A DeepSeek-native AI coding agent for your terminal, designed for stable long-running autonomous sessions.
DeepSeek-Reasonix is worth checking the docs before setup with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view esengine/DeepSeek-Reasonix --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
Repository setup guidance
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 24 days ago.
34683 GitHub stars indicate community interest.
1470 open issues signal maintenance load.
MIT license detected.
3 security/trust notes recorded.
Setup difficulty is 3/5.
Run large language models locally with a simple CLI. Supports Llama, Mistral, Gemma, and 100+ models with one command.
A public repository of example skills for Claude, demonstrating how to create reusable instructions and resources for specialized tasks.
The leading open-source AI code assistant for VS Code and JetBrains. Connect any model, customize your workflow.
Anthropic's official CLI agent for coding. Claude-powered terminal agent that reads, writes, and refactors entire codebases.
DeepSeek-Reasonix is a coding agent that runs in your terminal and helps you write code using AI. It is built to stay running for a long time without problems, so you can let it work on tasks while you do other things. It has features like plan mode, permissions, and checkpoints to keep you in control.
DeepSeek-Reasonix is an open-source, MIT-licensed AI coding agent that runs as a single Go binary. It is engineered around prefix-cache stability, meaning it is optimized to keep context caching efficient during long autonomous runs. The agent provides four ways to interact: terminal, desktop app, browser, and editor integration via the Agent Client Protocol (ACP). Key features include plan mode for step-by-step execution, a permission system to control actions, a workspace sandbox for safe experimentation, and per-turn checkpoints that allow you to review and undo changes. It is designed to be a coding agent you can leave running, making it suitable for complex, multi-step tasks. The project is actively developed with a large community and supports extensions and plugins.
34,683
Stars
2,304
Forks
1,470
Issues
MIT
License
A DeepSeek-native AI coding agent for your terminal, designed for stable long-running autonomous sessions.
Developers who want an AI coding agent that can run autonomously for long periods., Teams looking for an open-source, self-hosted alternative to commercial coding agents., Power users who prefer terminal-based tools and want deep control over AI actions.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
As with any AI coding agent, generated code may contain bugs or security vulnerabilities; review before deployment. The agent can execute commands and modify files; ensure permissions are configured to limit scope.
Similar or complementary options to evaluate include Ollama, anthropic-skills, Continue.
Aug 20, 2026