs, validation scripts, and settings to support systematic prompt generation and execution with tools like Claude Code. By using this template, teams can ensure consistency across AI outputs, reduce errors that stem from contextual misunderstandings, and build reusable patterns. -
8
Context Hub
Makes coding agents get smarter with every task
Context Hub is a curated documentation system built to help coding agents write more accurate code. It gives agents versioned, language-specific reference material instead of forcing them to rely on noisy web searches or stale model memory. The project includes a CLI called chub that agents can use to search for available docs, fetch specific API guidance, and request only the files they need. It also supports local annotations, allowing an agent to remember project-specific notes, pitfalls, or workarounds across future sessions. Feedback can be sent back to maintainers so shared documentation improves over time. Context Hub is especially useful for teams that use AI coding assistants and want more reliable API usage, fewer hallucinated calls, and a transparent source of agent-readable context. -
9
Context Mode
Context window optimization for AI coding agents
Context Mode is a development approach and tooling concept that enhances how AI-assisted coding environments manage and inject context into language model interactions. It focuses on improving the relevance and accuracy of AI-generated outputs by controlling what information is provided to the model at each step. The project explores structured context management, enabling developers to define how files, code snippets, and metadata are included in prompts. It is particularly useful for large codebases, where naive context inclusion can lead to inefficiency or irrelevant outputs. The system encourages modular and selective context injection, improving both performance and cost efficiency. It also aligns with emerging patterns in AI-assisted development, where context orchestration becomes a critical component of productivity. Overall, context-mode represents a shift toward more intentional and structured interaction between developers and AI systems. -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
10
Copilot.vim
GitHub Copilot for Vim and Neovim
Copilot.vim is a plugin that integrates GitHub Copilot — the AI code completion tool from GitHub — with Vim and Neovim. It effectively brings inline AI-powered code suggestions into the editor: you type a comment or a function name (or simply start coding) and Copilot proposes completions which you can accept (often via Tab) or reject. The plugin supports a variety of languages and code contexts, just as Copilot itself does, and aims to make the interaction feel native in Vim. Installation is relatively straightforward using any plugin manager or manual git clone, and setup involves running :Copilot setup. You must have a valid Copilot subscription or access via enterprise for the service to work. In short, this plugin bridges Vim’s editing environment with the power of AI-driven code suggestion, reducing repetitive boilerplate and helping you code faster and smarter. -
11
Devgen
The AI codebase research assistant for Github
DevGen is a development tool that automates the creation of boilerplate code, providing templates and scaffolding for various programming languages and frameworks. -
12
Expect
Let agents test your code in a real browser
Expect is a developer-focused utility designed to simplify validation, testing, and assertion workflows across software environments by providing a clean and expressive interface for defining expected outcomes. The project likely centers on improving readability and maintainability in testing scenarios, allowing developers to write expectations in a concise and human-readable format. It may support chaining conditions, enabling complex validation logic without introducing unnecessary verbosity. The design suggests a focus on productivity, reducing cognitive load when writing and reviewing tests or validation scripts. It is likely adaptable across multiple contexts, including unit testing, integration testing, and runtime assertions. By abstracting repetitive validation logic, expect helps developers focus on behavior rather than implementation details. Overall, it serves as a lightweight but powerful tool for improving software reliability and clarity in testing workflows. -
13
GoDex
AI coding agent
GoDex is a developer-focused tool designed to enhance code exploration and understanding through AI-assisted workflows. It provides an interface that allows users to analyze codebases, generate insights, and interact with code using natural language queries. The system is built to improve productivity by reducing the time required to understand complex projects or unfamiliar code structures. It integrates with language models to provide contextual explanations, summaries, and suggestions. Godex emphasizes usability, offering a streamlined interface that fits into existing development environments. It also supports extensibility, allowing developers to adapt the tool to their specific workflows. Overall, Godex serves as an intelligent assistant for navigating and understanding codebases more efficiently. -
14
Grida Assistant
Bring your Figma design & development pipeline to the next level
Bring your Figma design & development pipeline to the next level - with design-to-code, in-design-content-management, component management, and tools for faster design. -
15
Grok of Death is a desktop coding assistant with GUI powered by the Grok API. Users supply their own API key — all billing is handled directly with xAI.
-
16
Habit Tracker
Habit Tracker for the AI Coding Workshop
Habit Tracker is a personal habit-tracking web application designed to help users build and maintain daily habits through intuitive UI and analytics that visualize progress over time. It runs locally with a FastAPI backend (Python) and a React frontend, storing all data in a lightweight SQLite database so there’s no need for user accounts or cloud storage, which keeps habit data fully private and self-contained. The app provides streak tracking and completion rates for each habit, giving users feedback on consistency and motivation by showing how often habits are completed and where they may be lagging. A calendar view lets users see a monthly grid of their habit history with color-coded days to highlight patterns and encourage daily engagement. Habit-Tracker also supports planned absences so users can skip days without breaking their streaks, reducing frustration and keeping long-term habits on track. -
17
Kimi K2.7 Code
Coding-focused Kimi model for long-horizon agent workflows
Kimi K2.7 Code is a coding-focused agentic model built on Kimi K2.6, designed for long-horizon software engineering, autonomous coding workflows, and complex tool-based execution. It improves end-to-end task completion across real-world programming scenarios while reducing thinking-token usage by about 30% compared with K2.6. Architecturally, it uses a 1T-parameter Mixture-of-Experts design with 32B activated parameters, 61 layers, 384 experts, a 256K-token context window, and a MoonViT vision encoder. The model supports image and video input, native INT4 quantization, interleaved thinking, and multi-step tool calling. It also forces preserve-thinking mode by default, retaining full reasoning context across multi-turn interactions to improve coding-agent consistency. K2.7 Code is recommended for use through Kimi Code CLI and can be deployed with vLLM, SGLang, or KTransformers. -
18
Leanstral
Open-source code agent designed for Lean 4
Leanstral is an open-weight large language model developed by Mistral AI and specifically designed as a code agent for the Lean 4 proof assistant, enabling advanced interaction with formal mathematics and program verification systems. The model is built to understand and generate Lean 4 code, which is used to express complex mathematical constructs as well as formal software specifications. By focusing on theorem proving and formal reasoning, Leanstral represents a specialized direction within large language models, targeting domains that require strict correctness and logical rigor rather than general conversational tasks. It leverages modern large-scale architectures, likely incorporating mixture-of-experts techniques, to balance efficiency and capability while handling structured symbolic reasoning tasks. The model can assist in writing proofs, exploring mathematical structures, and validating logical properties in code. -
19
LongCat-2.0
Trillion-parameter MoE model for coding and million-token reasoning
LongCat-2.0 is Meituan’s flagship open-weight Mixture-of-Experts language model designed for frontier-scale coding, reasoning, and autonomous agent workflows. It features 1.6 trillion total parameters with approximately 48 billion activated per token, combining high capability with efficient sparse inference. The model was pretrained on more than 35 trillion tokens and trained entirely on a large-scale cluster of domestically developed AI accelerators, demonstrating stable frontier-scale training without rollback events. LongCat-2.0 introduces LongCat Sparse Attention and extensive 1M-context training, enabling native processing of million-token inputs for long-document analysis, repository-scale coding, and complex multi-step reasoning. Dedicated post-training further strengthens coding and agent performance, producing competitive benchmark results against leading proprietary models. -
20
Luna Code Checker
An advanced web-based tool for checking JavaScript code using ESLint.
Luna Code Checker An advanced web-based tool for checking JavaScript code using ESLint. How to Use Clone the repository. Run npm install to install the dependencies. Run npm start to start the server. Open http://localhost:3000 in your web browser. Write or paste your JavaScript code in the textarea. Click the "Check Code" button to see linting results. Features Comprehensive syntax and style checking using ESLint. Detailed error messages including line numbers and descriptions. License This project is open source and available under the MIT License. -
21
Markdown Viewer Agent Skills
Opinionated skills for AI coding agents to create stunning diagrams
Markdown Viewer Agent Skills is a repository that provides a collection of modular AI “skills” designed to extend the capabilities of agents or tools that operate on markdown-based workflows. These skills are typically structured as self-contained instruction sets that define how an AI should perform specific tasks, such as formatting, analysis, or content transformation. The project emphasizes simplicity and composability, allowing developers to integrate these skills into existing systems without requiring complex infrastructure. Each skill is designed to be reusable and adaptable, making it easy to customize behavior for different use cases. The repository aligns with the broader concept of agent skills, where capabilities are encapsulated into modular units that can be dynamically loaded and executed. It supports workflows that rely heavily on markdown as a primary medium for content and communication. -
22
MathCode
A Frontier Mathematical Coding Agent
MathCode is a terminal-based AI coding assistant focused on mathematical formalization and theorem proving. It is designed to transform plain-language mathematical reasoning into verified Lean 4 code and formal proofs. The project combines AI agents with Lean Language Server Protocol integration, allowing it to inspect compiler feedback, search for lemmas, and iteratively repair failed proof attempts. It supports an agentic proving workflow where the system behaves more like an interactive mathematical engineer than a one-shot text generator. MathCode also includes visualization-oriented tooling such as theorem graph generation for Obsidian knowledge workflows. Its main value is bridging natural-language mathematics with formal verification systems in a way that is more automated, inspectable, and iterative than traditional theorem-proving pipelines. -
23
MiniMax-M2
MiniMax-M2, a model built for Max coding & agentic workflows
MiniMax-M2 is an open-weight large language model designed specifically for high-end coding and agentic workflows while staying compact and efficient. It uses a Mixture-of-Experts (MoE) architecture with 230 billion total parameters but only 10 billion activated per token, giving it the behavior of a very large model at a fraction of the runtime cost. The model is tuned for end-to-end developer flows such as multi-file edits, compile–run–fix loops, and test-validated repairs across real repositories and diverse programming languages. It is also optimized for multi-step agent tasks, planning and executing long toolchains that span shell commands, browsers, retrieval systems, and code runners. Benchmarks show that it achieves highly competitive scores on a wide range of intelligence and agent benchmarks, including SWE-Bench variants, Terminal-Bench, BrowseComp, GAIA, and several long-context reasoning suites. -
24
OpenTag
Open-source @agent mentions for Slack and GitHub
OpenTag is a local-first coordination layer that turns workplace mentions into governed coding-agent runs. It connects collaboration platforms such as Slack, GitHub, GitLab, Linear, Telegram, Discord, Microsoft Teams, and Lark or Feishu to local executors. Each request becomes a bounded context packet whose permissions and executor capabilities are checked before work begins. Codex, Claude Code, or another compatible agent performs the task and returns concise results to the original thread. Action receipts show proposed changes and expose an Apply option only when an approved adapter can safely perform them. A local work ledger records the source event, admission decision, context, capabilities, artifacts, callbacks, and final outcome. The CLI supports guided setup, diagnostics, terminal operation, and background services on macOS and Linux. -
25
Ornith-1.0
Open reasoning model for agentic coding and tool workflows
Ornith-1.0 is a large open-source reasoning model from DeepReinforce, built for agentic coding, tool use, and complex software engineering workflows. It is part of the Ornith 1.0 family, which includes dense and MoE models post-trained on Gemma 4 and Qwen 3.5. The model focuses on coding-agent performance across benchmarks such as Terminal-Bench, SWE-Bench, NL2Repo, OpenClaw, and ClawEval. Its training uses a self-improving reinforcement learning framework that optimizes not only solution attempts but also the scaffolds that guide those attempts, helping the model discover better search paths and produce higher-quality solutions. Ornith-1.0-397B is a reasoning model by default, generating <think> blocks before final answers, and supports tool calling through OpenAI-compatible endpoints. It can be deployed with vLLM, SGLang, Transformers, Docker, and compatible quantized local apps, and is released under the MIT license.
