Open Source AI Coding Agents - Page 2
Sort By:
AI Coding Agents
View 200 business solutions-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
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
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. -
2
Dao Code
Open-source TypeScript terminal coding agent for DeepSeek-V4
Dao Code is an open-source terminal-native AI coding assistant built around DeepSeek V4 and a cost-conscious agent architecture. It reads code, writes code, runs commands, fixes bugs, and streams tool usage inside the terminal. The project emphasizes byte-stable prompts, prefix-cache reuse, and low-cost reflection or memory forks so longer coding sessions can remain affordable. It also includes cross-session memory that verifies saved facts against the current codebase instead of blindly trusting old context. Dao Code supports approval gates, slash commands, skills, MCP tools, hooks, custom subagents, permissions, crash recovery, shadow-git checkpoints, and autonomous long-task mode. It is aimed at developers who want a Claude Code-like workflow with stronger mainland China availability and DeepSeek-first economics. -
3
Happy Coder
Mobile and Web client for Codex and Claude Code, with realtime voice
Happy is an open-source, cross-platform mobile and web client designed to bring powerful AI coding agents such as Claude Code and Codex to your fingertips no matter where you are. At its core, Happy wraps existing AI coding tools with a unified interface, providing real-time voice interactions, encrypted communication, and seamless device switching between desktop and mobile. You can start a coding session locally through the Happy CLI or connect from a phone or browser, allowing developers to inspect, interact with, and guide the AI as it generates, tests, or explains code. The project includes components like a dedicated backend server for encrypted sync, a rich front-end experience across web and native apps, and support for push notifications when your coding agent encounters permission requests or errors. Happy prioritizes security with end-to-end encryption so your code and interactions remain private and auditable. -
4
Ornith-1.0
Ornith-1.0 is a self-improving open-source models for agentic coding
Ornith-1 is an open-source family of agentic coding models from DeepReinforce AI. It is designed for coding agents that need to solve software engineering tasks through iterative tool use and solution rollouts. The project presents 9B dense, 31B dense, 35B mixture-of-experts, and 397B mixture-of-experts variants. These models are post-trained on top of Gemma 4 and Qwen 3.5 foundations. Its training approach uses reinforcement learning to optimize both the solution and the scaffold that guides the solution process. The repository emphasizes benchmark performance on Terminal-Bench, SWE-bench, NL2Repo, OpenClaw, and SWE Atlas while keeping the project MIT licensed and globally accessible. -
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.
-
5
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. -
6
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. -
7
.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. -
8
AutoBE
AI Vibe Coding Agent of TS backend server
AutoBE is an AI backend builder that turns natural-language requirements into a working TypeScript backend application. It analyzes what the user wants, creates specifications, designs database structure, defines API documentation, writes end-to-end tests, and generates implementation logic. The project is aimed at moving from prototype to production more quickly while keeping generated code buildable and verifiable. It uses an agentic workflow supported by compiler-friendly checks and test generation, which helps reduce the risk of incomplete AI output. AutoBE can be explored through a local playground where users chat with agents and manage sessions. Its main value is giving developers and non-programmers a structured way to generate backend systems from requirements while still producing documentation and tests. -
9
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. -
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
10
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. -
11
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. -
12
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. -
13
pool
pool is Poolside’s coding agent that runs in your terminal
pool is Poolside’s coding agent for terminal and editor-based development workflows. It can run as a standalone interactive terminal app, as an ACP server for compatible editors, as an ACP client connected to another agent server, or non-interactively through command execution. The tool supports slash commands, file and directory fuzzy search, shell mode, message rewind, and configurable approval modes. It integrates with open agent specifications such as AGENTS.md, Skills, MCP, and ACP, making it adaptable to different coding environments. Developers can use it for interactive coding, scripted tasks, CI-style checks, project analysis, and agent-assisted implementation. Its main value is providing a flexible coding-agent interface that can move between terminal use, editor integration, and automated execution. -
14
VT Code
VT Code - semantic AI coding agent
VTCode is a terminal-based AI coding agent designed to provide semantic code understanding and interactive assistance directly within a command-line environment. It is implemented in Rust and focuses on performance, portability, and deep integration with developer workflows that rely on terminal tools. The system leverages syntax-aware parsing technologies such as tree-sitter and AST-based analysis to understand code structure rather than relying solely on raw text, which enables more accurate and context-aware suggestions. VTCode operates as an agent rather than a simple autocomplete tool, meaning it can interpret user intent, navigate codebases, and assist with multi-step tasks. It is highly configurable, allowing developers to define behavior, prompts, and workflows tailored to their projects. The tool is especially useful for developers who prefer lightweight, local-first environments but still want advanced AI assistance comparable to modern IDE-based tools. -
15
Codey
The home for Codey releases, updates, and the developer community
Codey Community is the public release, documentation, and collaboration hub for Codey, an AI coding agent built for terminal-first development. Codey combines a fast keyboard-driven TUI with a cross-platform desktop app for developers who want AI assistance close to their coding workflow. It can help read, write, refactor, and inspect code while also running commands and coordinating multi-step engineering tasks. The project uses the Model Context Protocol to connect agent workflows with external tools and richer development context. This repository does not contain the private application source, but it hosts releases, installers, updater metadata, guides, prompts, skills, workflows, issues, and discussions. It is useful for developers who want to install Codey, follow updates, contribute resources, or participate in the project community. -
16
RunVSAgent
Run VSCode-based coding agents and extensions seamlessly
RunVSAgent is a cross-platform development tool that lets VS Code-based coding agents and extensions run inside JetBrains IDEs and other IDE environments. It is designed to bridge the VS Code agent ecosystem with editors such as IntelliJ IDEA, WebStorm, PyCharm, PhpStorm, CLion, GoLand, Rider, Android Studio, and more. The project uses a Kotlin-based JetBrains plugin, a Node.js extension host, an editor bridge, and RPC communication to provide VS Code API compatibility outside VS Code. It supports agents such as Roo Code, Cline, and Kilo Code, making them available in IDEs where they would not normally run. This helps developers keep their preferred IDE while still using popular VS Code-native AI coding tools. Its main value is creating a compatibility layer between coding agents, extensions, and different development environments. -
17
Gemini CLI
Open source AI agent CLI tool to bring Gemini into your terminal
Gemini CLI is an open‑source AI agent that brings the capabilities of Google’s Gemini 2.5 Pro large‑language model directly into your terminal, enabling tasks ranging from coding and debugging to content creation and research via natural‑language prompts, with support for multimodal outputs like image and video generation. Gemini CLI integrates with external tools and MCP servers, enabling media generation and enhanced workflow automation. It also includes a built-in Google Search tool to ground queries with relevant information. Users can authenticate with their Google accounts for free usage limits or configure API keys for higher capacity and access to specific models. The tool is designed to be easy to install and use, with extensive documentation and community support for troubleshooting and advanced workflows. -
18
Junie
An AI coding agent by JetBrains that ships code from your terminal
Junie is an AI coding agent from JetBrains designed to help developers build, review, and ship code from the terminal, IDE, or CI/CD pipeline. It allows users to give development tasks in natural language, such as fixing bugs, implementing features, reviewing pull requests, or improving tests. Junie is LLM-agnostic, meaning it can work with different model providers, including JetBrains authentication, Junie API keys, or bring-your-own-key options. The tool integrates with real-world development workflows and can assist across local projects, repositories, and automated GitHub processes. Developers can use Junie through multiple release channels, including stable, EAP, nightly, and experimental builds. Its focus on practical coding automation makes it a useful assistant for speeding up software development while fitting into existing tools and workflows. -
19
Gajae-Code
Gajae Code MVP
Gajae-Code is an experimental coding-agent harness focused on structured planning, reviewable execution, and durable verification. It runs beside existing tools rather than hiding inside a specific agent runtime, so users can apply it to a chosen repository or isolated worktree. The workflow is built around clarifying requirements, planning before mutation, turning approved plans into goals, and tracking evidence until completion. It includes tmux-backed execution options for coordinating parallel workers when a task is large enough to benefit from them. Gajae-Code is useful for developers who want coding agents to behave less like single-prompt assistants and more like disciplined project collaborators. Its main value is giving AI coding work a clearer loop for interviews, plans, goals, execution checks, and evidence. -
20
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. -
21
Prime Agent
A self-improving RLM agent for coding workflows
Prime Agent is an open-source coding and research agent designed for complex workflows and long-running autonomous tasks. Its Recursive Language Model architecture treats context as programmable variables and subagents as callable functions inside a persistent Python environment. Files, shell commands, tools, context operations, and agent coordination are handled programmatically through the same runtime. Built-in subagents can work in parallel or continue tasks independently while returning results to a parent agent. A continual harness stores memories, skills, prompts, and reusable agent specifications that can improve through evidence-backed refinement. Daemon-backed sessions survive terminal disconnections and can be resumed later. Automatic compaction, persistent goals, schedules, heartbeats, and autonomous execution help maintain progress across extended tasks. -
22
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. -
23
skills-manage
Desktop app to manage AI coding agent skills across Claude Code
skills-manage is a Tauri desktop application for organizing AI coding agent skills across many local development tools from one interface. It uses a central skills library as the main source of truth, then installs skills into specific platforms through per-tool workflows. The app is designed for users who work with multiple AI coding agents and want consistent skills across environments such as Claude Code, Codex, Cursor, Gemini CLI, and many others. It provides detail views with Markdown previews, raw source views, AI-generated explanations, collections, marketplace browsing, and GitHub repository import. It also scans local projects for skill libraries, including project-level folders and Obsidian-style vaults. Its local-first design keeps metadata, collections, settings, scan results, and cached explanations on the user’s machine unless a feature explicitly requires network access. -
24
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. -
25
Grok Build
SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive
Grok Build is a terminal-based AI coding agent that operates through a full-screen text interface. It can inspect repositories, edit files, run shell commands, search the web, and coordinate longer development tasks. Users can work interactively, invoke it headlessly in scripts or CI, or connect it to editors through the Agent Client Protocol. The Rust codebase includes separate components for the interface, agent runtime, tools, workspace control, configuration, and sandboxing. It also supports MCP servers, skills, plugins, hooks, themes, checkpoints, and slash commands. Prebuilt binaries are available for macOS, Linux, and Windows, while the source can be compiled with the pinned Rust toolchain.
