Open Source Windows AI Coding Agents - Page 2
Sort By:
AI Coding Agents for Windows
View 104 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.
-
Error to trace to log to deploy. One click. No SSH.AppSignal links every error to the trace, the trace to the log, the log to the deploy that shipped it.
-
1
Kimchi
Terminal coding agent powered by Kimchi's multi-model orchestration
Kimchi is a terminal coding agent powered by multi-model orchestration. It is designed to help developers run AI-assisted coding sessions from the command line while coordinating specialized agents, tools, permissions, and project context. The repository includes systems for subagents, task classification, model delegation, MCP integration, web search, web fetching, Language Server Protocol support, authentication, and interactive terminal workflows. It also supports ACP-style JSON-RPC integration for editor workflows and remote session multiplexing through its teleport mode. Kimchi includes benchmarking tools for smoke testing sessions, auditing completed work, and comparing model behavior across predefined tasks. It is useful for developers who want a powerful terminal-first coding agent with structured orchestration rather than a simple chat wrapper. -
2
MiniMax-M2.1
MiniMax M2.1, a SOTA model for real-world dev & agents.
MiniMax-M2.1 is an open-source, state-of-the-art agentic language model released to democratize high-performance AI capabilities. It goes beyond a simple parameter upgrade, delivering major gains in coding, tool use, instruction following, and long-horizon planning. The model is designed to be transparent, controllable, and accessible, enabling developers to build autonomous systems without relying on closed platforms. MiniMax-M2.1 excels in real-world software engineering tasks, including multilingual development and complex workflow automation. It demonstrates strong generalization across agent frameworks and consistently improves upon its predecessor, MiniMax-M2. Benchmarks show that it rivals or approaches top proprietary models while remaining fully open for local deployment and customization. -
3
SmallCode
AI coding agent optimized for small LLMs. 87% benchmark
SmallCode is a terminal-native AI coding agent optimized for local models running on consumer hardware. It is designed to extract useful coding performance from smaller LLMs, especially models in the 7B to 20B range. The project focuses on making local coding assistance practical without requiring massive cloud-hosted models for every task. Its workflow is built around terminal usage, which makes it suitable for developers who prefer command-line control and local project context. smallcode emphasizes efficient agent behavior, careful tool use, and benchmark-driven improvements for constrained models. Its main value is giving developers a compact coding-agent environment that treats small local models as first-class tools. -
4
Aden Hive
Outcome driven agent development framework that evolves
Hive is an open-source agent development framework that helps developers build autonomous, reliable, self-improving AI agents by letting them describe goals in ordinary natural language instead of hand-coding detailed workflows. Rather than manually defining execution graphs, Hive’s coding agent generates the agent graph, connection code, and test cases based on your high-level objectives, enabling outcome-driven agent creation that fits real business processes. Once deployed, agents can capture failure data, evolve automatically to meet their success criteria, and redeploy without constant manual intervention, delivering continual improvement over time. The framework also includes human-in-the-loop nodes, credential management, cost and budget controls, and real-time observability so teams can monitor execution and intervene as needed. Hive is designed for production environments and supports a wide range of large language models, local models, and business system connectivity. -
$300 Free Credits to Build on Google CloudStart your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query petabytes in BigQuery, or build agents with Gemini Enterprise Agent Platform. Once your credits are used, keep building with 20+ always-free tier products including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. No commitment required—just sign up and start building.
-
5
claurst
Your favorite Terminal Coding Agent, now in Rust
claurst is an experimental AI agent framework that appears to focus on structured reasoning and task execution within coding or automation environments. The project likely explores how agents can be designed to handle complex workflows through modular components and clearly defined execution steps. It may include abstractions for managing context, decision-making, and interaction with external tools, enabling agents to perform multi-step tasks efficiently. The architecture suggests a focus on flexibility, allowing developers to adapt the system to different use cases or domains. It is likely intended as a lightweight but extensible platform for experimenting with agent behavior and orchestration. The project may also emphasize simplicity, making it accessible for developers who want to prototype agent systems quickly. -
6
Ditto
The simplest self-building coding agent
Ditto is a simple self-building coding agent that generates multi-file Flask applications from natural language descriptions. Users describe the app they want, and the system attempts to plan and create routes, templates, static assets, and supporting files. It uses an LLM loop with basic tools to automate part of the coding process. The project is intentionally lightweight and experimental, making it easier to understand than larger agentic coding platforms. Its modular structure separates generated Flask components into cleaner directories for routes, templates, and static files. It is best suited for prototyping, learning, and exploring how natural-language app generation can work in a small local project. -
7
Gemma Chat
Local AI chat + coding agent for Apple Silicon, powered by Gemma 4
Gemma Chat is a local-first AI chat and coding assistant designed to run fully on-device, particularly optimized for Apple Silicon machines. It leverages Google’s Gemma family of lightweight language models, which are built on the same underlying technology as Gemini and designed for efficient local inference and reasoning tasks. The project enables users to interact with AI through a chat interface while also supporting code generation and editing workflows. It emphasizes privacy and independence by avoiding cloud dependencies, allowing all interactions and data to remain local. The system integrates model selection and execution directly into the app, giving users control over performance and behavior. It is particularly aligned with the “vibe coding” approach, where users iteratively build and modify projects through conversational prompts. Overall, gemma-chat provides a streamlined, developer-focused environment for local AI experimentation and productivity. -
8
OpenMonoAgent
Terminal-native coding agent powered by local LLMs
OpenMonoAgent.ai is a self-hosted coding agent designed to run entirely on the user’s own hardware. It pairs a .NET CLI with a local llama.cpp inference server so developers can use agentic coding workflows without cloud subscriptions or per-token billing. The project emphasizes privacy, local control, and ownership of the model, compute, and project data. It includes a terminal-native workflow, built-in tools, Docker sandboxing, and code intelligence features. The system can run on CPU or GPU and is designed to auto-configure itself when possible. OpenMonoAgent.ai is best suited for developers who want a local AI development stack with no API keys, no cloud dependency, and no telemetry. -
9
kimaki
Like openclaw but on top of opencode. all opencode features
Kimaki is an AI-powered developer tool that integrates coding workflows directly into Discord, allowing users to control and automate code editing sessions through natural language messages. Acting as a bridge between Discord and an AI coding agent (via OpenCode), it enables developers to interact with their codebase conversationally, effectively turning Discord into a collaborative development interface. Each Discord channel is mapped to a specific project directory, and messages sent within that channel trigger AI-driven actions such as editing files, running commands, or searching the codebase. The system is designed to streamline development workflows by eliminating context switching between communication tools and coding environments. Kimaki supports both quick setup through a shared bot and more advanced self-hosted configurations, offering flexibility for different user needs. -
Secure File Transfer for Windows with Cerberus by RedwoodCerberus supports unlimited users and connections on a single IP, with built-in encryption, 2FA, and a browser-based web client — all deployable in under 15 minutes with a 25-day free trial.
-
10
Open SWE
Open source async coding agent that plans, codes, and opens PRs
Open SWE is an open source asynchronous coding agent designed to automate software engineering workflows across entire repositories. Built with LangGraph, it can understand a codebase, generate a structured plan, and execute code changes from start to finish without constant human intervention. It operates in a cloud-based environment where tasks are processed asynchronously, allowing multiple coding jobs to run in parallel in isolated sandboxes. It integrates directly with development workflows by responding to triggers from tools like GitHub, enabling users to initiate tasks through issues or comments. Open SWE is capable of creating commits and automatically opening pull requests once implementation is complete, effectively closing the loop on development tasks. It also supports interactive feedback during execution, allowing users to guide or adjust the process mid-task. Despite its advanced capabilities, the project has been officially marked as deprecated. -
11
deepclaude
Use Claude Code's agent loop with DeepSeek V4 Pro, OpenRouter & more
deepclaude is a lightweight proxy tool that enables developers to run Claude Code’s autonomous coding agent loop using alternative AI backends like DeepSeek V4 Pro, OpenRouter, or other Anthropic-compatible models. It preserves the full Claude Code experience—including file editing, terminal execution, and multi-step agent workflows—while dramatically reducing operational costs. By swapping out the underlying model instead of the interface, deepclaude delivers the same familiar UX with significantly cheaper token pricing. The platform supports seamless backend switching in real time, allowing users to choose between cost efficiency and higher reasoning power when needed. It also includes built-in cost tracking and benchmarking tools to help developers monitor usage and optimize performance. Designed for flexibility and efficiency, deepclaude is ideal for developers who want powerful AI coding agents without the premium price tag. -
12
Every Code
Local AI coding agent CLI with multi-agent orchestration tools
Every Code (often referred to simply as Code) is a fast, local AI-powered coding agent designed to run directly in the terminal environment. It is a community-driven fork of the Codex CLI, with a strong emphasis on improving real-world developer ergonomics and workflows. Every Code enhances the traditional coding assistant model by introducing multi-agent orchestration, allowing multiple AI agents to collaborate, compare solutions, and refine outputs in parallel. It supports integration with various AI providers, enabling users to route tasks across different models depending on their needs. Every Code also includes browser integration and automation capabilities, extending its usefulness beyond simple code generation into more complex development tasks. Customization is a key focus, with support for theming, configurable settings, and reasoning controls that allow developers to fine-tune how the agent behaves. -
13
Fulling
Full-stack Engineer Agent. Built with Next.js, Claude, shadcn/ui
Fulling is an open-source AI-powered development environment designed to function as an autonomous full-stack engineering assistant. The platform provides a sandboxed workspace where developers can build complete applications with the help of an integrated AI coding agent. Instead of manually configuring development environments, the system automatically provisions the required infrastructure including a Linux environment, database services, and development tools. It integrates an AI pair programmer that can generate code, implement features, and assist with debugging tasks through natural language instructions. The environment also includes web-based terminals, file management tools, and version control capabilities to support collaborative software development workflows. Developers can connect external services by simply providing API credentials, allowing the AI system to automatically integrate features such as authentication or payment processing. -
14
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. -
15
.NET Agent Skills
Repository for skills to assist AI coding agents with .NET and C#
.NET Agent Skills is Microsoft’s curated skill repository for helping AI coding agents work more accurately with .NET and C# projects. It provides structured knowledge packs and custom agents that guide coding assistants through common development, debugging, migration, build, package, and performance tasks. The repository covers core .NET work as well as more specialized areas such as Entity Framework, MSBuild, NuGet, .NET upgrades, .NET MAUI, and AI-related .NET development. Its purpose is to reduce trial and error by giving agents task-specific context and repeatable workflows. The project also includes evaluation and dashboard support to track skill performance over time. It is best suited for developers who use AI coding tools and want better results on real .NET codebases. -
16
ByteRover CLI
The portable memory layer for autonomous coding agents
ByteRover CLI is a portable memory layer for autonomous coding agents. It gives developers a way to store, organize, and reuse project knowledge across coding tools and sessions. The project centers on a context tree that can capture important information about a codebase, decisions, patterns, and instructions. It can run as an interactive command-line experience and connect to an LLM of the user’s choice. ByteRover is useful when agents need persistent context instead of starting from scratch every time they enter a project. Its main value is making agent memory more structured, shareable, and practical across teams, tools, and long-running development workflows. -
17
CUDA Agent
Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
CUDA Agent is a research-driven agentic reinforcement learning system designed to automatically generate and optimize high-performance CUDA kernels for GPU workloads. The project addresses the long-standing challenge that efficient CUDA programming typically requires deep hardware expertise by training an autonomous coding agent capable of iterative improvement through execution feedback. Its architecture combines large-scale data synthesis, a skill-augmented CUDA development environment, and long-horizon reinforcement learning to build intrinsic optimization capability rather than relying on simple post-hoc tuning. The system operates in a ReAct-style loop where the agent profiles baseline implementations, writes CUDA code, compiles it in a sandbox, and iteratively refines performance. CUDA-Agent has demonstrated strong benchmark results, achieving high pass rates and significant speedups compared with compiler baselines such as torch.compile. -
18
GSD Pi
Development system that enables agents to work for long periods
GSD Pi is a local-first coding agent for planning, implementing, verifying, and tracking software project work from the command line. It is built for developers who want an AI-assisted workflow that can handle structured tasks rather than only single chat prompts. The project emphasizes spec-driven development, context engineering, and longer autonomous work sessions. It helps users break ideas into plans, manage execution steps, verify results, and keep track of progress across a project. Because it runs as a command-line tool, it fits naturally into developer environments and repository-based workflows. Its main value is turning AI coding assistance into a more organized project system with planning, task management, and implementation support. -
19
LazyCodex
The one and only agent harness for complex codebases
LazyCodex is an agent harness for using Codex on complex software projects. It is designed to add structure around AI coding sessions through memory, planning, execution, verification, skills, hooks, routing, and diagnostics. The project helps developers move beyond one-off prompts by giving the agent a more organized workflow inside a codebase. It supports project memory so context can persist across sessions and decisions do not need to be repeatedly reintroduced. LazyCodex also emphasizes verified completion, which means the workflow is built around checking whether tasks are actually finished rather than only generating code. Its main value is turning Codex into a more disciplined coding agent environment for larger and more demanding repositories. -
20
Nanocoder
A beautiful local-first coding agent running in your terminal
Nanocoder is an open-source, local-first coding assistant that runs in the command line and allows developers to use AI models to assist with programming tasks directly from their terminal environment. The tool is designed as a privacy-focused alternative to proprietary AI coding assistants, allowing users to run local models or connect to external APIs while keeping full control over their data and development workflow. Built with TypeScript and distributed as a CLI application, nanocoder enables developers to interact with AI agents that can read files, modify code, execute commands, and assist with debugging tasks. The platform supports multiple AI providers through OpenAI-compatible APIs and can also integrate with local model runtimes such as Ollama or LM Studio. Its architecture emphasizes extensibility through custom commands and integration with Model Context Protocol servers that allow the AI agent to access additional tools. -
21
AutoCoder
A long-running autonomous coding agent powered by the Claude Agent
Autocoder is an experimental auto-generation engine that transforms high-level prompts or structured descriptions into functioning source code, models, or systems with minimal manual intervention. Rather than hand-writing boilerplate or repetitive patterns, users supply a specification—such as a description of a feature, a function prototype, or a module outline—and Autocoder fills in complete implementations that compile and run. It is built to support iterative refinement: after generating an initial draft, you can provide feedback or corrections, and the system will adjust the output to match evolving intentions. The core idea is to accelerate software production while preserving correctness and readability, minimizing the cognitive overhead that comes from switching between concept and implementation. Its architecture typically integrates language models with static analysis and template logic so that generated code is not only syntactically valid but also idiomatic and testable. -
22
Kodu
Kodu is an autonomous coding agent that lives in your IDE
Claude Coder is an open-source developer environment that integrates Anthropic’s Claude models directly into the coding workflow, functioning as a local or hosted AI pair programmer. It provides conversational and in-line code assistance, helping developers write, refactor, and debug code through context-aware interactions. The system runs through a local interface or within VS Code and other editors, maintaining privacy by keeping context on-device when possible. Claude Coder supports large-context interactions, enabling the AI to process entire repositories or multi-file structures rather than isolated snippets. It includes conversation history, diff previews, and code-generation templates for repetitive tasks. The project also focuses on openness—developers can extend it with plugins, API configurations, and custom model backends to use Anthropic’s Claude or other compatible LLM APIs. -
23
Letta Code
The memory-first coding agent
Letta Code is a memory-first CLI coding agent built on the Letta platform that offers developers a persistent AI assistant capable of learning and improving over time rather than resetting state each session, giving agents a sense of continuity and context across coding tasks. Unlike traditional session-based coding tools, Letta Code attaches a long-lived agent to a working directory so that the agent accumulates memory about a project’s structure, preferences, and history, effectively acting as a collaborative partner rather than a stateless helper. Users can initialize and connect the agent to various models, including popular large language models, and issue commands, refactor code, or ask context-aware questions directly in the terminal, with memory retained across multiple interactions. -
24
Open Vibe
Open Vibe turns Claude Code into a SaaS-building assistant
Open Vibe is an open-source course and agent workflow that turns Claude Code, Codex, Copilot, Open Code, or another terminal-capable AI coding agent into a SaaS-building assistant. It is built around Open SaaS, a free Wasp-powered SaaS boilerplate, so learners can create a real app while understanding the architecture behind production-ready SaaS systems. The workflow starts with setup instructions that install Node.js, install the Wasp CLI, and verify the local environment. After creating a new Wasp app, the user opens an AI coding agent inside the project and lets it fetch course module instructions. The agent then works as both tutor and pair programmer, explaining the system while helping the user build features from plain-language requests. Progress is tracked through JSON files written into the project, making the learning path structured while still letting the user build their own app idea. -
25
nanocode
Minimal Claude Code alternative. Single Python file, zero dependencies
nanocode is a minimalist coding agent implementation designed as a compact alternative to Claude Code, packaged in a single Python file with no external dependencies and totaling around 250 lines of code. It implements a full agentic loop where the model can reason, decide when to use tools, execute those tools, and iterate until producing a final answer, making it useful for simple AI-assisted coding workflows. It includes a set of integrated tools such as read, write, edit, glob, grep, and bash that let the agent interact with the file system and shell commands directly from the terminal, and it keeps a conversation history with colored terminal output for readability. The project exemplifies how lightweight architectures can still support practical agent workflows without complex infrastructure, making it suitable for developers exploring agent frameworks or building custom coding assistants.