Open-Source Terminal Coding Agents

Docker Agent runs individual AI agents or teams from configuration files. Developers can use it for coding assistants, research tasks and automation workflows.

Goose is a general-purpose AI agent for people who want help with coding, research, writing, automation or data analysis. It runs on your computer and lets you choose the model provider behind the agent.

Cline is an AI coding agent for developers who want help understanding a codebase, making changes and running project tasks. It works in VS Code, JetBrains IDEs and the terminal, with a standalone desktop app for macOS, Windows and Linux.

Herdr manages persistent terminals for developers running coding agents across projects and machines. Closing its client or losing an SSH connection leaves work running on the host, so you can reconnect later.

Free Claude Code lets developers use coding agents with local models or a choice of cloud providers. It connects existing clients to a shared model catalog rather than requiring a separate coding workflow.

Gemini CLI is a coding assistant for developers who want to work with an AI agent in their terminal. It can inspect a codebase and act on files and shell commands, with Gemini handling the model responses in Google's cloud.

Mini SWE Agent is a command-line AI coding assistant for developers tackling GitHub issues and everyday coding tasks. Its small Python core also suits researchers who want to inspect and modify an agent for model evaluations.

kodo coordinates coding agents for developers who have a clear goal and want work to continue unattended for hours. It divides implementation and review across agents and multiple context windows.

Continue is a coding agent for developers working in a terminal, VS Code or JetBrains. Its Ollama integration can run models on your computer; Standard OpenAI and Anthropic service connections use cloud models. The repository is read-only and no longer actively maintained.

iCode is a terminal development workspace for developers who want to work with AI agents and inspect their changes. It brings conversations, agent workflows and a working shell into one interface.

Pi Interactive Shell lets developers give the Pi coding agent control of terminal programs that need ongoing input. You can watch the session in an overlay and take control when a task needs your attention.

Claudio coordinates multiple Claude Code sessions on one repository. It's for developers who want agents to tackle separate coding tasks in parallel, with each session working on its own branch.

Potpie's open-source CLI gives developers and coding assistants a local store of project context, backed by a daemon and a browser graph explorer. It's for teams that need agents to understand code alongside engineering decisions and project history. With Claude Code’s standard cloud connection, prompts and model outputs travel to a remote model provider over the network.

Apache Maka is an AI agent workspace for people who want an agent to work on tasks on their machine and keep an inspectable record of its actions. It suits developers who need to review commands, file edits and approvals, or continue work after an interruption.

Klaat Code is a terminal AI coding agent for developers who want an assistant to read code, make changes, and run commands in their projects. Its default model routing runs through hosted Klaatu, which receives your messages; file edits and shell commands happen on your machine.

RSI Harness builds on the Pi coding agent for developers and researchers who want to version and share tailored agent setups. It collects each setup into a local directory bundle called a Genome.

Kolega Code is a local-first AI coding assistant for developers working in the terminal or an editor. Its Gigacode engine lets a model write a Python workflow to coordinate sub-agents for repository reviews, migrations and tasks with independent workstreams. You can inspect and rerun those workflows, including parallel work and separate verification steps.

Devon is an open-source AI coding agent that runs on your machine and works across files in a project. It's aimed mainly at Python developers who want help making code changes and investigating bugs, with the ability to redirect the agent while it works.

Kilo Code is an AI coding assistant for developers who want an agent to edit, explain, and debug a codebase in their editor or terminal. You can choose local models, connect a provider with your own API keys, or use Kilo's hosted model access.

Fast Agent is a terminal coding assistant and Python toolkit for developers building AI agents and automated workflows. You can choose local LLMs or hosted providers and use the same toolkit for interactive work, scripting, and evaluation.

ChatOllama is an AI agent app with a command-line interface for people who want to use local models or hosted services from the same client. It discovers available models from connected providers, including installed models at an Ollama endpoint.

Grok Build is a terminal coding assistant whose runtime edits files and executes commands on your computer. The default connection uses xAI’s remote inference service and needs network access and authentication. Browser login, device codes and API keys are supported, and organizations can configure third-party BYOK endpoints.

OpenHarness is a Python framework for developers and researchers building AI agents that can act on files, use tools and retain work across sessions. It includes ohmo, a personal agent that handles coding tasks through Feishu, Slack, Telegram or Discord.

Qwen Code is an AI coding assistant for developers who want an agent to review code, fix bugs and carry out work in a project. You can use it in a terminal, editor, desktop app or browser.

Instrukt is a terminal app for developers who want to build and test AI agents on their own machine or server. It can index local code and documents, but its chat models run through OpenAI's API, which requires an API key and internet access. It doesn't provide local chat inference.

avante.nvim adds AI coding assistance to Neovim for developers who want code questions and suggested edits inside their existing editor. It lets you choose a model backend and apply recommendations directly to source files.

Plasma Fractal coordinates autonomous coding agents working in a Git repository. It's for developers delegating substantial tasks that agents can divide into smaller pieces as the work progresses.

Orbi is a self-hosted AI coding agent for developers and teams who want GitHub backlog tasks carried through to reviewed pull requests and tagged releases. It runs on Linux or macOS, on your own computer or server. The macOS launchd scheduler is documented but has not yet been verified on real hardware. The open source core is free under AGPL-3.0.

Agents Studio manages Claude Code work on your repositories for developers who want tasks to run while they're away. It brings unattended runs and the tools to review and finish their changes into one interface.

Kimi Code CLI is a locally installed AI coding agent for developers who want an agent to work directly on their projects. File edits and shell commands run on your computer; its default Kimi connection sends model requests to Moonshot AI's hosted API. That connection needs internet access and Kimi Code OAuth or an API key.

Mercury Agent is a personal AI agent for people who want ongoing help with coding, research and routine tasks. It keeps context between conversations and can continue working in the background after you close the terminal.

Pydantic DeepAgents is a terminal coding assistant and Python framework for developers who want to use or build their own AI agents. Both share a Pydantic AI foundation for carrying out tasks across files and tools.

Pi Messenger connects Pi coding agent sessions working in separate terminals on the same project. It's for developers who want agents to divide work, share progress and avoid conflicting edits.

Omnigent coordinates AI agents for developers and teams who want to combine coding assistants, control their access, and supervise work in shared sessions. It runs locally or on a self-hosted server, with remote cloud sandboxes as another option.